Open source agents projects
Every project in the registry tagged agents, ranked by real GitHub adoption.
Visual builder for AI agents and RAG pipelines
The agent engineering platform.
Open-source AI penetration testing tool to find and fix your app’s vulnerabilities.
Persistent memory layer for AI agents and apps
Framework for orchestrating role-playing, autonomous AI agents. By fostering collaborative intelligence, CrewAI empowers agents to work together seamlessly, tac
LlamaIndex is the document processing platform for AI
LEAKED SYSTEM PROMPTS FOR CHATGPT, CLAUDE, GEMINI, GROK, PERPLEXITY, CURSOR, LOVABLE, REPLIT, AND MORE! - AI SYSTEMS TRANSPARENCY FOR ALL! 👐
Self-hosted AI runtime for text, voice, vision, and agents
Build resilient agents.
Model-agnostic platform for building intelligent AI agents
📑 PageIndex: Document Index for Vectorless, Reasoning-based RAG
Build AI copilots for your product in hours, not months
Effortless deployment and management for any VPS
Composio powers 1000+ toolkits, tool search, context management, authentication, and a sandboxed workbench to help you build AI agents that turn intent into act
Secure secret management for modern development teams
Sim is the collaborative workspace to build, deploy, and monitor AI agents and workflows. Used by 100,000+ builders.
Open-source vector database for AI search and retrieval
Open-source AI orchestration framework for building context-engineered, production-ready LLM applications. Design modular pipelines and agent workflows with exp
The SDK to extract data and interact with any site on the web. Get started with Claude Code, Codex, Eve, Mastra, and more.
Run coding agents from your phone, desktop, or terminal
24/7 screen and audio recorder with AI memory search
Unify data models and metrics across your entire stack
open-source agentic AI data assistant for the next generation of AI + Data products.
No-code web scraping, crawling, and extraction platform
Open-source AI coworker, with memory
Fast, secure cloud development environments on your infrastructure
MCP Toolbox for Databases is an open source MCP server for databases.
Privacy-first knowledge base with any AI model you choose
Automation engine to build, test and ship any codebase. Runs locally, in CI, or directly in the cloud
A framework for building, orchestrating and deploying AI agents and multi-agent workflows with support for Python and .NET.
💡 All-in-one AI framework for semantic search, LLM orchestration and language model workflows
Open-source LLM tracing & evaluation for AI optimization
Pocket Flow: 100-line LLM framework. Let Agents build Agents!
Common layer for composing and governing AI agents
AI Agent Engineering Platform built on an Open Source TypeScript AI Agent Framework
Annotate and review coding agent plans and code diffs visually, share with your team, send feedback to agents with one click.
Review-first terminal diff viewer for agentic coders
Lightweight (7MB) Terminal-first AI-native dev workspace
A local multi-agent harness that works with your existing Claude Code, Codex subscriptions, allows you to run an office of agents
Open-source framework for building agentic apps in JavaScript, Go, Dart, and Python, built and used in production by Google
Next Generation Agentic Proxy for AI Agents and MCP servers
A visual playground for agentic workflows: Iterate over your agents 10x faster
Context Graph for AI Native SDLC
⚡️ Open-source AI Gateway — Use any SDK to call 100+ LLMs. Built-in failover, load balancing, cost control & end-to-end tracing.
Eko (Eko Keeps Operating) - Build Production-ready Agentic Workflow with Natural Language - eko.fellou.ai
Build reliable AI agents with unified tool integration
The first AI agent that builds permissionless integrations through reverse engineering platforms' internal APIs.
An AI Gateway, registry, and proxy that sits in front of any MCP, A2A, or REST/gRPC APIs, exposing a unified endpoint with centralized discovery, guardrails and
A persistent workspace for development work that self-improves and continues beyond one session.
Observal is self-hosted registry for your coding agent extensions with a built in insight engine. Setup Observal, define the scope and share your Skills, MCPs
ADHD — a skill for coding agents. Tree-of-thought with pruning, built on the Claude & Codex Agent SDK. Fans out parallel divergent thoughts under different cogn
The Ruby-native AI framework. Chats, agents, tools, images, audio, and video through one consistent API, in plain Ruby or Rails.
Your agent in your terminal, equipped with local tools: writes code, uses the terminal, browses the web. Make your own persistent autonomous agent on top!
Optimizing inference proxy for LLMs
A system for agentic LLM-powered data processing and ETL
Harness LLMs with Multi-Agent Programming
Open source security automation platform for builders
Atomic Agent is a local-first AI agent. Runs open-weight models on your own machine via llama.cpp.
AI-powered platform for engineering LLM products
Related tags
Frequently asked questions
How many open source agents projects are there?
This registry tracks 92 projects tagged agents, with 1,522,109 GitHub stars between them. The most-adopted is Langflow at 156,266 stars.
Are these agents projects free to use?
Yes — 83 of the 92 carry an explicit open-source licence across 3 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 agents 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 agents projects still maintained?
83 of the 92 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.