build-your-own-x
Master programming by recreating your favorite technologies from scratch.
- 564k
- Markdown
- 2 d ago
๐ Hand-picked awesome Python libraries and frameworks, organised by category
Repo dylanhogg/awesome-python, read from GitHub 2 h ago. dylanhogg has not joined Take My Repo.
dylanhogg/awesome-python is a public repo on GitHub by dylanhogg. ๐ Hand-picked awesome Python libraries and frameworks, organised by category. It declares the MIT license on GitHub. It has 470 stars and last changed on 2026-11-04. Nobody has reviewed it on Take My Repo yet, which says nothing about its quality. Read from GitHub on 2026-11-21.
A link is a mention. It does not prove the project needs that model to run.
In the maintainer's words. Shown from GitHub; Take My Repo does not keep a copy.
Hand-picked awesome Python libraries and frameworks, organised by category ๐
Interactive version: www.awesomepython.org
Updated 04 Nov 2026 with 1,515 repos
Awesome Python is regularly updated, and this category lists the most recently created GitHub repositories from all the other repositories here.
google-research/harness2 โญ 22,436
Harness2 is a plug-and-play framework for recursive agent harnessing in an open world, where agents encounter tasks unseen during harness design.
nandhakishorm/laya โญ 20,688
Non-autoregressive System 1 decision engine. Typed choice, score and yes/no decisions over any text in a single forward pass, in 100+ languages, with a router that picks the right checkpoint per request.
๐ huggingface.co/convaiinnovations/laya
deepseek-ai/dsh-superagent-prototype โญ 16,685
A proactive coding agent for one GitHub repository, packaged as a bundle for DeepSeek Harness.
jaredpalmer/kev โญ 6,080
tiny Jev-like family of decision models built on top of Qwen3.5 you can train and run on your own
nvidia-nemo/labs-OO-Agents โญ 2,305
NVIDIA Object Oriented Agents: the Pythonic way to build AI Agents.
tianyucodings/NanoJev โญ 2,125
A nano replica of Jev: parallel decisions, dynamic candidates, and an end-to-end training pipeline.
bespokelabsai/nimble โญ 1,690
Local typed decisions, contrastive data curation, and model evaluation.
mhviraf/ai-lobotomy โญ 36
Find and dose the "personality neurons" of a Qwen model
auto-index/autoindex โญ 19
Implementation for AutoIndex: Learning Representation Programs for Retrieval
๐ autoindex-one.vercel.app
hanxiao/jina-reranker-v3.5-in-page-search โญ 12
Ask a web page a question and highlight the answer in place, with one listwise jina-reranker-v3.5 call. No index, no vector store. Runs locally on Apple Silicon via MLX.
Agentic AI libraries, frameworks and tools: AI agents, workflows, autonomous decision-making, goal-oriented tasks, and API integrations.
obra/superpowers โญ 290,723
An agentic skills framework & software development methodology that works.
nousresearch/hermes-agent โญ 248,428
The self-improving AI agent built by Nous Research. It's the only agent with a built-in learning loop โ it creates skills from experience, improves them during use
๐ hermes-agent.nousresearch.com
multica-ai/andrej-karpathy-skills โญ 214,845
A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.
langgenius/dify โญ 156,892
Build Agentic workflows, RAG pipelines, with rich AI model and tool support on one collaborative workspace. Deploy on cloud, VPC, or self-hosted, so teams move from prototype to production without rebuilding the stack.
๐ dify.ai
logspace-ai/langflow โญ 155,125
Langflow is a powerful tool for building and deploying AI-powered agents and workflows.
๐ www.langflow.org
langchain-ai/langchain โญ 146,852
The agent engineering platform.
๐ docs.langchain.com/langchain
github/spec-kit โญ 138,415
Toolkit to help you get started with Spec-Driven Development: specifications become executable, directly generating working implementations
๐ github.github.com/spec-kit
safishamsi/graphify โญ 120,937
Turn any codebase, with its docs, SQL schemas, configs, and PDFs, into a queryable knowledge graph. A /graphify skill for Claude Code, Cursor, Codex, and Gemini CLI: local deterministic AST parsing, every edge explained, no vector store.
๐ www.graphify.com
browser-use/browser-use โญ 115,956
Browser use is the easiest way to connect your AI agents with the browser.
๐ browser-use.com
karpathy/autoresearch โญ 96,683
AI agents running research on single-GPU nanochat training automatically
bytedance/deer-flow โญ 82,868
An open-source long-horizon SuperAgent harness that researches, codes, and creates. With the help of sandboxes, memories, tools, skill, subagents and message gateway, it handles different levels of tasks that could take minutes to hours.
๐ deerflow.tech
geekan/MetaGPT โญ 70,550
๐ The Multi-Agent Framework: First AI Software Company, Towards Natural Language Programming
๐ atoms.dev
fission-ai/OpenSpec โญ 70,069
Spec-driven development (SDD) for AI coding assistants.
๐ openspec.dev
mem0ai/mem0 โญ 65,844
Enhances AI assistants and agents with an intelligent memory layer, enabling personalized AI interactions
๐ mem0.ai
microsoft/autogen โญ 61,107
AutoGen is a framework for creating multi-agent AI applications that can act autonomously or work alongside humans.
๐ microsoft.github.io/autogen
crewaiinc/crewAI โญ 58,895
Framework for orchestrating role-playing, autonomous AI agents. By fostering collaborative intelligence, CrewAI empowers agents to work together seamlessly, tackling complex tasks.
๐ crewai.com
run-llama/llama_index โญ 52,274
LlamaIndex is the document processing platform for AI
๐ developers.llamaindex.ai
blader/humanizer โญ 51,685
Agent skill that removes signs of AI-generated writing from text
๐ skills.sh/blader/humanizer
agno-agi/agno โญ 42,306
Build, run, and manage agent platforms.
๐ docs.agno.com
langchain-ai/langgraph โญ 42,129
LangGraph is a library for building stateful, multi-actor applications with LLMs, built on top of (and intended to be used with) LangChain.
๐ docs.langchain.com/oss/python/langgraph
anthropics/financial-services โญ 36,982
Reference agents, skills, and data connectors for the financial-services workflows: investment banking, equity research, private equity, and wealth management.
voltagent/awesome-agent-skills โญ 34,786
A curated collection of 1000+ agent skills from official dev teams and the community, compatible with Claude Code, Codex, Gemini CLI, Cursor, and more.
๐ officialskills.sh
openbmb/ChatDev โญ 34,364
ChatDev stands as a virtual software company that operates through various intelligent agents holding different roles, including Chief Executive Officer, Chief Product Officer etc
๐ arxiv.org/abs/2307.07924
agentscope-ai/agentscope โญ 32,185
Build and run agents you can see, understand and trust.
๐ docs.agentscope.io
stanford-oval/storm โญ 31,475
An LLM-powered knowledge curation system that researches a topic and generates a full-length report with citations.
๐ storm.genie.stanford.edu
composiohq/composio โญ 30,288
Composio powers 1000+ toolkits, tool search, context management, authentication, and a sandboxed workbench to help you build AI agents that turn intent into action.
๐ docs.composio.dev
langchain-ai/deepagents โญ 29,708
Deep Agents is an open source agent harness โ an opinionated agent that runs out of the box. Extend, override, or replace any piece.
๐ docs.langchain.com/deepagents
openai/openai-agents-python โญ 29,644
A lightweight yet powerful framework for building multi-agent workflows. It is provider-agnostic, supporting the OpenAI Responses and Chat Completions APIs, as well as 100+ other LLMs.
๐ openai.github.io/openai-agents-python
assafelovic/gpt-researcher โญ 29,565
An autonomous agent that conducts deep research on any data using any LLM providers
๐ gptr.dev
huggingface/smolagents โญ 29,454
๐ค smolagents: a barebones library for agents that think in code.
๐ huggingface.co/docs/smolagents
nutlope/hallmark โญ 29,092
A design skill for Claude Code, Cursor, and Codex that refuses to look AI-generated.
๐ www.usehallmark.com
fosowl/agenticSeek โญ 27,273
A 100% local alternative to Manus AI, this voice-enabled AI assistant autonomously browses the web, writes code, and plans tasks while keeping all data on your device.
๐ agenticseek.tech
browser-use/video-use โญ 26,530
Edit videos with coding agents
a2aproject/A2A โญ 25,895
Agent2Agent (A2A) is an open protocol enabling communication and interoperability between opaque agentic applications.
๐ a2a-protocol.org
microsoft/OmniParser โญ 25,440
OmniParser is a comprehensive method for parsing user interface screenshots into structured and easy-to-understand elements
titanwings/distilly โญ 24,997
Distilly โ Distill how they think into reusable Skills for any Agent or Bot. Formerly Colleague Skill๏ผๅๅไบ Skill๏ผ.
letta-ai/letta โญ 24,848
Letta (formerly MemGPT) is a framework for creating LLM services with memory.
๐ docs.letta.com
nirdiamant/GenAI_Agents โญ 24,367
Tutorials and implementations for various Generative AI Agent techniques, from basic to advanced. It serves as a comprehensive guide for building intelligent, interactive AI systems.
๐ diamant-ai.com
google-research/harness2 โญ 22,436
Harness2 is a plug-and-play framework for recursive agent harnessing in an open world, where agents encounter tasks unseen during harness design.
yoheinakajima/babyagi โญ 22,356
GPT-4 powered task-driven autonomous agent
๐ babyagi.org
openai/swarm โญ 22,005
A framework exploring ergonomic, lightweight multi-agent orchestration.
google/adk-python โญ 21,603
An open-source, code-first Python toolkit for building, evaluating, and deploying sophisticated AI agents with flexibility and control.
๐ google.github.io/adk-docs
google/skills โญ 20,325
Agent Skills for Google products and technologies
camel-ai/owl โญ 20,146
๐ฆ OWL: Optimized Workforce Learning for General Multi-Agent Assistance in Real-World Task Automation
pydantic/pydantic-ai โญ 20,121
PydanticAI is a Python Agent Framework designed to make it less painful to build production grade applications with Generative AI.
๐ pydantic.dev/pydantic-ai
alibaba-nlp/DeepResearch โญ 19,981
Tongyi Deep Research, the Leading Open-source Deep Research Agent
๐ tongyi-agent.github.io/blog/introducing-tongyi-deep-research
dzhng/deep-research โญ 19,717
An AI-powered research assistant that performs iterative, deep research on any topic by combining search engines, web scraping, and large language models.
unity-technologies/ml-agents โญ 19,696
The Unity Machine Learning Agents Toolkit (ML-Agents) is an open-source project that enables games and simulations to serve as environments for training intelligent agents using deep reinforcement learning and imitation learning.
๐ unity.com/products/machine-learning-agents
agent0ai/agent-zero โญ 19,252
Agent Zero AI framework
๐ agent-zero.ai
andrewyng/openworker โญ 18,886
An AI coworker that lives on your desktop and delivers finished work, not just chat: your code reviewed for vulnerabilities with fixes ready to go, a polished document, a Slack reply with the numbers, a triaged inbox.
๐ openworker.com
microsoft/agent-lightning โญ 18,445
A structured way to train your agents with Automatic Prompt Optimization (APO). Just like you train a machine learning model on data, you can train an agent on a task dataset.
๐ microsoft.github.io/agent-lightning
google-gemini/gemini-fullstack-langgraph-quickstart โญ 18,339
Demonstrates a fullstack application using a React and LangGraph-powered backend agent. The agent is designed to perform comprehensive research on a user's query.
๐ ai.google.dev/gemini-api/docs/google-search
emcie-co/parlant โญ 18,288
Build reliable customer-facing AI agents with Parlant: an interaction control harness optimized for controlled, consistent, and predictable LLM interactions.
