llm

Open repos and models their makers tagged llm, most starred first. The same for everyone.

AI agentsRepo

ECC

The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.

  • 306k
  • JavaScript
  • MIT
  • 1 d ago
affaan-mTake it
AutomationRepo

dify

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.

  • 161k
  • Python
  • 4 h ago
langgeniusTake it
AI agentsRepo

graphify

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.

  • 150k
  • Python
  • Apache-2.0
  • 11 h ago
Graphify-LabsTake it
AI on my own machineRepo

caveman

why use many token when few token do trick. Skill + local proxy for coding agents: shorter answers, smaller tool output, every original recoverable.

  • 121k
  • Go
  • Apache-2.0
  • 10 h ago
JuliusBrusseeTake it
AI agentsRepo

crawl4ai

Official Crawl4AI Cloud: a hosted web scraping, extraction, and search API for AI agents. Free API key, 1,000 credits a month, no card. Fully open source: this repo is the Apache-2.0 crawler that powers it, and you can self-host it.

  • 87k
  • Python
  • Apache-2.0
  • 22 h ago
unclecodeTake it
AI agentsRepo

deer-flow

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.

  • 85k
  • Python
  • MIT
  • 4 h ago
bytedanceTake it
AI agentsRepo

headroom

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.

  • 80k
  • Python
  • Apache-2.0
  • 12 h ago
headroomlabs-aiTake it
AI on my own machineRepo

unsloth

Local UI to run and train LLMs and diffusion models. Supports GGUF, MLX, Qwen3.8, DeepSeek-V4.1, MiniMax-H3, Gemma 4, FLUX and more.

  • 80k
  • Python
  • Apache-2.0
  • 4 h ago
unslothaiTake it
AI on my own machineRepo

dsh-our-free-model

在 dsh 里装上这个插件即可,无需登录、注册或填 API Key,就能使用包括 DeepSeek V4.1 Flash、Kimi K3 在内的前沿模型——完全免费,不限量。 All you do is install this plugin in dsh: no login, no sign-up, no API key — the frontier models are just there, DeepSeek V4.1 Flash and Kimi K3 among them. Completely free, with no usage cap.

  • 79k
  • JavaScript
  • 6 h ago
Ebony-VinylTake it
AI on my own machineRepo

daily_stock_analysis

LLM 驱动的多市场股票智能分析系统:多源行情、实时新闻、决策看板与自动推送,支持零成本定时运行。 LLM-powered multi-market stock analysis system with multi-source market data, real-time news, decision dashboard, automated notifications, and cost-free scheduled runs.

  • 73k
  • Python
  • MIT
  • 17 h ago
ZhuLinsenTake it
AI agentsRepo

system_prompts_leaks

Leaked system prompts of ChatGPT, Claude, Gemini and more. The hidden system prompt of every popular chatbot, in full, every version since May 2025. Also Anthropic Claude Code, OpenAI Codex, Google Antigravity, xAI Grok, Meta Muse, Moonshot Kimi, Alibaba Qwen, Z.ai GLM ZCode, MiniMax, Cursor, Perplexity, DeepSeek and 30+ others. Updated daily.

  • 72k
  • Python
  • CC0-1.0
  • 4 h ago
asgeirtjTake it
Search GitHub and Hugging Face for llm

Send to which agent?

goes to the agent you pick.

Get , open it once and sign in. Then come back here and press the button again.