Open source agentic-ai projects
Every project in the registry tagged agentic-ai, ranked by real GitHub adoption.
Build and deploy AI agents and RAG pipelines visually
Org chart, budgets, and governance for AI agent teams
RAGFlow is a leading open-source Retrieval-Augmented Generation (RAG) engine that fuses cutting-edge RAG with Agent capabilities to create a superior context la
Chat with your documents using any LLM, fully private
Privacy-first knowledge management with block-level linking
📑 PageIndex: Document Index for Vectorless, Reasoning-based RAG
Build AI copilots for your product in hours, not months
Anti-detect agentic browser: undetected browsing, browser automation, MCP server, AI web browsing agent, computer use, scraping, lead generation. No captchas.
Open-source dots for the web: an AI agent with its own browser, one that does not get blocked.
Open-source, self-hosted alternative to OpenAI Dots, Grok Bot. Built to be undetectable by anti-bot systems.
Anti detect browser and web browsing agent: an open-source MCP server for undetected browsing, AI web scraping and computer use agents. No captchas.
Composio powers 1000+ toolkits, tool search, context management, authentication, and a sandboxed workbench to help you build AI agents that turn intent into act
380 Claude Code skills & agent skills & plugins (30+ Agents, 70+ custom commands, 380+ skills, customizable references, scripts)for Claude Code, Codex, Gemini C
Open-source AI orchestration framework for building context-engineered, production-ready LLM applications. Design modular pipelines and agent workflows with exp
Distilly — Distill how they think into reusable Skills for any Agent or Bot. Formerly Colleague Skill（原同事 Skill）.
Build custom apps without code, deploy with ease
Security scanner for AI agent skills. Detect vulnerabilities, malicious patterns, security risks, prompt injection, data exfiltration, and supply-chain risks in
AI assistant that enhances enterprise knowledge management
Desktop multi-agent workforce for automating real tasks
An open-source Agent-first Identity and Access Management (IAM) /LLM MCP & agent gateway and auth server with web UI supporting OpenClaw, MCP, OAuth, OIDC, SAML
A framework for building, orchestrating and deploying AI agents and multi-agent workflows with support for Python and .NET.
One portable memory layer for every AI agent: local-first, Markdown-native, user-owned, and self-evolving across apps, tools, and workflows.
Practical patterns, starters & CLI tools for loop engineering with AI coding agents. Design systems that prompt and orchestrate agents (inspired by Addy Osmani
A smarter, self-hosted AI assistant — multi-user, multi-agent.
Pocket Flow: 100-line LLM framework. Let Agents build Agents!
Lean, fine tuned Opencode multi agent suite · Mix any models · Auto delegate tasks
The 100 line AI agent that solves GitHub issues or helps you in your command line. Radically simple, no huge configs, no giant monorepo—but scores >74% on SWE-b
Enterprise-grade, commercial-friendly agentic workflow platform for building next-generation SuperAgents.
A full-stack AI Red Teaming platform securing AI ecosystems via Agent Scan, Skills Scan, MCP scan, AI Infra scan and LLM jailbreak evaluation.
Backlog.md - A tool for managing project collaboration between humans and AI Agents in a git ecosystem
Self-hosted TypeScript agent runtime with durable approvals and verifiable run records. Own it, approve it, audit it.
A Modern Orchestration Engine for Security
Open-source, self-hosted alternative to Claude Duet: AI coworkers (named agents) with instructions, memory, routines, their own isolated computer, and your appr
Open-source alternative to OpenAI Dots: self-hosted AI chat, tools, approvals, connectors, and computer tasks.
Open-source AI-powered Security Operations Center — alert fusion, purple-team drills, agent-assisted triage, MITRE ATT&CK investigation. MIT-licensed, self-host
Nexent is a zero-code platform for auto-generating production-grade AI agents using Harness Engineering principles — unified tools, skills, memory, and orchestr
Super-fast/easy runtime validators and serializers via transformation
⚡️next-generation personal AI assistant powered by LLM, RAG and agent loops, supporting computer-use, browser-use and coding agent, demo: https://demo.openagent
AI-powered bug bounty hunting toolkit that works with or without subscription.
Open-Source Personal Cloud OS for Always-On Agents
Zero-modification Human-in-the-Loop adapter for OpenOPC's agentic DAG runtime.
Zero-modification Human-in-the-Loop adapter for OpenOPC's agentic DAG runtime.
Eko (Eko Keeps Operating) - Build Production-ready Agentic Workflow with Natural Language - eko.fellou.ai
Build, automate, and improve AI agents with your team
DeepAnalyze is the first agentic LLM for autonomous data science. 🎈你的AI数据分析师，自动分析大量数据，一键生成专业分析报告！
A persistent workspace for development work that self-improves and continues beyond one session.
A bio-inspired cognitive memory engine — a new paradigm for Graph RAG.
The Ruby-native AI framework. Chats, agents, tools, images, audio, and video through one consistent API, in plain Ruby or Rails.
Learn Agentic AI using Dapr Agentic Cloud Ascent (DACA) Design Pattern and Agent-Native Cloud Technologies: OpenAI Agents SDK, Memory, MCP, A2A, Knowledge Graph
Optimizing inference proxy for LLMs
Portable AI agent runtime for the JVM. One @Agent class runs on Spring AI, LangChain4j, Anthropic, or 9 more behind one SPI. Token streaming, tool calls, human
Claude Code, Codex, Copilot, Pi, OpenCode, Gemini, and Prime Agent versions of Poteto's pstack. Rigorous agent workflows with Cursor primitives translated for o
Open-source AI agent for B2B lead generation — describe your product, it finds the people who fit, explains why each one does, and emails them from your mailbox
II-Agent: a new open-source framework to build and deploy intelligent agents
A native macOS app that allows users to chat with a local LLM that can respond with information from files, folders and websites on your Mac without installing
Open-source, self-hosted AI penetration testing framework: maps your attack surface into a graph, autonomously exploits it from a Kali sandbox with human approv
🐧 Harness for RSI. Let AI Build AI. Multi-Agent Auto-Dev Platform. Everything is Transparent.
Open-source, local-first conversational AI video editor with a professional multi-track timeline, Agent Skills, MCP integration, and Remotion rendering.
Real-time stream processing made simple and affordable
Related tags
Frequently asked questions
How many open source agentic-ai projects are there?
This registry tracks 105 projects tagged agentic-ai, with 1,210,489 GitHub stars between them. The most-adopted is Dify at 160,186 stars.
Are these agentic-ai projects free to use?
Yes — 102 of the 105 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 agentic-ai 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 agentic-ai projects still maintained?
98 of the 105 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.