maka
Apache Maka (Incubating) is a high-performance agent workspace that keeps a complete record of everything it did.
- 6k
- TypeScript
- Apache-2.0
- 8 h ago
Apache Maka (Incubating) is a high-performance agent workspace that keeps a complete record of everything it did.
Text generation model, used with transformers.
🎨 NeMo Data Designer: Generate high-quality synthetic data from scratch or from seed data.
Text generation model, used with gguf.
Source-available agent platform for Global × China enterprises — wire every system through one agent core. Self-hosted, any LLM.
ReSearch: Learning to Reason with Search for LLMs via Reinforcement Learning & ReCall: Learning to Reason with Tool Call for LLMs via Reinforcement Learning
An autonomous agent that takes work, does work, gets paid, and gets better at it.
AgenticX is a unified, production-ready multi-agent platform — Python SDK + CLI (agx) + Studio server + Machi desktop app. Features Meta-Agent orchestration, 15+ LLM providers, MCP Hub, hierarchical memory, avatar & group chat, skill ecosystem, safety sandbox, and IM gateway (Feishu/WeChat).
Easily create LLM tools and agents using plain Bash/JavaScript/Python functions.
LLaVA-Plus: Large Language and Vision Assistants that Plug and Learn to Use Skills
Official repository for DR Tulu: Reinforcement Learning with Evolving Rubrics for Deep Research
Second Brain is an agentic framework that acts as an operating system, using local file intelligence, workflow automation, and LLMs to complete tasks and communicate over multiple modalities and messaging platforms.
TypeScript AI agent framework: cognitive memory, dynamic personalities, emergent behaviors and self-building designs
ScienceClaw is a personal research assistant built with LangChain DeepAgents and AIO Sandbox infrastructure, adopting a completely new architecture beyond OpenClaw. It offers stronger security, better transparency, and a more user-friendly experience.
Companionship, chat, coding, and work share one memory and context framework — the kind of AI you see in science fiction: it keeps you company, and it gets things done with you.(这是一个基于上下文和注意力机制做的一个多元化的agent项目)
Agentic AI explained with chickens 🐔 every pattern a runnable, CI-checked file.
OpenART is an open-source framework designed to evaluate the safety and robustness of autonomous AI agents in dynamic, long-horizon, and stateful environments. It stress-tests agent runtimes against multi-step state poisoning, privilege escalation, and tool-use vulnerabilities across 10,000+ benchmark scenarios.
The lossless, headless coding agent harness. One 7 MB static binary, four tools, plain stdin/stdout, no silent cuts.
Text generation model, used with transformers.
Text generation model, used with transformers.
Learn to build and customize multi-agent systems using the AutoGen. The course teaches you to implement complex AI applications through agent collaboration and advanced design patterns.
The marketplace for verifiable AI outcomes: state a task, get a fixed price upfront, and Primitive Bench routes across tools to complete it, refunded if the outcome isn't delivered. This repo is the open verification layer.
Learn function calling and tool calling from simple tools to full agents.
开源桌面 AI Agent 与 CLI:长期记忆、多 Agent、实时语音;Qwen3.8-27B Coder390 EfficientThink 本地 GGUF(llama.cpp Q2/Q3,内置 Q4 MTP)· Open-source desktop AI agent & CLI with Coder390 local models
AI Agents internals - system prompts, tool architectures, and implementation patterns
Control Ableton Live from Claude and any LLM. An MCP server built on Ableton's official Extensions SDK: one .ablx, no Remote Script, no AbletonOSC, no Max for Live. TypeScript, Live 12.4.5 Suite beta.
TypeScript AI agent framework with recorded context, tool calls and decisions, plus configurable answer checks.
uh-harness (UH) — local-first, provider-agnostic agent harness for your desktop: chat, memory graph, telemetry, backups, skills. MIT. Not affiliated with the PyPI package universal-harness.
A harness-engineered AI agent runtime. Build agents with tool isolation, self-correction, and permission scoping out of the box.
Guides for connecting tool-capable Muapi-hosted models to OpenClaw, Hermes Agent, and other general-purpose AI agents.
卡内基梅隆大学 11-768《AI Agents》课程中文详细讲义:覆盖工具使用、长上下文、记忆、规划、编码与计算机使用 Agent,以及 SFT/RL 训练与 Agent 安全
Watch two AI agents collaborate via filesystem in real-time
Runs in the browser on Hugging Face