๐ www.parlant.io
asyncfuncai/deepwiki-open โญ 18,044
Custom implementation of DeepWiki, automatically creates beautiful, interactive wikis for any GitHub, GitLab, or BitBucket repository
๐ grok-wiki.com
rowboatlabs/rowboat โญ 17,952
AI coworker with memory and collaboration
๐ www.rowboatlabs.com
camel-ai/camel โญ 17,757
๐ซ CAMEL: The first and the best multi-agent framework. Finding the Scaling Law of Agents. https://www.camel-ai.org
๐ docs.camel-ai.org
canner/WrenAI โญ 17,723
Gives the AI agents you already use (Claude Code, Cursor, MCP clients, LangChain) a governed semantic layer and an AI context layer
๐ www.getwren.ai/en/open-core
deepseek-ai/dsh-superagent-prototype โญ 16,685
A proactive coding agent for one GitHub repository, packaged as a bundle for DeepSeek Harness.
ag-ui-protocol/ag-ui โญ 15,993
AG-UI: the Agent-User Interaction Protocol. Bring Agents into Frontend Applications.
๐ ag-ui.com
kyegomez/OpenMythos โญ 14,905
A theoretical reconstruction of the Claude Mythos architecture, built from first principles using the available research literature.
๐ discord.gg/eamjgsaeqf
sakanaai/AI-Scientist โญ 14,601
The AI Scientist, the first comprehensive system for fully automatic scientific discovery, enabling Foundation Models such as Large Language Models (LLMs) to perform research independently.
aiming-lab/AutoResearchClaw โญ 14,516
Fully autonomous & self-evolving research from idea to paper. Chat an Idea. Get a Paper. ๐ฆ
piebald-ai/claude-code-system-prompts โญ 12,755
All parts of Claude Code's system prompt, 27 builtin tool descriptions, sub agent prompts (Plan/Explore/Task), utility prompts (CLAUDE.md, compact, statusline, magic docs, WebFetch, Bash cmd, security review, agent creation). Updated for each Claude Code version.
langchain-ai/open_deep_research โญ 12,683
Open Deep Research is an open source assistant that automates research and produces customizable reports on any topic
smol-ai/developer โญ 12,190
the first library to let you embed a developer agent in your own app!
๐ twitter.com/smolmodels
humanlayer/humanlayer โญ 11,599
HumanLayer is an API and SDK that enables AI Agents to contact humans for help, feedback, and approvals.
๐ humanlayer.dev/code
huggingface/ml-intern โญ 10,820
Archived โ ML Intern is no longer maintained. Continue with HuggingChat.
๐ huggingface.co/chat
omnigent-ai/omnigent โญ 10,192
Omnigent is an open-source AI agent framework and meta-harness: orchestrate Claude Code, Codex, Cursor, Pi, and custom agents โ swap harnesses without rewriting, enforce policies and sandboxing, and collaborate in real time from any device.
๐ omnigent.ai
microsoft/magentic-ui โญ 10,092
A prototype of a human-centered interface powered by a multi-agent system that can browse and perform actions on the web, generate and execute code
๐ www.microsoft.com/en-us/research/blog/magenticlite-magenticbrain-fara1-5-an-agentic-experience-optimized-for-small-models
nicobailon/visual-explainer โญ 9,906
Agent skill that generates rich HTML pages or slide decks for diagrams, diff reviews, plan audits, data tables, and project recaps
anthropics/claude-for-legal โญ 9,509
Reference agents, skills, and connectors for the legal workflows: in-house commercial, privacy, product, corporate, employment, litigation, regulatory
x-plug/MobileAgent โญ 9,238
Mobile-Agent: The Powerful GUI Agent Family
meta-llama/ogx โญ 8,437
Llama Stack standardizes the building blocks needed to bring genai applications to market. These blocks cover model training and fine-tuning, evaluation, and running AI agents in production
๐ ogx-ai.github.io
zilliztech/deep-searcher โญ 8,280
DeepSearcher combines reasoning LLMs and VectorDBs o perform search, evaluation, and reasoning based on private data, providing highly accurate answer and comprehensive report
๐ zilliztech.github.io/deep-searcher
upsonic/Upsonic โญ 7,958
Upsonic is a reliability-focused framework designed for real-world applications. It enables trusted agent workflows in your organization through advanced reliability features, including verification layers, triangular architecture, validator agents, and output evaluation systems.
๐ docs.upsonic.ai
swe-agent/mini-swe-agent โญ 7,890
The 100 line AI agent that solves GitHub issues or helps you in your command line
๐ mini-swe-agent.com
awslabs/agent-squad โญ 7,769
Flexible, lightweight open-source framework for orchestrating multiple AI agents to handle complex conversations
๐ 2fastlabs.github.io/agent-squad
strands-agents/harness-sdk โญ 7,566
Build an agent harness and control it end-to-end. Open-source SDK for production AI agents in Python & TypeScript - any model, any cloud.
๐ strandsagents.com
codelion/openevolve โญ 7,416
Evolutionary coding agent (like AlphaEvolve) enabling automated scientific and algorithmic discovery
plastic-labs/honcho โญ 7,319
Memory library for building stateful agents
๐ docs.honcho.dev
sakanaai/AI-Scientist-v2 โญ 7,206
The AI Scientist-v2: Workshop-Level Automated Scientific Discovery via Agentic Tree Search
kyegomez/swarms โญ 7,195
The Enterprise-Grade Multi-Agent Orchestration Framework. Website: https://swarms.ai
๐ docs.swarms.world
tw93/Waza โญ 7,082
๐ฅท Engineering habits you already know, turned into skills Claude can run.
mnotgod96/AppAgent โญ 6,888
AppAgent: Multimodal Agents as Smartphone Users, an LLM-based multimodal agent framework designed to operate smartphone apps.
๐ appagent-official.github.io
openai/openai-cs-agents-demo โญ 6,574
Demo of a Customer Service Agent interface built on top of the OpenAI Agents SDK
samsungsailmontreal/TinyRecursiveModels โญ 6,561
A recursive reasoning model that achieves amazing scores ARC-AGI-1 and ARC-AGI-2 with a tiny 7M parameters neural network
microsoft/agent-governance-toolkit โญ 6,324
AI Agent Governance Toolkit โ Policy enforcement, zero-trust identity, execution sandboxing, and reliability engineering for autonomous AI agents. Covers 10/10 OWASP Agentic Top 10.
brainblend-ai/atomic-agents โญ 6,255
Atomic Agents provides a set of tools and agents that can be combined to create powerful applications. It is built on top of Instructor and leverages the power of Pydantic for data and schema validation and serialization.
๐ eigenwise.github.io/atomic-agents
prefecthq/marvin โญ 6,198
an ambient intelligence library
๐ marvin.mintlify.app
crewaiinc/crewAI-examples โญ 6,149
A collection of examples that show how to use CrewAI framework to automate workflows.
vllm-project/semantic-router โญ 5,900
An Mixture-of-Models router that directs OpenAI API requests to the most suitable models from a defined pool based on Semantic Understanding
๐ vllm-sr.ai
pyspur-dev/pyspur โญ 5,789
A visual playground for agentic workflows: Iterate over your agents 10x faster
๐ pyspur.dev
landing-ai/vision-agent โญ 5,302
VisionAgent is a library that helps you utilize agent frameworks to generate code to solve your vision task
going-doer/Paper2Code โญ 4,964
A multi-agent LLM system that transforms paper into a code repository. It follows a three-stage pipeline: planning, analysis, and code generation, each handled by specialized agents.
ag2ai/ag2 โญ 4,953
AG2 (formerly AutoGen) is an open-source programming framework for building AI agents and facilitating cooperation among multiple agents to solve tasks.
๐ ag2.ai
getzep/zep โญ 4,927
Zep is a memory platform for AI agents that learns from user interactions and business data
๐ help.getzep.com
tencentcloudadp/youtu-agent โญ 4,615
A flexible, high-performance framework for building, running, and evaluating autonomous agents
๐ tencentcloudadp.github.io/youtu-agent
dimensionalos/dimos โญ 4,561
Dimensional is the agentic operating system for physical space. Command humanoids, quadrupeds, drones, and other hardware platforms in natural language and build multi-agent systems that work seamlessly with physical input (cameras, lidar, actuators).
๐ dimensional.org
joshuac215/agent-service-toolkit โญ 4,500
A full toolkit for running an AI agent service built with LangGraph, FastAPI and Streamlit.
๐ agent-service-toolkit.streamlit.app
meta-llama/llama-stack-apps โญ 4,298
Agentic components of the Llama Stack APIs
openmanus/OpenManus-RL โญ 4,158
OpenManus-RL is an open-source initiative collaboratively led by Ulab-UIUC and MetaGPT. This project is an extended version of the original OpenManus initiative.
langroid/langroid โญ 4,103
Harness LLMs with Multi-Agent Programming
๐ langroid.github.io/langroid
i-am-bee/beeai-framework โญ 3,410
Build production-ready AI agents in both Python and Typescript.
๐ framework.beeai.dev
researai/DeepScientist โญ 3,334
Now, Stronger AI Pushes Frontiers, Stronger Our Shared Future.
cheshire-cat-ai/core โญ 3,089
AI agent microservice
๐ cheshirecat.ai
facebookresearch/Pearl โญ 3,029
A Production-ready Reinforcement Learning AI Agent Library brought by the Applied Reinforcement Learning team at Meta.
huggingface/tau โญ 3,020
A Python port of Piโs minimalist coding agent.
๐ twotimespi.dev
ciembor/agent-rules-books โญ 2,852
AGENTS.md rules / skills for AI coding agents: Codex, Cursor & Claude Code. Inspired by Clean Code, Refactoring, DDD, Clean Architecture and DDIA programming books.
๐ ciembor.github.io/agent-rules-books
facebookresearch/HyperAgents โญ 2,761
Self-referential self-improving agents that can optimize for any computable task
om-ai-lab/OmAgent โญ 2,667
OmAgent is python library for building multimodal language agents with ease. We try to keep the library simple without too much overhead like other agent framework.
๐ om-agent.com
griptape-ai/griptape โญ 2,580
Modular Python framework for AI agents and workflows with chain-of-thought reasoning, tools, and memory.
๐ www.griptape.ai
miolini/autoresearch-macos โญ 2,395
AI agents running research on single-GPU nanochat training automatically adopted for MacOS
jennyzzt/dgm โญ 2,364
Self-improving system that iteratively modifies its own code and empirically validates each change
nvidia-nemo/labs-OO-Agents โญ 2,305
NVIDIA Object Oriented Agents: the Pythonic way to build AI Agents.
agno-agi/dash โญ 2,267
A self-learning data agent built with systems engineering principles. It grounds answers in 6 layers of context and improves with every query.
๐ agno.com
langchain-ai/executive-ai-assistant โญ 2,212
Executive AI Assistant (EAIA) is an AI agent that attempts to do the job of an Executive Assistant (EA).
agentops-ai/AgentStack โญ 2,192
AgentStack scaffolds your agent stack - The tech stack that collectively is your agent
btahir/open-deep-research โญ 2,141
Open source alternative to Gemini Deep Research. Generate reports with AI based on search results.
๐ opendeepresearch.vercel.app
vila-lab/Dive-into-Claude-Code โญ 2,123
A Systematic Analysis and Discussion of Claude Code for Designing Today's and Future AI Agent Systems
๐ arxiv.org/abs/2604.14228
openautocoder/Agentless โญ 2,114
Agentless๐ฑ: an agentless approach to automatically solve software development problems
jd-opensource/OxyGent โญ 2,074
OxyGent is a modular multi-agent framework that lets you build, deploy, and evolve AI teams
๐ oxygent.jd.com
run-llama/llama_deploy โญ 2,069
Async-first framework for deploying, scaling, and productionizing agentic multi-service systems based on workflows from llama_index.
๐ docs.llamaindex.ai/en/stable/module_guides/llama_deploy
msoedov/agentic_security โญ 2,005
An open-source vulnerability scanner for Agent Workflows and LLMs. Protecting AI systems from jailbreaks, fuzzing, and multimodal attacks.
