Open source llm projects
Every project in the registry tagged llm, ranked by real GitHub adoption.
The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor
Desktop AI agent with persistent memory across platforms
Run open-source LLMs locally on your own machine
Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.
Build and deploy AI agents and RAG pipelines visually
One interface for every AI model you run or connect
Let AI agents control any browser, at scale
🪨 why use many token when few token do trick. Viral skill + proxy for coding agents that cuts 65% of tokens by talking like a caveman.
A high-throughput and memory-efficient inference and serving engine for LLMs
Autonomous coding agents that complete real engineering tasks
LLM-ready web crawler built for AI data pipelines
CLI proxy that reduces LLM token consumption by 60-90% on common dev commands. Single Rust binary, zero dependencies
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. Li
Persistent memory layer for AI agents and apps
Chat with your documents using any LLM, fully private
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 dashbo
Agent skill that removes signs of AI-generated writing from text
LLM gateway for auth, load balancing, and spend tracking
Ready-to-run cloud templates for RAG, AI pipelines, and enterprise search with live data. 🐳Docker-friendly.⚡Always in sync with Sharepoint, Google Drive, S3, K
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 k
Multi-model AI desktop client with local-first privacy
LlamaIndex is the document processing platform for AI
Self-hosted AI runtime for text, voice, vision, and agents
【低代码v2.0,一句话即可生成整个系统】企业级AI低代码平台,一键生成前后端代码甚至整个系统。 AI Skills 一句话画流程、设计表单、生成报表、大屏。内置 AI应用平台涵盖:AI聊天、知识库、流程编排、MCP插件等,兼容主流大模型。引领AI低代码「Skills 生成 → 在线配置 → 代码生成 → 手工合并->
Open-source super AI assistant & Agent Harness. Plans tasks, runs tools and skills, self-evolves with memory and knowledge. Multi-agent, multi-model, multi-chan
Effortlessly organize your digital documents
High-performance vector database for GenAI applications
AI Agent Assistant & development framework that integrates lots of IM platforms, LLMs, plugins and AI feature, and can be your openclaw alternative. ✨
Run AI models locally or connect to cloud, privately
Build resilient agents.
OpenHuman is an open source agent harness with local-first memory, agent orchestration, and workflows
[EMNLP2025] LightRAG: Simple and Fast Retrieval-Augmented Generation
📑 PageIndex: Document Index for Vectorless, Reasoning-based RAG
An open-source engine that turns continuous content streams into search and monitoring. Durable ingestion, hybrid search, alerts, and plugins for formats, model
AI second brain for research, automation, and personal agents
⌥ Coding agent with the IDE wired in
Open source LLM engineering platform for AI-powered applications
A modular graph-based Retrieval-Augmented Generation (RAG) system
DeepSeek-native AI coding agent for your terminal. Engineered around prefix-cache stability — leave it running.
817 structured cybersecurity skills for AI agents · Mapped to 6 frameworks: MITRE ATT&CK, NIST CSF 2.0, MITRE ATLAS, D3FEND, NIST AI RMF & MITRE F3 (Fight Fraud
Build and run agents you can see, understand and trust.
Unified AI-powered enterprise search across company data
Local-first code intelligence graph for MCP and CLI. Builds a persistent map of your codebase so AI coding tools read only what matters, with benchmarked contex
Python scraper based on AI
Local AI meeting transcription with zero data leaving your device
Composio powers 1000+ toolkits, tool search, context management, authentication, and a sandboxed workbench to help you build AI agents that turn intent into act
Build powerful AI knowledge bases with ease
An open-source AI coding agent that lives in your terminal.
Transform natural language into SQL queries with AI
Test your prompts, agents, and RAGs. Red teaming/pentesting/vulnerability scanning for AI. Compare performance of GPT, Claude, Gemini, DeepSeek, and more. Simpl
Automate any website workflow with AI and computer vision
Debug, evaluate, and monitor your LLM applications, RAG systems, and agentic workflows with comprehensive tracing, automated evaluations, and production-ready d
AI assistant that enhances enterprise knowledge management
A powerful GUI app and Toolkit for Claude Code - Create custom agents, manage interactive Claude Code sessions, run secure background agents, and more.
24/7 screen and audio recorder with AI memory search
Build unlimited AI apps locally with zero vendor lock-in
数字生命卡兹克开源的 AI Skills 合集 | Agent Skills: leader(帮你定义目标), neat-freak 洁癖, hv-analysis, khazix-writer & more — Claude Code, Codex & 40+ agents
🎭 277 个即插即用的 AI 专家角色 — 支持 Claude Code/Cursor/Copilot 等 20 种工具,覆盖工程/设计/营销/金融等 20 个部门。含 64 个中国市场原创智能体(小红书/抖音/微信/飞书/钉钉/Qt 上位机/机械设计)。搭配编排器 agency-orchestrator,一句话即
The most RAM efficient harness
Related tags
Frequently asked questions
How many open source llm projects are there?
This registry tracks 314 projects tagged llm, with 5,113,462 GitHub stars between them. The most-adopted is ECC at 295,522 stars.
Are these llm projects free to use?
Yes — 297 of the 314 carry an explicit open-source licence across 4 distinct licences, so there is no licence fee. Where a project also sells a hosted or enterprise version, the self-hosted path remains free.
Which llm project should I choose?
The list above is ranked by GitHub stars, but stars measure attention rather than fit. Check three things on each card: the licence (permissive versus copyleft), the language it is written in, and the last-push date — a high-star project that has not been pushed in a year is a liability.
Are these llm projects still maintained?
283 of the 314 were pushed in the last 90 days, and every card shows its exact last-push date so you can see the rest. Sort your shortlist by that date before committing to a migration.