- hermes-agent by NousResearch, 263k stars. Personal agent that builds memory and skills over time
- AutoGPT by Significant-Gravitas, 188k stars. Platform for building and running autonomous AI agents
- ollama by ollama, 187k stars. Run open-weight language models locally from the command line and an API
- prompts.chat by f, 177k stars. Community library of shareable AI prompts that can be self-hosted
- langflow by langflow-ai, 157k stars. Visual builder for deploying AI agents and workflows built on React Flow
- langchain by langchain-ai, 150k stars. Platform for building LLM agents and applications in Python
- llama.cpp by ggml-org, 135k stars. LLM inference in C and C++
- TradingAgents by TauricResearch, 123k stars. Framework where LLM agents collaborate on stock trading decisions
- pi by earendil-works, 122k stars. Toolkit with a unified LLM API, agent loop, terminal UI and coding CLI
- caveman by JuliusBrussee, 120k stars. Skill and proxy for coding agents that makes replies terser to cut tokens
- LLMs-from-scratch by rasbt, 108k stars. Step-by-step notebooks for building a GPT-style LLM in PyTorch
- vllm by vllm-project, 97k stars. High-throughput inference and serving engine for large language models
- OpenHands by OpenHands, 93k stars. Agent platform that writes and runs code from natural language tasks
- OmniRoute by cheaper-inference, 88k stars. Single endpoint gateway routing requests to hundreds of LLM providers
- rtk by rtk-ai, 87k stars. CLI proxy that trims command output to cut LLM token use on dev commands
- MiroFish by 666ghj, 86k stars. Multi-agent swarm engine for predicting outcomes from a knowledge graph
- lobehub by lobehub, 86k stars. Workspace for building, scheduling and tracking a team of AI agents
- deer-flow by bytedance, 85k stars. Long-running agent harness with sandboxes, memory, tools and subagents
- llm-course by mlabonne, 85k stars. Course with roadmaps and Colab notebooks for learning large language models
- headroom by headroomlabs-ai, 80k stars. Compresses tool outputs and RAG chunks before they reach the LLM as a library, proxy, or MCP server
- ai-agents-for-beginners by microsoft, 80k stars. 18 lessons with notebooks on building AI agents from scratch
- unsloth by unslothai, 80k stars. Local UI for running and fine-tuning LLMs and diffusion models
- ai-engineering-from-scratch by rohitg00, 79k stars. Course that teaches AI engineering by building each piece from scratch
- daily_stock_analysis by ZhuLinsen, 72k stars. LLM-driven stock analysis with market data, news and scheduled reports
- system_prompts_leaks by asgeirtj, 71k stars. Collected system prompts from major AI chatbots and coding tools
- MetaGPT by FoundationAgents, 71k stars. Multi-agent framework that assigns software company roles to LLM agents
- context7 by upstash, 65k stars. Hosted up-to-date library documentation served to AI agents over MCP
- litellm by BerriAI, 63k stars. Gateway and Python SDK that calls 100+ LLM APIs in OpenAI format
- crewAI by crewAIInc, 61k stars. Python framework for orchestrating role-based autonomous agents
- mempalace by MemPalace, 61k stars. Open-source memory system for AI assistants, built on ChromaDB and MCP
- ai-agent-book by bojieli, 58k stars. Open-source book on AI agent design with full text, PDF, and chapter code
- freellmapi by tashfeenahmed, 52k stars. OpenAI-compatible gateway that routes requests across free LLM providers with failover
- new-api by QuantumNous, 52k stars. Self-hosted LLM gateway with OpenAI and Claude compatible APIs and usage logs
- LibreChat by LibreChat-AI, 47k stars. Self-hostable chat interface for many LLM providers with agents and MCP support
- AstrBot by AstrBotDevs, 47k stars. Agent framework with chat platform integrations, plugins and LLM support
- jan by janhq, 46k stars. Desktop app for running open LLMs locally as a ChatGPT alternative
- airllm by lyogavin, 42k stars. Runs large language models layer by layer so they fit in a small GPU's memory
- ai-engineering-hub by patchy631, 42k stars. Tutorials on LLMs, RAG, and AI agent apps, mostly as Jupyter notebooks
- BitNet by microsoft, 42k stars. Inference framework for running 1-bit quantized large language models
- heretic by p-e-w, 41k stars. Training-free tool that edits language models to reduce refusals and sycophancy
New repos every two days, stars refreshed daily. Visits are counted without cookies, and the numbers are public. How it works Data RSS Newsletter