๐ agentic-security.vercel.app
szczyglis-dev/py-gpt โญ 1,932
Desktop AI Assistant powered by GPT-6, GPT-5, Gemini, Claude, Ollama, Grok, DeepSeek, Perplexity, chat, agents, vision, voice, RAG, image and video generation, tools, MCP, plugins, speech synthesis and recognition, web search, memory, presets, assistants,and more. Linux, Windows, Mac
๐ pygpt.net
weaviate/elysia โญ 1,919
Elysia is an agentic platform designed to use tools in a decision tree. A decision agent decides which tools to use dynamically based on its environment and context.
google-deepmind/concordia โญ 1,723
Concordia is a library to facilitate construction and use of generative agent-based models to simulate interactions of agents in grounded physical, social, or digital space.
agentera/Agently โญ 1,654
Agently is a development framework that helps developers build AI agent native application really fast.
๐ agently.tech
shengranhu/ADAS โญ 1,639
Automated Design of Agentic Systems using Meta Agent Search to show agents can invent novel and powerful agent designs
๐ www.shengranhu.com/adas
langchain-ai/langgraph-swarm-py โญ 1,568
A library for creating swarm-style multi-agent systems using LangGraph. A swarm is a type of multi-agent architecture where agents dynamically hand off control to one another based on their specializations
๐ langchain-ai.github.io/langgraph/concepts/multi_agent
rightnow-ai/autokernel โญ 1,567
Autoresearch for GPU kernels. Give it any PyTorch model, go to sleep, wake up to optimized Triton kernels.
๐ www.rightnowai.co/forge
k-dense-ai/karpathy โญ 1,554
An agentic Machine Learning Engineer that trains state-of-the-art ML models using Claude Code SDK and Google ADK
๐ k-dense.ai
link-agi/AutoAgents โญ 1,494
[IJCAI 2024] Generate different roles for GPTs to form a collaborative entity for complex tasks.
๐ huggingface.co/spaces/linksoul/autoagents
nagisanzenin/engram โญ 1,471
Evidence-based learning engine โ first-principles curricula, free-recall verification with receipts, FSRS-scheduled memory, and explorable artifacts. Learn anything; keep it.
bytedance-seed/m3-agent โญ 1,450
Seeing, Listening, Remembering, and Reasoning: A Multimodal Agent with Long-Term Memory
alpha-innovator/InternAgent โญ 1,443
InternAgent-1.5: A Unified Agentic Framework for Long-Horizon Autonomous Scientific Discovery
๐ discovery.intern-ai.org.cn/home
prefecthq/ControlFlow โญ 1,387
ControlFlow provides a structured, developer-focused framework for defining workflows and delegating work to LLMs, without sacrificing control or transparency
๐ controlflow.ai
strnad/CrewAI-Studio โญ 1,358
agentic,gui,automation
plurai-ai/intellagent โญ 1,259
Simulate interactions, analyze performance, and gain actionable insights for conversational agents. Test, evaluate, and optimize your agent to ensure reliable real-world deployment.
๐ intellagent-doc.plurai.ai
thytu/Agentarium โญ 934
Framework for managing and orchestrating AI agents with ease. Agentarium provides a flexible and intuitive way to create, manage, and coordinate interactions between multiple AI agents in various environments.
facebookresearch/ProgramBench โญ 931
Can Language Models Rebuild Programs From Scratch?
๐ programbench.com
deedy/mac_computer_use โญ 885
A fork of Anthropic Computer Use that you can run on Mac computers to give Claude and other AI models autonomous access to your computer.
๐ x.com/deedydas/status/1849481225041559910
agentscope-ai/agentscope-runtime โญ 872
AgentScope Runtime: secure sandboxed tool execution and scalable agent deployment
๐ runtime.agentscope.io
tiangolo/library-skills โญ 797
Library Agent Skills
codingmoh/open-codex โญ 695
Open Codex is a fully open-source command-line AI assistant inspired by OpenAI Codex, supporting local language models like phi-4-mini and full integration with Ollama.
mannaandpoem/OpenManus โญ 672
Open source version of Manus, the general AI agent
salesforceairesearch/AgentLite โญ 653
AgentLite is a research-oriented library designed for building and advancing LLM-based task-oriented agent systems. It simplifies the implementation of new agent/multi-agent architectures, enabling easy orchestration of multiple agents through a manager agent.
quantalogic/quantalogic โญ 468
QuantaLogic is a ReAct (Reasoning & Action) framework for building advanced AI agents. The cli version include coding capabilities comparable to Aider.
sakanaai/AI-Scientist-ICLR2025-Workshop-Experiment โญ 305
A paper produced by The AI Scientist passed a peer-review process at a workshop in a top machine learning conference
hanxiao/dataroom โญ 191
Give a query, get a dataroom. Pi + self-hosted Qwen3.6 research harness on a single L4.
๐ dataroom.hanxiao.io
prithivirajdamodaran/Route0x โญ 122
A production-grade query routing solution, leveraging LLMs while optimizing for cost per query
hanxiao/searchbox โญ 55
Airgapped closed-corpus QA loop: a self-hosted Qwen3.6 agent explores a .zip dataroom under a token budget with local tools
๐ hanxiao.io/searchbox
auto-index/autoindex โญ 19
Implementation for AutoIndex: Learning Representation Programs for Retrieval
๐ autoindex-one.vercel.app
Code quality tooling: linters, formatters, pre-commit hooks, unused code removal.
astral-sh/ruff โญ 49,727
An extremely fast Python linter and code formatter, written in Rust.
๐ docs.astral.sh/ruff
psf/black โญ 41,850
The uncompromising Python code formatter
๐ black.readthedocs.io/en/stable
pre-commit/pre-commit โญ 15,588
A framework for managing and maintaining multi-language pre-commit hooks.
๐ pre-commit.com
sqlfluff/sqlfluff โญ 9,886
A modular SQL linter and auto-formatter with support for multiple dialects and templated code.
๐ www.sqlfluff.com
pycqa/isort โญ 6,953
A Python utility / library to sort imports.
๐ isort.readthedocs.io
davidhalter/jedi โญ 6,179
Awesome autocompletion, static analysis and refactoring library for python
๐ jedi.readthedocs.io
pycqa/pylint โญ 5,725
It's not just a linter that annoys you!
๐ pylint.readthedocs.io/en/latest
jendrikseipp/vulture โญ 4,814
Find dead Python code
asottile/pyupgrade โญ 4,112
A tool (and pre-commit hook) to automatically upgrade syntax for newer versions of the language.
peteromallet/desloppify โญ 3,151
Agent harness to make your slop code well-engineered and beautiful.
๐ desloppify.it
python-lsp/python-lsp-server โญ 2,598
Fork of the python-language-server project, maintained by the Spyder IDE team and the community
tconbeer/sqlfmt โญ 547
sqlfmt formats your dbt SQL files so you don't have to
๐ sqlfmt.com
Cryptocurrency and blockchain libraries: trading bots, API integration, Ethereum virtual machine, solidity.
freqtrade/freqtrade โญ 54,658
Free, open source crypto trading bot
๐ www.freqtrade.io
ccxt/ccxt โญ 44,106
A unified trading API with more than 100 crypto exchanges and prediction markets in JavaScript / TypeScript / Python / C# / PHP / Go / Java / Rust
๐ docs.ccxt.com
crytic/slither โญ 6,365
Static Analyzer for Solidity and Vyper
๐ blog.trailofbits.com/2018/10/19/slither-a-solidity-static-analysis-framework
ethereum/web3.py โญ 5,532
A python interface for interacting with the Ethereum blockchain and ecosystem.
๐ web3py.readthedocs.io
ethereum/consensus-specs โญ 3,966
Ethereum Consensus Specifications
๐ ethereum.github.io/consensus-specs
cyberpunkmetalhead/Binance-volatility-trading-bot โญ 3,497
This is a fully functioning Binance trading bot that measures the volatility of every coin on Binance and places trades with the highest gaining coins If you like this project consider donating though the Brave browser to allow me to continuously improve the script.
coinbase/agentkit โญ 1,316
AgentKit is Coinbase Developer Platform's framework for easily enabling AI agents to take actions onchain. It is designed to be framework-agnostic, so you can use it with any AI framework, and wallet-agnostic
dylanhogg/awesome-crypto โญ 85
A list of awesome crypto and blockchain projects
๐ www.awesomecrypto.xyz
General data libraries: data processing, serialisation, formats, databases, SQL, connectors, web crawlers, data generation/augmentation/checks.
microsoft/markitdown โญ 186,469
A utility for converting files to Markdown, supports: PDF, PPT, Word, Excel, Images etc
ds4sd/docling โญ 67,635
Docling parses documents and exports them to the desired format with ease and speed.
๐ docling-project.github.io/docling
scrapy/scrapy โญ 64,439
Scrapy, a fast high-level web crawling & scraping framework for Python.
๐ scrapy.org
pathwaycom/pathway โญ 62,248
Python ETL framework for stream processing, real-time analytics, LLM pipelines, and RAG.
๐ pathway.com
apache/spark โญ 44,029
Apache Spark - A unified analytics engine for large-scale data processing
๐ spark.apache.org
mindsdb/mindshub โญ 39,762
The unified workspace where open-source models get things done for you.
๐ mindshub.ai
qdrant/qdrant โญ 34,750
Qdrant - High-performance, massive-scale Vector Database and Vector Search Engine for the next generation of AI. Also available in the cloud https://cloud.qdrant.io/
๐ qdrant.tech
jaidedai/EasyOCR โญ 30,019
Ready-to-use OCR with 80+ supported languages and all popular writing scripts including Latin, Chinese, Arabic, Devanagari, Cyrillic and etc.
๐ www.jaided.ai
chroma-core/chroma โญ 29,353
Search infrastructure for AI
๐ www.trychroma.com
getredash/redash โญ 28,807
Make Your Company Data Driven. Connect to any data source, easily visualize, dashboard and share your data.
๐ redash.io
humansignal/label-studio โญ 28,325
Label Studio is an open source data labeling tool. It lets you label data types like audio, text, images, videos, and time series with a simple and straightforward UI and export to various model formats.
๐ labelstud.io
airbytehq/airbyte โญ 22,116
Open-source data movement for ELT pipelines and AI agents โ from APIs, databases & files to warehouses, lakes, and AI applications. Both self-hosted and Cloud.
๐ airbyte.com
avaiga/taipy โญ 19,434
Turns Data and AI algorithms into production-ready web applications in no time.
๐ www.taipy.io
joke2k/faker โญ 19,405
Faker is a Python package that generates fake data for you.
๐ faker.readthedocs.io
tiangolo/sqlmodel โญ 18,335
SQL databases in Python, designed for simplicity, compatibility, and robustness.
๐ sqlmodel.tiangolo.com
apache/arrow โญ 17,148
Apache Arrow is the universal columnar format and multi-language toolbox for fast data interchange and in-memory analytics
๐ arrow.apache.org
weaviate/weaviate โญ 16,839
Weaviate is an open-source vector database that stores both objects and vectors, allowing for the combination of vector search with structured filtering with the fault tolerance and scalability of a cloud-native databaseโ.
๐ weaviate.io/developers/weaviate
binux/pyspider โญ 16,766
A Powerful Spider(Web Crawler) System in Python.
๐ docs.pyspider.org
googleapis/mcp-toolbox โญ 16,477
MCP Toolbox for Databases is an open source MCP server for databases. Develop tools easier, faster, and more securely by handling connection pooling, authentication.
๐ mcp-toolbox.dev/documentation/introduction
twintproject/twint โญ 16,399
An advanced Twitter scraping & OSINT tool written in Python that doesn't use Twitter's API, allowing you to scrape a user's followers, following, Tweets and more while evading most API limitations.
cyclotruc/gitingest โญ 15,602
Turn any Git repository into a prompt-friendly text ingest for LLMs.
๐ gitingest.com
s0md3v/Photon โญ 13,222
Incredibly fast crawler designed for OSINT.
sqlalchemy/sqlalchemy โญ 12,171
The Database Toolkit for Python
๐ www.sqlalchemy.org
coleifer/peewee โญ 11,989
a small, expressive orm -- supports postgresql, mysql, sqlite, now with asyncio
๐ docs.peewee-orm.com
gristlabs/grist-core โญ 11,843
Grist is the evolution of spreadsheets.
๐ www.getgrist.com
lancedb/lancedb โญ 11,499
Developer-friendly OSS embedded retrieval library for multimodal AI. Search More; Manage Less.
๐ lancedb.com/docs
simonw/datasette โญ 11,478
An open source multi-tool for exploring and publishing data
๐ datasette.io
voxel51/fiftyone โญ 11,107
Refine high-quality datasets and visual AI models
๐ fiftyone.ai
pymupdf/PyMuPDF โญ 10,762
PyMuPDF is a high performance Python library for data extraction, analysis, conversion & manipulation of PDF (and other) documents.
๐ pymupdf.readthedocs.io/?utm_source=github&utm_medium=referral&utm_campaign=pymupdf_github&utm_content=about&utm_term=docs
bigscience-workshop/petals โญ 10,584
๐ธ Run LLMs at home, BitTorrent-style. Fine-tuning and inference up to 10x faster than offloading
๐ petals.dev
yzhao062/pyod โญ 10,012
A Python library for anomaly detection across tabular, time series, graph, text, image, and audio data. 60+ detectors, benchmark-backed ADEngine orchestration, and an agentic workflow for AI agents.
๐ pyod.dev
tobymao/sqlglot โญ 9,628
Python SQL Parser and Transpiler
๐ sqlglot.com
alirezamika/autoscraper โญ 7,990
A Smart, Automatic, Fast and Lightweight Web Scraper for Python
rapidai/RapidOCR โญ 7,917
๐ Awesome OCR multiple programing languages toolkits based on ONNX Runtime, OpenVINO, MNN, PaddlePaddle, TensorRT and PyTorch.
๐ rapidai.github.io/rapidocrdocs
kaggle/kaggle-cli โญ 7,559
Official Kaggle CLI
adbar/trafilatura โญ 6,849
Python & Command-line tool to gather text and metadata on the Web: Crawling, scraping, extraction, output as CSV, JSON, HTML, MD, TXT, XML
๐ trafilatura.readthedocs.io
ibis-project/ibis โญ 6,661
Ibis is a Python library that provides a lightweight, universal interface for data wrangling. It helps Python users explore and transform data of any size, stored anywhere.
๐ ibis-project.org
dlt-hub/dlt โญ 5,880
data load tool (dlt) is an open source Python library that makes data loading easy ๐ ๏ธ
๐ dlthub.com/docs
giskard-ai/giskard-oss โญ 5,834
๐ข Open-Source Evaluation & Testing library for LLM Agents
๐ docs.giskard.ai
vi3k6i5/flashtext โญ 5,706
Extract Keywords from sentence or Replace keywords in sentences.
airbnb/knowledge-repo โญ 5,540
A next-generation curated knowledge sharing platform for data scientists and other technical professions.
superduperdb/superduper โญ 5,323
Superduper: End-to-end framework for building custom AI applications and agents.
๐ superduper.io
mangiucugna/json_repair โญ 5,104
A python module to repair invalid JSON from LLMs
๐ mangiucugna.github.io/json_repair
facebookresearch/AugLy โญ 5,097
A data augmentations library for audio, image, text, and video.
๐ ai.facebook.com/blog/augly-a-new-data-augmentation-library-to-help-build-more-robust-ai-models
lk-geimfari/mimesis โญ 4,841
Mimesis is a Python library for generating fake but realistic data in multiple languages and locales.
๐ mimesis.name
mlabonne/llm-datasets โญ 4,792
Curated list of datasets and tools for post-training.
๐ mlabonne.github.io/blog
amundsen-io/amundsen โญ 4,783
Amundsen is a metadata driven application for improving the productivity of data analysts, data scientists and engineers when interacting with data.
๐ www.amundsen.io/amundsen
rom1504/img2dataset โญ 4,455
Easily turn large sets of image urls to an image dataset. Can download, resize and package 100M urls in 20h on one machine.
sqlalchemy/alembic โญ 4,408
A database migrations tool for SQLAlchemy.
deepchecks/deepchecks โญ 4,056
Deepchecks: Tests for Continuous Validation of ML Models & Data. Deepchecks is a holistic open-source solution for all of your AI & ML validation needs, enabling to thoroughly test your data and models from research to production.
๐ docs.deepchecks.com/stable
sdv-dev/SDV โญ 3,563
Synthetic data generation for tabular data
๐ docs.sdv.dev/sdv
run-llama/llama-hub โญ 3,461
A library of data loaders for LLMs made by the community -- to be used with LlamaIndex and/or LangChain
๐ llamahub.ai
huggingface/datatrove โญ 3,349
DataTrove is a library to process, filter and deduplicate text data at a very large scale. It provides a set of prebuilt commonly used processing blocks with a framework to easily add custom functionality
docarray/docarray โญ 3,123
Represent, send, store and search multimodal data
๐ docs.docarray.org
datafold/data-diff โญ 2,991
Compare tables within or across databases
๐ docs.datafold.com
aminalaee/sqladmin โญ 2,829
SQLAlchemy Admin for FastAPI and Starlette
๐ smithyhq.github.io/sqladmin
pikepdf/pikepdf โญ 2,804
A Python library for reading and writing PDF, powered by QPDF
๐ pikepdf.readthedocs.io
sfu-db/connector-x โญ 2,650
Fastest library to load data from DB to DataFrames in Rust and Python
๐ sfu-db.github.io/connector-x
pynamodb/PynamoDB โญ 2,646
A pythonic interface to Amazon's DynamoDB
๐ pynamodb.readthedocs.io
uqfoundation/dill โญ 2,451
serialize all of Python
๐ dill.rtfd.io
milvus-io/bootcamp โญ 2,444
Dealing with all unstructured data, such as reverse image search, audio search, molecular search, video analysis, question and answer systems, NLP, etc.
๐ milvus.io
emirozer/fake2db โญ 2,346
Generate fake but valid data filled databases for test purposes using most popular patterns(AFAIK). Current support is sqlite, mysql, postgresql, mongodb, redis, couchdb.
nvidia-nemo/DataDesigner โญ 2,272
Create synthetic datasets that go beyond simple LLM prompting. Covers diverse statistical distributions, meaningful correlations between fields, or validated high-quality outputs.
๐ docs.nvidia.com/nemo/datadesigner
pymupdf/pymupdf4llm โญ 2,206
Extension for PyMuPDF that converts documents into structured Markdown, JSON, and plain text optimised for RAG pipelines, vector embeddings, and LLM ingestion.
๐ pymupdf.readthedocs.io/en/latest/pymupdf4llm
simonw/sqlite-utils โญ 2,171
Python CLI utility and library for manipulating SQLite databases
๐ sqlite-utils.datasette.io
huggingface/aisheets โญ 1,645
Build, enrich, and transform datasets using AI models with no code. Deploy locally or on the Hub with access to thousands of open models.
๐ huggingface.co/spaces/aisheets/sheets
meta-llama/synthetic-data-kit โญ 1,640
Tool for generating high-quality synthetic datasets to fine-tune LLMs. Generate Reasoning Traces, QA Pairs, save them to a fine-tuning format with a simple CLI.
๐ pypi.org/project/synthetic-data-kit
igorbenav/fastcrud โญ 1,590
FastCRUD is a Python package for FastAPI, offering robust async CRUD operations and flexible endpoint creation utilities.
๐ benavlabs.github.io/fastcrud
d-star-ai/dsRAG โญ 1,588
A retrieval engine for unstructured data. It is especially good at handling challenging queries over dense text, like financial reports, legal documents, and academic papers.
always-further/deepfabric โญ 886
Generate High-Quality Synthetics, Train, Measure, and Evaluate in a Single Pipeline
๐ docs.deepfabric.dev
macbre/sql-metadata โญ 883
Uses tokenized query returned by python-sqlparse and generates query metadata
๐ pypi.python.org/pypi/sql-metadata
koaning/bulk โญ 599
Bulk is a quick UI developer tool to apply some bulk labels.
titan-systems/titan โญ 486
Snowflake infrastructure-as-code. Provision environments, automate deploys, CI/CD. Manage RBAC, users, roles, and data access. Declarative Python Resource API.
pmgraham/datagrunt โญ 13
Datagrunt is a Python library designed to simplify the way you work with CSV files. It provides a streamlined approach to reading, processing, and transforming your data into various formats, making data manipulation efficient and intuitive.
๐ www.datagrunt.io
Debugging and tracing tools.
cool-rr/PySnooper โญ 16,575
Never use print for debugging again
gruns/icecream โญ 10,110
๐ฆ Never use print() to debug again.
shobrook/rebound โญ 4,112
Instant Stack Overflow results whenever an exception is thrown
Text-to-image diffusion model libraries, tools and apps for generating images from natural language.
automatic1111/stable-diffusion-webui โญ 165,060
Stable Diffusion web UI
comfyanonymous/ComfyUI โญ 134,438
The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface.
๐ www.comfy.org
compvis/stable-diffusion โญ 73,458
A latent text-to-image diffusion model
๐ ommer-lab.com/research/latent-diffusion-models
huggingface/diffusers โญ 34,568
๐ค Diffusers: State-of-the-art diffusion models for image, video, and audio generation in PyTorch.
๐ huggingface.co/docs/diffusers
lllyasviel/ControlNet โญ 34,119
Let us control diffusion models!
invoke-ai/InvokeAI โญ 28,266
Invoke is a leading creative engine for Stable Diffusion models, empowering professionals, artists, and enthusiasts to generate and create visual media using the latest AI-driven technologies. The solution offers an industry leading WebUI, and serves as the foundation for multiple commercial products.
๐ invoke-ai.github.io/invokeai
stability-ai/generative-models โญ 27,291
Generative Models by Stability AI
openbmb/MiniCPM-V โญ 26,446
A Pocket-Sized MLLM for Ultra-Efficient Image and Video Understanding on Your Phone
apple/ml-stable-diffusion โญ 17,967
Stable Diffusion with Core ML on Apple Silicon
borisdayma/dalle-mini โญ 14,722
DALLยทE Mini - Generate images from a text prompt
๐ www.craiyon.com
compvis/latent-diffusion โญ 14,156
High-Resolution Image Synthesis with Latent Diffusion Models
divamgupta/diffusionbee-stable-diffusion-ui โญ 13,593
Diffusion Bee is the easiest way to run Stable Diffusion locally on your M1 Mac. Comes with a one-click installer. No dependencies or technical knowledge needed.
๐ diffusionbee.com
facebookresearch/dinov2 โญ 13,358
PyTorch code and models for the DINOv2 self-supervised learning method.
instantid/InstantID โญ 11,994
InstantID: Zero-shot Identity-Preserving Generation in Seconds ๐ฅ
๐ instantid.github.io
lucidrains/DALLE2-pytorch โญ 11,302
Implementation of DALL-E 2, OpenAI's updated text-to-image synthesis neural network, in Pytorch
idea-research/GroundingDINO โญ 10,608
[ECCV 2024] Official implementation of the paper "Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection"
๐ arxiv.org/abs/2303.05499
opengvlab/InternVL โญ 10,162
[CVPR 2024 Oral] InternVL Family: A Pioneering Open-Source Alternative to GPT-4o. ๆฅ่ฟGPT-4o่กจ็ฐ็ๅผๆบๅคๆจกๆๅฏน่ฏๆจกๅ
๐ internvl.readthedocs.io/en/latest
nvlabs/Sana โญ 9,133
SANA: Efficient High-Resolution Image Synthesis with Linear Diffusion Transformer
๐ nvlabs.github.io/sana/docs
ashawkey/stable-dreamfusion โญ 8,860
Text-to-3D & Image-to-3D & Mesh Exportation with NeRF + Diffusion.
carson-katri/dream-textures โญ 8,206
Stable Diffusion built-in to Blender
xavierxiao/Dreambooth-Stable-Diffusion โญ 7,732
Implementation of Dreambooth (https://arxiv.org/abs/2208.12242) with Stable Diffusion
timothybrooks/instruct-pix2pix โญ 6,882
PyTorch implementation of InstructPix2Pix, an instruction-based image editing model, based on the original CompVis/stable_diffusion repo.
openai/consistency_models โญ 6,483
Official repo for consistency models.
salesforce/BLIP โญ 5,708
PyTorch code for BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation
nateraw/stable-diffusion-videos โญ 4,708
Create ๐ฅ videos with Stable Diffusion by exploring the latent space and morphing between text prompts
open-compass/VLMEvalKit โญ 4,407
Open-source evaluation toolkit of large multi-modality models (LMMs), support 220+ LMMs, 80+ benchmarks
๐ huggingface.co/spaces/opencompass/open_vlm_leaderboard
lkwq007/stablediffusion-infinity โญ 3,890
Outpainting with Stable Diffusion on an infinite canvas
openai/improved-diffusion โญ 3,848
Release for Improved Denoising Diffusion Probabilistic Models
jina-ai/discoart โญ 3,822
๐ชฉ Create Disco Diffusion artworks in one line
mlc-ai/web-stable-diffusion โญ 3,724
Bringing stable diffusion models to web browsers. Everything runs inside the browser with no server support.
๐ mlc.ai/web-stable-diffusion
openai/glide-text2im โญ 3,678
GLIDE: a diffusion-based text-conditional image synthesis model
nvlabs/Eagle โญ 3,603
Eagle: Frontier Vision-Language Models with Data-Centric Strategies
๐ nvlabs.github.io/eagle
google-research/big_vision โญ 3,541
Official codebase used to develop Vision Transformer, SigLIP, MLP-Mixer, LiT and more.
saharmor/dalle-playground โญ 2,740
A playground to generate images from any text prompt using Stable Diffusion (past: using DALL-E Mini)
stability-ai/stability-sdk โญ 2,434
SDK for interacting with stability.ai APIs (e.g. stable diffusion inference)
๐ platform.stability.ai
thudm/CogVLM2 โญ 2,431
GPT4V-level open-source multi-modal model based on Llama3-8B
coyote-a/ultimate-upscale-for-automatic1111 โญ 1,765
Ultimate SD Upscale extension for AUTOMATIC1111 Stable Diffusion web UI
Financial and quantitative libraries: investment research tools, market data, algorithmic trading, backtesting, financial derivatives.
openbb-finance/OpenBB โญ 73,362
Open Data Platform for analysts, quants and AI agents.
๐ openbb.co
virattt/ai-hedge-fund โญ 63,670
AI-powered hedge fund. The goal of this project is to explore the use of AI to make trading decisions.
microsoft/qlib โญ 48,748
Qlib is an AI-oriented Quant investment platform that aims to use AI tech to empower Quant Research, from exploring ideas to implementing productions. Qlib supports diverse ML modeling paradigms, including supervised learning, market dynamics modeling, and RL, and is now equipped with https://github.com/microsoft/RD...
๐ qlib.readthedocs.io/en/latest
shiyu-coder/Kronos โญ 39,350
Open-source foundation model for financial candlesticks, trained on data from over 45 global exchanges
hkuds/Vibe-Trading โญ 37,566
A research workspace for turning finance questions into runnable analysis. It connects natural-language prompts to market-data loaders, strategy generation, backtest engines, reports, exports, and persistent research memory.
๐ vibetrading.wiki
ranaroussi/yfinance โญ 25,310
Download market data from Yahoo! Finance's API
๐ ranaroussi.github.io/yfinance
mementum/backtrader โญ 23,303
Python Backtesting library for trading strategies
๐ www.backtrader.com
quantconnect/Lean โญ 21,719
Lean Algorithmic Trading Engine by QuantConnect (Python, C#)
๐ lean.io
stefan-jansen/machine-learning-for-trading โญ 21,702
Code for Machine Learning for Trading, 3rd edition โ from data sourcing to live execution.
๐ ml4trading.io
ai4finance-foundation/FinGPT โญ 21,272
FinGPT: Open-Source Financial Large Language Models! Revolutionize ๐ฅ We release the trained model on HuggingFace.
๐ fingpt.io
hummingbot/hummingbot โญ 20,926
Open source software that helps you create and deploy high-frequency crypto trading bots
๐ hummingbot.org
quantopian/zipline โญ 20,108
Zipline, a Pythonic Algorithmic Trading Library
๐ www.zipline.io
ai4finance-foundation/FinRL โญ 16,372
FinRLยฎ: Financial Reinforcement Learning. ๐ฅ
๐ finrl.ai
goldmansachs/gs-quant โญ 12,998
Python toolkit for quantitative finance
๐ developer.gs.com/discover/products/gs-quant
ta-lib/ta-lib-python โญ 12,248
Python wrapper for TA-Lib (http://ta-lib.org/).
๐ ta-lib.github.io/ta-lib-python
polakowo/vectorbt โญ 9,152
The backtesting engine that gives you an unfair advantage. Run thousands of trading ideas before others finish one.
๐ vectorbt.dev
kernc/backtesting.py โญ 8,982
๐ ๐ ๐ ๐ฐ Backtest trading strategies in Python.
๐ kernc.github.io/backtesting.py
ranaroussi/quantstats โญ 7,651
Portfolio analytics for quants, written in Python
tensortrade-org/tensortrade โญ 7,256
An open source reinforcement learning framework for training, evaluating, and deploying robust trading agents.
๐ discord.gg/zz7bgwh
quantopian/pyfolio โญ 6,425
Portfolio and risk analytics in Python
๐ quantopian.github.io/pyfolio
borisbanushev/stockpredictionai โญ 5,604
In this noteboook I will create a complete process for predicting stock price movements. Follow along and we will achieve some pretty good results. For that purpose we will use a Generative Adversarial Network (GAN) with LSTM, a type of Recurrent Neural Network, as generator, and a Convolutional Neural Networ...
google/tf-quant-finance โญ 5,502
High-performance TensorFlow library for quantitative finance.
quantopian/alphalens โญ 4,450
Performance analysis of predictive (alpha) stock factors
๐ quantopian.github.io/alphalens
matplotlib/mplfinance โญ 4,434
Financial Markets Data Visualization using Matplotlib
๐ pypi.org/project/mplfinance
zvtvz/zvt โญ 4,311
modular quant framework.
๐ zvt.readthedocs.io/en/latest
edtechre/pybroker โญ 3,546
Algorithmic Trading in Python with Machine Learning
๐ www.pybroker.com
domokane/FinancePy โญ 3,155
A Python Finance Library that focuses on the pricing and risk-management of Financial Derivatives, including fixed-income, equity, FX and credit derivatives.
blankly-finance/blankly โญ 2,476
๐ ๐ธ Easily build, backtest and deploy your algo in just a few lines of code. Trade stocks, cryptos, and forex across exchanges w/ one package.
๐ package.blankly.finance
coding-kitties/investing-algorithm-framework โญ 2,230
Framework for quantitative trading. Complete framework for development, backtesting, and deploying automated trading algorithms and trading bots.
๐ coding-kitties.github.io/investing-algorithm-framework
cuemacro/findatapy โญ 2,125
Python library to download market data via Bloomberg, Eikon, Quandl, Yahoo etc.
ivebotunac/PrimoAgent โญ 346
PrimoAgent is an multi agent AI stock analysis system built on LangGraph architecture that orchestrates four specialized agents to provide comprehensive daily trading insights and next-day price predictions
๐ primoinvesting.com
Game development tools, engines and libraries.
microsoft/TRELLIS โญ 13,697
A large 3D asset generation model. It takes in text or image prompts and generates high-quality 3D assets in various formats, such as Radiance Fields, 3D Gaussians, and meshes.
๐ trellis3d.github.io
pygame/pygame โญ 8,944
๐๐ฎ pygame (the library) is a Free and Open Source python programming language library for making multimedia applications like games built on top of the excellent SDL library. C, Python, Native, OpenGL.
๐ www.pygame.org
f3d-app/f3d โญ 4,779
Fast and minimalist 3D viewer.
๐ f3d.app
pythonarcade/arcade โญ 2,077
Easy to use Python library for creating 2D arcade games.
๐ arcade.academy
pygame-community/pygame-ce โญ 1,714
๐๐ฎ pygame - Community Edition is a FOSS Python library for multimedia applications (like games). Built on top of the excellent SDL library.
๐ pyga.me
Geospatial libraries: raster and vector data formats, interactive mapping and visualisation, computing frameworks for processing images, projections.
originalankur/maptoposter โญ 14,147
Transform your favorite cities into beautiful, minimalist designs. MapToPoster lets you create and export visually striking map posters with code.
domlysz/BlenderGIS โญ 9,404
Blender addons to make the bridge between Blender and geographic data
python-visualization/folium โญ 7,403
Python Data. Leaflet.js Maps.
๐ python-visualization.github.io/folium
osgeo/gdal โญ 6,073
GDAL is an open source MIT licensed translator library for raster and vector geospatial data formats.
๐ gdal.org
gboeing/osmnx โญ 5,852
Download, model, analyze, and visualize street networks and other geospatial features from OpenStreetMap.
๐ osmnx.readthedocs.io
geopandas/geopandas โญ 5,256
Python tools for geographic data
๐ geopandas.org
shapely/shapely โญ 4,513
Manipulation and analysis of geometric objects
๐ shapely.readthedocs.io/en/stable
microsoft/torchgeo โญ 4,189
TorchGeo: datasets, samplers, transforms, and pre-trained models for geospatial data
๐ torchgeo.org
opengeos/segment-geospatial โญ 4,145
A Python package for segmenting geospatial data with the Segment Anything Model (SAM)
๐ samgeo.gishub.org
giswqs/geemap โญ 4,030
A Python package for interactive geospatial analysis and visualization with Google Earth Engine.
๐ geemap.org
opengeos/leafmap โญ 3,773
A Python package for interactive mapping and geospatial analysis with minimal coding in a Jupyter environment
๐ leafmap.org
holoviz/datashader โญ 3,561
Quickly and accurately render even the largest data.
๐ datashader.org
rasterio/rasterio โญ 2,577
Rasterio reads and writes geospatial raster datasets
๐ rasterio.readthedocs.io
microsoft/GlobalMLBuildingFootprints โญ 1,959
Worldwide building footprints derived from satellite imagery
c2g-dev/city2graph โญ 1,925
Transform geospatial relations into graphs for Graph Neural Networks and spatial network analysis
๐ city2graph.net
pysal/pysal โญ 1,524
PySAL: Python Spatial Analysis Library Meta-Package
๐ pysal.org/pysal
residentmario/geoplot โญ 1,215
High-level geospatial data visualization library for Python.
๐ residentmario.github.io/geoplot/index.html
Graphs and network libraries: network analysis, graph machine learning, visualisation.
networkx/networkx โญ 17,274
Network Analysis in Python
๐ networkx.org
microsoft/graspologic โญ 1,014
graspologic is a package for graph statistical algorithms
๐ graspologic-org.github.io/graspologic
dylanhogg/llmgraph โญ 509
Create knowledge graphs with LLMs
Graphical user interface libraries and toolkits.
hoffstadt/DearPyGui โญ 15,632
Dear PyGui: A fast and powerful Graphical User Interface Toolkit for Python with minimal dependencies
๐ dearpygui.readthedocs.io/en/latest
pysimplegui/PySimpleGUI โญ 13,819
Python GUIs for Humans! Create any GUI simple or complicated in a way that's intuitive. Launched in 2018. NEW for 2026 - the LGPL3 Version 6. Transforms tkinter, Qt, WxPython, and Remi into a simple, intuitive, and fun experience for both hobbyists and expert users.
๐ www.pysimplegui.com
parthjadhav/Tkinter-Designer โญ 10,262
An easy and fast way to create a Python GUI ๐
๐ www.parthjadhav.com/products/tkinter-designer
samuelcolvin/FastUI โญ 8,940
FastUI is a new way to build web application user interfaces defined by declarative Python code.
๐ fastui-demo.onrender.com
r0x0r/pywebview โญ 6,030
Build GUI for your Python program with JavaScript, HTML, and CSS
๐ pywebview.flowrl.com
beeware/toga โญ 5,414
A Python native, OS native GUI toolkit.
๐ toga.beeware.org
Jupyter and JupyterLab and Notebook tools, libraries and plugins.
marimo-team/marimo โญ 22,878
A reactive Python notebook: run a cell or interact with a UI element, and marimo automatically runs dependent cells, keeping code and outputs consistent. marimo notebooks are stored as pure Python, executable as scripts, and deployable as apps.
๐ marimo.io
jupyterlab/jupyterlab โญ 15,309
JupyterLab computational environment.
๐ jupyterlab.readthedocs.io
jupyter/notebook โญ 13,356
Jupyter Interactive Notebook
๐ jupyter-notebook.readthedocs.io
garrettj403/SciencePlots โญ 9,247
Matplotlib styles for scientific plotting
mwouts/jupytext โญ 7,251
Jupyter Notebooks as Markdown Documents, Julia, Python or R scripts
๐ jupytext.org
nteract/papermill โญ 6,485
๐ Parameterize, execute, and analyze notebooks
๐ papermill.readthedocs.io/en/latest
voila-dashboards/voila โญ 5,944
Voilร turns Jupyter notebooks into standalone web applications
๐ voila.readthedocs.io
connorferster/handcalcs โญ 5,804
Python library for converting Python calculations into rendered latex.
jupyterlite/jupyterlite โญ 4,898
Wasm powered Jupyter running in the browser ๐ก
๐ jupyterlite.rtfd.io/en/stable/try/lab
jupyterlab/jupyter-ai โญ 4,406
An open source extension that connects AI agents to computational notebooks in JupyterLab.
๐ jupyter-ai.readthedocs.io
jupyterlab/jupyterlab-desktop โญ 4,317
JupyterLab desktop application, based on Electron.
executablebooks/jupyter-book โญ 4,278
Create beautiful, publication-quality books and documents from computational content.
๐ jupyterbook.org
deepnote/deepnote โญ 3,009
Deepnote is a successor of Jupyter. It uses the Deepnote kernel which is more powerful but still backwards compatible so you can seamlessly move between both, but adds an AI agent, sleek UI, new block types, and native data integrations.
๐ deepnote.com/?utm_source=github&utm_medium=github&utm_campaign=github&utm_content=readme_main
mito-ds/mito โญ 2,648
Jupyter extensions that help you write code faster: Context aware AI Chat, Autocomplete, and Spreadsheet
๐ trymito.io
infuseai/colab-xterm โญ 490
Open a terminal in colab, including the free tier.
Large language model and GPT libraries and frameworks: auto-gpt, agents, QnA, chain-of-thought workflows, API integations. Also see the Natural Language Processing category for crossover.
significant-gravitas/AutoGPT โญ 187,484
AutoGPT is the vision of accessible AI for everyone, to use and to build on. Our mission is to provide the tools, so that you can focus on what matters.
๐ agpt.co
open-webui/open-webui โญ 152,850
Open WebUI is an extensible, feature-rich, and user-friendly self-hosted AI platform designed to operate entirely offline. It supports various LLM runners like Ollama and OpenAI-compatible APIs, with built-in inference engine for RAG
๐ openwebui.com
ggerganov/llama.cpp โญ 129,162
LLM inference in C/C++
๐ llama.app
deepseek-ai/DeepSeek-V3 โญ 104,480
A strong Mixture-of-Experts (MoE) language model with 671B total parameters with 37B activated for each token.
vllm-project/vllm โญ 92,413
A high-throughput and memory-efficient inference and serving engine for LLMs
๐ vllm.ai
infiniflow/ragflow โญ 91,158
RAGFlow is a leading open-source Retrieval-Augmented Generation (RAG) engine that fuses cutting-edge RAG with Agent capabilities to create a superior context layer for LLMs
๐ ragflow.io
modelcontextprotocol/servers โญ 90,555
A collection of reference implementations for the Model Context Protocol (MCP), as well as references to community built servers
๐ modelcontextprotocol.io
unclecode/crawl4ai โญ 84,092
AI-ready web crawling tailored for LLMs, AI agents, and data pipelines. Open source, flexible, and built for real-time performance, Crawl4AI empowers developers with unmatched speed, precision, and deployment ease.
๐ crawl4ai.com
nomic-ai/gpt4all โญ 77,391
GPT4All: Run Local LLMs on Any Device. Open-source and available for commercial use.
๐ nomic.ai/gpt4all
unslothai/unsloth โญ 76,567
Local UI to run and train LLMs and diffusion models. Supports GGUF, MLX, Qwen3.8, DeepSeek-V4, MiniMax-H3, Gemma 4, FLUX and more.
๐ unsloth.ai/docs
hiyouga/LlamaFactory โญ 74,966
Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)
๐ llamafactory.readthedocs.io
headroomlabs-ai/headroom โญ 73,658
Compress tool outputs, logs, files, and RAG chunks before they reach the LLM. 20% fewer tokens for coding agents, 60-95% fewer tokens for JSON, same answers. Library, proxy, MCP server.
๐ docs.headroomlabs.ai/docs
killianlucas/openinterpreter โญ 68,400
A coding agent for open models like Kimi K3 and GLM 5.3
๐ openinterpreter.com
xtekky/gpt4free โญ 66,716
The official gpt4free repository | various collection of powerful language models | opus 4.6 gpt 5.3 kimi 2.5 deepseek v3.2 gemini 3
๐ t.me/g4f_channel
karpathy/nanoGPT โญ 63,312
The simplest, fastest repository for training/finetuning medium-sized GPTs.
facebookresearch/llama โญ 59,620
Inference code for Llama models
berriai/litellm โญ 59,390
The fastest, litest AI Gateway. Rust core with Python SDK. Call 100+ LLM APIs in OpenAI (or native) format with cost tracking, guardrails, load balancing, and logging [Bedrock, Azure, OpenAI, Anthropic, OpenAI, VertexAI, vLLM, Nvidia NIM]
๐ docs.litellm.ai/docs
pathwaycom/llm-app โญ 58,910
Ready-to-run cloud templates for RAG, AI pipelines, and enterprise search with live data. ๐ณDocker-friendly.โกAlways in sync with Sharepoint, Google Drive, S3, Kafka, PostgreSQL, real-time data APIs, and more.
๐ pathway.com/developers/templates
karpathy/nanochat โญ 58,220
A full-stack implementation of an LLM like ChatGPT in a single, clean, minimal, hackable, dependency-lite codebase
imartinez/private-gpt โญ 57,519
Complete API layer for private AI applications on local models: RAG, skills, tools, MCP, text-to-sql, and more. Works with any OpenAI-compatible inference server.
๐ www.zylon.ai/private-gpt
gpt-engineer-org/gpt-engineer โญ 55,091
CLI platform to experiment with codegen. Precursor to: https://lovable.dev
anthropics/claude-cookbooks โญ 52,912
Provides code and guides designed to help developers build with Claude, offering copy-able code snippets that you can easily integrate into your own projects.
xai-org/grok-1 โญ 52,236
This repository contains JAX example code for loading and running the Grok-1 open-weights model.
oobabooga/textgen โญ 47,695
Open-source desktop app for local LLMs. Text, vision, tool-calling, OpenAI/Anthropic-compatible API. 100% private.
exo-explore/exo โญ 47,610
Run your own AI cluster at home. Unify your existing devices into one powerful GPU: iPhone, iPad, Android, Mac, NVIDIA, Raspberry Pi etc
justvugg/colibri โญ 47,239
A hierarchical inference engine for frontier MoE models: hot experts on the GPU (CUDA, Vulkan), warm ones in RAM, cold ones streamed from NVMe. Written in C, runs on the hardware you already own.
๐ justvugg.github.io/colibri
k-dense-ai/scientific-agent-skills โญ 46,150
A set of ready to use scientific skills for Claude
๐ arxiv.org/abs/2609.00065
danielmiessler/Fabric โญ 44,043
Fabric is an open-source framework for augmenting humans using AI. It provides a modular system for solving specific problems using a crowdsourced set of AI prompts that can be used anywhere.
๐ danielmiessler.com/p/fabric-origin-story
hpcaitech/ColossalAI โญ 41,439
Making large AI models cheaper, faster and more accessible
๐ www.colossalai.org
thudm/ChatGLM-6B โญ 40,951
ChatGLM-6B: An Open Bilingual Dialogue Language Model | ๅผๆบๅ่ฏญๅฏน่ฏ่ฏญ่จๆจกๅ
microsoft/BitNet โญ 40,337
Official inference framework for 1-bit LLMs (e.g., BitNet b1.58). It offers a suite of optimized kernels, that support fast and lossless inference of 1.58-bit models
quivrhq/quivr โญ 39,547
Opiniated RAG for integrating GenAI in your apps ๐ง Focus on your product rather than the RAG. Easy integration in existing products with customisation! Any LLM: GPT4, Groq, Llama. Any Vectorstore: PGVector, Faiss. Any Files. Anyway you want.
๐ core.quivr.com
lm-sys/FastChat โญ 39,545
An open platform for training, serving, and evaluating large language models. Release repo for Vicuna and Chatbot Arena.
google/langextract โญ 38,647
Library that uses LLMs to extract structured information from unstructured text documents based on user-defined instructions
๐ pypi.org/project/langextract
stanfordnlp/dspy โญ 38,201
DSPy: The framework for programmingโnot promptingโlanguage models
๐ dspy.ai
khoj-ai/khoj โญ 37,470
Your AI second brain. Self-hostable. Get answers from the web or your docs. Build custom agents, schedule automations, do deep research. Turn any online or local LLM into your personal, autonomous AI
๐ khoj.dev
laion-ai/Open-Assistant โญ 37,392
OpenAssistant is a chat-based assistant that understands tasks, can interact with third-party systems, and retrieve information dynamically to do so.
๐ open-assistant.io
sgl-project/sglang โญ 36,321
SGLang is a high-performance serving framework for large language models and multimodal models.
๐ sglang.io
microsoft/graphrag โญ 36,074
A modular graph-based Retrieval-Augmented Generation (RAG) system
๐ microsoft.github.io/graphrag
vectifyai/PageIndex โญ 35,808
A document indexing system that builds search tree structures from long documents, making them ready for reasoning-based RAG
๐ pageindex.ai
lyogavin/airllm โญ 34,701
AirLLM optimizes inference memory usage, allowing 70B large language models to run inference on a single 4GB GPU card without quantization, distillation and pruning. And you can run 405B Llama3.1 on 8GB vram now.
moymix/TaskMatrix โญ 33,975
Connects ChatGPT and a series of Visual Foundation Models to enable sending and receiving images during chatting.
pythagora-io/gpt-pilot โญ 33,668
The first real AI developer
p-e-w/heretic โญ 32,199
Heretic is a tool that removes censorship from transformer-based LLMs without post-training
๐ heretic-project.org
karpathy/llm.c โญ 31,046
LLM training in simple, pure C/CUDA. There is no need for 245MB of PyTorch or 107MB of cPython
topoteretes/cognee โญ 30,906
Cognee is the open-source AI memory platform for agents. Give your AI agents persistent long-term memory across sessions with a self-hosted knowledge graph engine.
๐ www.cognee.ai
tatsu-lab/stanford_alpaca โญ 30,232
Code and documentation to train Stanford's Alpaca models, and generate the data.
๐ crfm.stanford.edu/2023/03/13/alpaca.html
nirdiamant/RAG_Techniques โญ 29,587
The most comprehensive and dynamic collections of Retrieval-Augmented Generation (RAG) tutorials available today. This repository serves as a hub for cutting-edge techniques aimed at enhancing the accuracy, efficiency, and contextual richness of RAG systems.
๐ diamant-ai.com
meta-llama/llama3 โญ 29,219
The official Meta Llama 3 GitHub site
microsoft/semantic-kernel โญ 28,589
An SDK that integrates LLMs like OpenAI, Azure OpenAI, and Hugging Face with conventional programming languages like C#, Python, and Java
๐ aka.ms/semantic-kernel
qwenlm/Qwen3 โญ 27,654
Qwen3 is the large language model series developed by Qwen team, Alibaba Cloud.
deepset-ai/haystack โญ 26,579
Open-source AI orchestration framework for building context-engineered, production-ready LLM applications. Design modular pipelines and agent workflows with explicit control over retrieval, routing, memory, and generation. Built for scalable agents, RAG, multimodal applications, semantic search, and conversational s...
๐ haystack.deepset.ai
huggingface/open-r1 โญ 26,477
The goal of this repo is to build the missing pieces of the R1 pipeline such that everybody can reproduce and build on top of it
cinnamon/kotaemon โญ 25,779
An open-source RAG UI for chatting with your documents. Built with both end users and developers in mind
๐ cinnamon.github.io/kotaemon
vision-cair/MiniGPT-4 โญ 25,609
Open-sourced codes for MiniGPT-4 and MiniGPT-v2 (https://minigpt-4.github.io, https://minigpt-v2.github.io/)
๐ minigpt-4.github.io
anthropics/knowledge-work-plugins โญ 25,505
Knowledge Work Plugins that turn Claude into a specialist for your role, team, and company
promptfoo/promptfoo โญ 25,366
Test your prompts, agents, and RAGs. Red teaming/pentesting/vulnerability scanning for AI. Compare performance of GPT, Claude, Gemini, DeepSeek, and more. Simple declarative configs with command line and CI/CD integration. Used by OpenAI and Anthropic.
๐ promptfoo.dev
microsoft/JARVIS โญ 25,315
JARVIS, a system to connect LLMs with ML community. Paper: https://arxiv.org/pdf/2303.17580.pdf
haotian-liu/LLaVA โญ 25,035
[NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.
๐ llava.hliu.cc
openai/gpt-2 โญ 25,010
Code for the paper "Language Models are Unsupervised Multitask Learners"
๐ openai.com/blog/better-language-models
dao-ailab/flash-attention โญ 24,999
Fast and memory-efficient exact attention
karpathy/llm-council โญ 24,952
LLM Council works together to answer your hardest questions
karpathy/minGPT โญ 24,909
A minimal PyTorch re-implementation of the OpenAI GPT (Generative Pretrained Transformer) training
modelcontextprotocol/python-sdk โญ 24,368
The Model Context Protocol allows applications to provide context for LLMs in a standardized way, separating the concerns of providing context from the actual LLM interaction.
๐ py.sdk.modelcontextprotocol.io
vanna-ai/vanna โญ 23,813
RAG (Retrieval-Augmented Generation) framework for SQL generation and related functionality.
๐ vanna.ai/docs
volcengine/verl โญ 23,573
veRL is a flexible, efficient and production-ready RL training library for large language models (LLMs).
๐ verl-project.github.io
mlc-ai/mlc-llm โญ 23,179
Universal LLM Deployment Engine with ML Compilation
๐ llm.mlc.ai
skyvern-ai/skyvern โญ 23,053
Skyvern automates browser-based workflows using LLMs and computer vision. It provides a simple API endpoint to fully automate manual workflows, replacing brittle or unreliable automation solutions.
๐ www.skyvern.com
jundot/omlx โญ 22,155
LLM inference server with continuous batching & SSD caching for Apple Silicon โ managed from the macOS menu bar
๐ omlx.ai
qwenlm/Qwen โญ 21,819
The official repo of Qwen (้ไนๅ้ฎ) chat & pretrained large language model proposed by Alibaba Cloud.
guidance-ai/guidance โญ 21,772
A guidance language for controlling large language models.
huggingface/peft โญ 21,712
๐ค PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.
๐ huggingface.co/docs/peft
rasahq/rasa โญ 21,326
๐ฌ Open source machine learning framework to automate text- and voice-based conversations: NLU, dialogue management, connect to Slack, Facebook, and more - Create chatbots and voice assistants
๐ rasa.com/docs/rasa
openai/chatgpt-retrieval-plugin โญ 21,246
The ChatGPT Retrieval Plugin lets you easily find personal or work documents by asking questions in natural language.
nandhakishorm/laya โญ 20,688
Non-autoregressive System 1 decision engine. Typed choice, score and yes/no decisions over any text in a single forward pass, in 100+ languages, with a router that picks the right checkpoint per request.
๐ huggingface.co/convaiinnovations/laya
karpathy/llama2.c โญ 20,101
Inference Llama 2 in one file of pure C
stitionai/devika โญ 19,562
Devika is an advanced AI software engineer that can understand high-level human instructions, break them down into steps, research relevant information, and write code to achieve the given objective.
๐ winfunc.com
kvcache-ai/ktransformers โญ 19,533
A Flexible Framework for LLM Inference Optimizations - allows researchers to replace original torch modules with optimized variants
๐ kvcache-ai.github.io/ktransformers
openai/evals โญ 19,490
Evals is a framework for evaluating LLMs and LLM systems, and an open-source registry of benchmarks.
mlc-ai/web-llm โญ 19,159
High-performance In-browser LLM Inference Engine
๐ webllm.mlc.ai
tloen/alpaca-lora โญ 18,903
Instruct-tune LLaMA on consumer hardware
facebookresearch/llama-cookbook โญ 18,561
Welcome to the Llama Cookbook! This is your go to guide for Building with Llama: Getting started with Inference, Fine-Tuning, RAG. We also show you how to solve end to end problems using Llama model family and using them on various provider services
๐ www.llama.com
browser-use/browser-harness โญ 18,069
Browser Harness | Self-healing harness that enables LLMs to complete any task.
๐ browser-harness.com
nvidia/Megatron-LM โญ 17,975
Ongoing research training transformer models at scale
๐ docs.nvidia.com/megatron-core/developer-guide/latest/get-started/quickstart.html
idea-research/Grounded-Segment-Anything โญ 17,732
Grounded SAM: Marrying Grounding DINO with Segment Anything & Stable Diffusion & Recognize Anything - Automatically Detect , Segment and Generate Anything
๐ arxiv.org/abs/2401.14159
anthropics/claude-quickstarts โญ 17,721
A collection of projects designed to help developers quickly get started with building applications using the Anthropic API. Each quickstart provides a foundation that you can easily build upon and customize for your specific needs.
transformeroptimus/SuperAGI โญ 17,685
<โก๏ธ> SuperAGI - A dev-first open source autonomous AI agent framework. Enabling developers to build, manage & run useful autonomous agents quickly and reliably.
๐ superagi.com
ryancodrai/turbovec โญ 17,231
A vector index built on TurboQuant, written in Rust with Python bindings
๐ pypi.org/project/turbovec
qwenlm/Qwen-Agent โญ 17,117
Agent framework and applications built upon Qwen>=3.0, featuring Function Calling, MCP, Code Interpreter, RAG, Chrome extension, etc.
๐ pypi.org/project/qwen-agent
gibsonai/Memori โญ 16,905
Memori enables any LLM to remember conversations, learn from interactions, and maintain context across sessions
๐ memorilabs.ai
qwenlm/Qwen3-Coder โญ 16,846
Qwen3-Coder is the code version of Qwen3, the large language model series developed by Qwen team.
mayooear/ai-pdf-chatbot-langchain โญ 16,589
AI PDF chatbot agent built with LangChain & LangGraph
๐ www.youtube.com/watch?v=of6soldiewu
andrewyng/aisuite โญ 16,293
Simple, unified interface to multiple Generative AI providers. aisuite makes it easy for developers to use multiple LLM through a standardized interface.
facebookresearch/codellama โญ 16,251
Inference code for CodeLlama models
dottxt-ai/outlines โญ 15,870
Structured Text Generation from LLMs
๐ dottxt-ai.github.io/outlines
explodinggradients/ragas โญ 15,820
Supercharge Your LLM Application Evaluations ๐
๐ docs.ragas.io
pipecat-ai/pipecat โญ 15,775
Open Source framework for voice agents, multimodal apps, and realtime AI. Maintained by Daily and the community.
๐ pipecat.ai
modelscope/ms-swift โญ 15,708
Use PEFT or Full-parameter to CPT/SFT/DPO/GRPO 600+ LLMs (Qwen3.6, DeepSeek-V4, GLM-5.1, InternLM3, Llama4, ...) and 300+ MLLMs (Qwen3-VL, Qwen3-Omni, InternVL3.5, Ovis2.5, GLM4.5v, Gemma4, Llava, Phi4, ...) (AAAI 2025).
๐ swift.readthedocs.io/zh-cn/latest
geeeekexplorer/nano-vllm โญ 15,584
A lightweight vLLM implementation built from scratch.
thudm/ChatGLM2-6B โญ 15,515
ChatGLM2-6B: An Open Bilingual Chat LLM | ๅผๆบๅ่ฏญๅฏน่ฏ่ฏญ่จๆจกๅ
swivid/F5-TTS โญ 15,269
Official code for "F5-TTS: A Fairytaler that Fakes Fluent and Faithful Speech with Flow Matching"
๐ arxiv.org/abs/2410.06885
llmware-ai/llmware โญ 14,834
Unified framework for building enterprise RAG pipelines with small, specialized models
๐ llmware-ai.github.io/llmware
blinkdl/RWKV-LM โญ 14,713
RWKV (pronounced RwaKuv) is an RNN with great LLM performance, which can also be directly trained like a GPT transformer (parallelizable). We are at RWKV-7 "Goose". So it's combining the best of RNN and transformer - great performance, linear time, constant space (no kv-cache), fast training, infinite ctx_len, and f...
fauxpilot/fauxpilot โญ 14,682
FauxPilot - an open-source alternative to GitHub Copilot server
flashml-org/FreeToken โญ 14,438
FreeToken brings datacenter-scale model serving to your desktop. Run massive models locally, fast and efficiently.
๐ flashml.ai
eleutherai/lm-evaluation-harness โญ 14,054
A framework for few-shot evaluation of language models.
๐ www.eleuther.ai
instructor-ai/instructor โญ 13,935
Instructor is a Python library that makes it a breeze to work with structured outputs from large language models (LLMs). Built on top of Pydantic, it provides a simple, transparent, and user-friendly API to manage validation, retries, and streaming responses.
๐ python.useinstructor.com
e2b-dev/E2B โญ 13,924
E2B is an open-source infrastructure that allows you to run AI-generated code in secure isolated sandboxes in the cloud
๐ docs.e2b.dev/?utm_source=github&utm_medium=referral&utm_campaign=repo_website&utm_content=e2b
microsoft/LoRA โญ 13,810
Code for loralib, an implementation of "LoRA: Low-Rank Adaptation of Large Language Models"
๐ arxiv.org/abs/2106.09685
startrail-org/LEANN โญ 13,762
The smallest vector index in the world
๐ arxiv.org/abs/2506.08276
lightning-ai/litgpt โญ 13,679
20+ high-performance LLMs with recipes to pretrain, finetune and deploy at scale.
๐ lightning.ai
lightning-ai/litgpt โญ 13,677
20+ high-performance LLMs with recipes to pretrain, finetune and deploy at scale.
๐ lightning.ai
jiayi-pan/TinyZero โญ 13,240
TinyZero is a reproduction of DeepSeek R1 Zero in countdown and multiplication tasks.
vaibhavs10/insanely-fast-whisper โญ 13,061
An opinionated CLI to transcribe Audio files w/ Whisper on-device! Powered by ๐ค Transformers, Optimum & flash-attn
shishirpatil/gorilla โญ 13,038
Enables LLMs to use tools by invoking APIs. Given a query, Gorilla comes up with the semantically and syntactically correct API.
๐ gorilla.cs.berkeley.edu
paddlepaddle/PaddleNLP โญ 12,977
Easy-to-use and powerful LLM and SLM library with awesome model zoo.
๐ paddlenlp.readthedocs.io
the-pocket/PocketFlow-Tutorial-Codebase-Knowledge โญ 12,733
Pocket Flow: Codebase to Tutorial
๐ code2tutorial.com/
google-research/vision_transformer โญ 12,719
Vision Transformer and MLP-Mixer Architectures
sapientinc/HRM โญ 12,643
Hierarchical Reasoning Model (HRM), a novel recurrent architecture that attains significant computational depth while maintaining both training stability and efficiency
๐ sapient.inc
axolotl-ai-cloud/axolotl โญ 12,492
Go ahead and axolotl questions
๐ docs.axolotl.ai
chainlit/chainlit โญ 12,467
Build Conversational AI in minutes โก๏ธ
๐ docs.chainlit.io
cactus-compute/needle โญ 12,434
Automation foundation model for tiny devices: 2-bit, 8-29 MB, tool calls, structured extraction and embeddings on phones, wearables, smart homes, robots, cars and microcontrollers.
๐ cactuscompute.com
openlmlab/MOSS โญ 12,252
An open-source, tool-augmented conversational language model from Fudan University
๐ txsun1997.github.io/blogs/moss.html
h2oai/h2ogpt โญ 11,965
Private chat with local GPT with document, images, video, etc. 100% private, Apache 2.0. Supports oLLaMa, Mixtral, llama.cpp, and more. Demo: https://gpt.h2o.ai/ https://gpt-docs.h2o.ai/
๐ h2o.ai
lmcache/LMCache โญ 11,893
LMCache is an LLM serving engine extension to reduce TTFT and increase throughput, especially under long-context scenarios
๐ lmcache.ai
the-pocket/PocketFlow โญ 11,300
Pocket Flow: 100-line LLM framework. Let Agents build Agents!
๐ the-pocket.github.io/pocketflow
microsoft/promptflow โญ 11,242
Build high-quality LLM apps - from prototyping, testing to production deployment and monitoring.
๐ microsoft.github.io/promptflow
artidoro/qlora โญ 11,021
QLoRA: Efficient Finetuning of Quantized LLMs
๐ arxiv.org/abs/2305.14314
fareedkhan-dev/train-llm-from-scratch โญ 10,892
A straightforward method for training your LLM, from downloading data to generating text.
๐ fareedkhan-dev.github.io/train-llm-from-scratch
mistralai/mistral-inference โญ 10,823
Official inference library for Mistral models
๐ mistral.ai
databrickslabs/dolly โญ 10,806
Databricksโ Dolly, a large language model trained on the Databricks Machine Learning Platform
๐ www.databricks.com/blog/2023/03/24/hello-dolly-democratizing-magic-chatgpt-open-models.html
karpathy/minbpe โญ 10,733
Minimal, clean code for the Byte Pair Encoding (BPE) algorithm commonly used in LLM tokenization.
skypilot-org/skypilot โญ 10,634
The AI Compute Platform for frontier teams. SkyPilot turns fragmented AI compute into one AI supercomputer, so frontier AI teams build custom intelligence faster.
๐ skypilot.ai
abetlen/llama-cpp-python โญ 10,630
Simple Python bindings for @ggerganov's llama.cpp library.
๐ llama-cpp-python.readthedocs.io
startrail-org/PixelRAG โญ 10,088
Renders documents as screenshots and retrieves over the images directly.
๐ arxiv.org/pdf/2606.28344
vikhyat/moondream โญ 10,056
A tiny open-source computer-vision language model designed to run efficiently on edge devices
๐ moondream.ai
sjtu-ipads/PowerInfer โญ 9,803
High-speed Large Language Model Serving for Local Deployment
mshumer/gpt-prompt-engineer โญ 9,681
Simply input a description of your task and some test cases, and the system will generate, test, and rank a multitude of prompts to find the ones that perform the best.
blinkdl/ChatRWKV โญ 9,498
ChatRWKV is like ChatGPT but powered by RWKV (100% RNN) language model, and open source.
boundaryml/baml โญ 9,263
The programming language for agents
๐ boundaryml.com/explore
future-house/paper-qa โญ 9,236
High-accuracy retrieval augmented generation (RAG) on PDFs or text files, with a focus on the scientific literature
๐ futurehouse.gitbook.io/futurehouse-cookbook
bytedance/Dolphin โญ 9,052
A novel multimodal document image parsing model following an analyze-then-parse paradigm
jzhang38/TinyLlama โญ 9,014
The TinyLlama project is an open endeavor to pretrain a 1.1B Llama model on 3 trillion tokens.
thudm/CodeGeeX โญ 8,807
CodeGeeX: An Open Multilingual Code Generation Model (KDD 2023)
๐ codegeex.cn
apple/ml-ferret โญ 8,662
Ferret: Refer and Ground Anything Anywhere at Any Granularity
optimalscale/LMFlow โญ 8,487
An Extensible Toolkit for Finetuning and Inference of Large Foundation Models. Large Models for All.
๐ optimalscale.github.io/lmflow
lianjiatech/BELLE โญ 8,270
BELLE: Be Everyone's Large Language model Engine๏ผๅผๆบไธญๆๅฏน่ฏๅคงๆจกๅ๏ผ
eleutherai/gpt-neo โญ 8,261
An implementation of model parallel GPT-2 and GPT-3-style models using the mesh-tensorflow library.
๐ www.eleuther.ai
zilliztech/GPTCache โญ 8,200
Semantic cache for LLMs. Fully integrated with LangChain and llama_index.
๐ gptcache.readthedocs.io
plachtaa/VALL-E-X โญ 7,927
An open source implementation of Microsoft's VALL-E X zero-shot TTS model. Demo is available in https://plachtaa.github.io/vallex/
nirdiamant/Prompt_Engineering โญ 7,864
A comprehensive collection of tutorials and implementations for Prompt Engineering techniques, ranging from fundamental concepts to advanced strategies.
๐ diamant-ai.com
01-ai/Yi โญ 7,833
The Yi series models are the next generation of open-source large language models trained from scratch by 01.AI.
๐ 01.ai
sweepai/sweep โญ 7,710
Sweep: AI coding assistant for JetBrains
๐ sweep.dev
weaviate/Verba โญ 7,703
Retrieval Augmented Generation (RAG) chatbot powered by Weaviate
thudm/GLM-130B โญ 7,649
GLM-130B: An Open Bilingual Pre-Trained Model (ICLR 2023)
openlm-research/open_llama โญ 7,528
OpenLLaMA: An Open Reproduction of LLaMA
bigcode-project/starcoder โญ 7,501
Home of StarCoder: fine-tuning & inference!
open-compass/opencompass โญ 7,467
OpenCompass is an LLM evaluation platform, supporting a wide range of models from OpenAI, Anthropic, Gemini, Qwen, GLM, DeepSeek, etc, across 100+ datasets covering knowledge, reasoning, coding, science, language, long-context, and safety.
๐ opencompass.org.cn
eleutherai/gpt-neox โญ 7,461
An implementation of model parallel autoregressive transformers on GPUs, based on the Megatron and DeepSpeed libraries
๐ www.eleuther.ai
guardrails-ai/guardrails โญ 7,441
Open-source Python package for specifying structure and type, validating and correcting the outputs of large language models (LLMs)
๐ www.guardrailsai.com/docs
apple/ml-fastvlm โญ 7,418
FastVLM: Efficient Vision Encoding for Vision Language Models
arcee-ai/mergekit โญ 7,366
Tools for merging pretrained large language models.
internlm/InternLM โญ 7,279
Official release of InternLM series (InternLM, InternLM2, InternLM2.5, InternLM3).
๐ internlm.readthedocs.io
mit-han-lab/streaming-llm โญ 7,267
[ICLR 2024] Efficient Streaming Language Models with Attention Sinks
๐ arxiv.org/abs/2309.17453
minedojo/Voyager โญ 7,224
An Open-Ended Embodied Agent with Large Language Models
๐ voyager.minedojo.org
nvidia/Guardrails โญ 7,178
NeMo Guardrails is an open-source toolkit for easily adding programmable guardrails to LLM-based conversational systems.
๐ docs.nvidia.com/nemo/guardrails/latest/index.html
bhaskatripathi/pdfGPT โญ 7,162
PDF GPT allows you to chat with the contents of your PDF file by using GPT capabilities. The most effective open source solution to turn your pdf files in a chatbot!
๐ huggingface.co/spaces/bhaskartripathi/pdfchatter
ml-explore/mlx-lm โญ 7,116
Run LLMs with MLX
thetom/turboquant_plus โญ 7,032
Implementation of TurboQuant (ICLR 2026) with implementation work, experiments, and follow-on findings beyond the base paper. Now in vLLM.
apple/corenet โญ 7,005
CoreNet is a deep neural network toolkit that allows researchers and engineers to train standard and novel small and large-scale models for variety of tasks, including foundation models (e.g., CLIP and LLM), object classification, object detection, and semantic segmentation.
qwenlm/Qwen-VL โญ 6,729
The official repo of Qwen-VL (้ไนๅ้ฎ-VL) chat & pretrained large vision language model proposed by Alibaba Cloud.
langchain-ai/opengpts โญ 6,719
An open source effort to create a similar experience to OpenAI's GPTs and Assistants API.
gepa-ai/gepa โญ 6,707
GEPA (Genetic-Pareto) is a framework for optimizing arbitrary systems composed of text componentsโlike AI prompts, code snippets, or textual specsโagainst any evaluation metric
๐ gepa-ai.github.io/gepa
microsoft/LLMLingua โญ 6,692
[EMNLP'23, ACL'24] To speed up LLMs' inference and enhance LLM's perceive of key information, compress the prompt and KV-Cache, which achieves up to 20x compression with minimal performance loss.
๐ llmlingua.com
allenai/OLMo โญ 6,684
OLMo is a repository for training and using AI2's state-of-the-art open language models. It is designed by scientists, for scientists.
๐ allenai.org/olmo
yuliang-liu/MonkeyOCR โญ 6,649
A lightweight LMM-based Document Parsing Model with a Structure-Recognition-Relation Triplet Paradigm
linkedin/Liger-Kernel โญ 6,629
Efficient Triton Kernels for LLM Training
๐ linkedin.github.io/liger-kernel
run-llama/rags โญ 6,551
RAGs is a Streamlit app that lets you create a RAG pipeline from a data source using natural language.
flashinfer-ai/flashinfer โญ 6,484
FlashInfer is a library and kernel generator for Large Language Models that provides high-performance implementation of LLM GPU kernels such as FlashAttention, SparseAttention, PageAttention, Sampling
๐ flashinfer.ai
langchain-ai/chat-langchain โญ 6,461
Locally hosted chatbot specifically focused on question answering over the LangChain documentation
๐ chat.langchain.com
agiresearch/AIOS โญ 6,406
AIOS, a Large Language Model (LLM) Agent operating system, embeds large language model into Operating Systems (OS) as the brain of the OS, enabling an operating system "with soul" -- an important step towards AGI.
๐ docs.aios.foundation
nat/openplayground โญ 6,348
An LLM playground you can run on your laptop
pytorch-labs/gpt-fast โญ 6,255
Simple and efficient pytorch-native transformer text generation in <1000 LOC of python.
lightning-ai/lit-llama โญ 6,081
Implementation of the LLaMA language model based on nanoGPT. Supports flash attention, Int8 and GPTQ 4bit quantization, LoRA and LLaMA-Adapter fine-tuning, pre-training. Apache 2.0-licensed.
jaredpalmer/kev โญ 6,080
tiny Jev-like family of decision models built on top of Qwen3.5 you can train and run on your own
meta-pytorch/torchtune โญ 5,812
a PyTorch library for easily authoring, post-training, and experimenting with recipes for SF
dylanhogg/awesome-python is a public repo on GitHub by dylanhogg. ๐ Hand-picked awesome Python libraries and frameworks, organised by category.
It declares the MIT license on GitHub.
Its maker has not tagged a system, so it is unknown here. Its README says what it needs.
Open "Take it" on its page: Take My Repo writes an install plan for your machine and hands it to your AI agent (Claude Code, Codex or Cursor), which asks you before each step. Take My Repo has not tested it on any machine.
Its last change on GitHub was on 2026-11-04. Take My Repo does not judge from that whether it is maintained.
Nobody has reviewed it on Take My Repo yet, which says nothing about its quality.

Master programming by recreating your favorite technologies from scratch.
Rich is a Python library for rich text and beautiful formatting in the terminal.
๐ท๏ธ The BEST Web Scraping framework that handles everything from a single request to a full-scale crawl! Don't be shy, join here: https://discord.gg/EMgGbDceNQ and follow here for daily tips and tricks: https://x.com/Scrapling_dev
12 weeks, 26 lessons, 52 quizzes, classic Machine Learning for all
Bring data to life with SVG, Canvas and HTML. :bar_chart::chart_with_upwards_trend::tada:
This page is also available as structured data, with the same sources and dates.
/api/v1/resources/gh/dylanhogg/awesome-pythonTake My Repo has not tested this on your machine. Requirements come from the project's own documentation.