Discover Open Source AI Agent Projects

The most comprehensive directory of open-source AI Agent projects. Discover and compare top Agent frameworks like LangChain, CrewAI, and more.

1334 projects 13 categories 21,774,506 Stars
Explore Projects Read Articles

Categories

View all
πŸ€–

Agent Framework

Core open-source frameworks for building AI agents β€” discover and compare LangChain, CrewAI, AutoGen, LangGraph and more. Filter by tool-calling, memory, multi-step reasoning, stars, and license to pick the right foundation for your project.

πŸ† Top 20 Ranking
πŸ’¬

Chat UI

Open-source chat UI and conversation interface frameworks β€” Open WebUI, LobeChat, LibreChat and more. Compare features like custom models, multi-user support, and plugin extensibility to deploy your own ChatGPT alternative.

πŸ† Top 20 Ranking
⚑

Agent Tools

Development tools and libraries that accelerate AI agent engineering β€” tool-calling helpers, prompt templates, evaluation frameworks, dataset managers, and debugging utilities for building, testing, and iterating agent applications.

πŸ† Top 20 Ranking
🧠

Multi-Agent

Multi-agent collaboration frameworks β€” CrewAI, AutoGen, MetaGPT, OpenAI Swarm and more. Explore how multiple AI agents divide tasks, coordinate roles, schedule work, and orchestrate conversations to solve complex jobs together.

πŸ† Top 20 Ranking
πŸ“š

RAG Tools

Open-source retrieval-augmented generation (RAG) tools β€” vector databases, document chunking, hybrid search, reranking, and RAG evaluation. Compare options for building high-quality private-knowledge Q&A and document retrieval apps.

πŸ† Top 20 Ranking
πŸ”„

Workflow

Agent workflow orchestration tools β€” LangGraph, Dify, n8n, Flowise and more. Define multi-step agent pipelines visually or in code with state machines, DAGs, conditional branching, and human-in-the-loop steps.

πŸ† Top 20 Ranking
πŸ“Š

Observability

Observability, tracing, and evaluation tools for AI agents in production β€” Langfuse, LangSmith, OpenTelemetry integrations and more. Track token usage, call chains, latency, cost, and output quality to keep agents reliable.

πŸ† Top 20 Ranking
πŸ”Œ

MCP Tools

Open-source tools and servers for the Model Context Protocol (MCP) ecosystem. Connect AI agents to databases, browsers, file systems, and APIs through a unified protocol β€” includes official and community-built MCP servers.

πŸ† Top 20 Ranking
🌐

Browser Agent

Browser and web automation agents β€” Browser-use, Playwright MCP, Skyvern and more. Combine LLM vision with DOM control for data extraction, form filling, end-to-end testing, and other browser-driven tasks.

πŸ† Top 20 Ranking
πŸ’»

Coding Agent

AI coding assistants and autonomous coding agents β€” Claude Code, Cline, Aider, OpenHands and more. Compare terminal-native, IDE-plugin, and CLI paradigms for multi-file edits, repo-level refactors, and automated pull requests.

πŸ† Top 20 Ranking
🧩

Agent Memory

Tools and platforms providing long-term memory, knowledge persistence, and context management for AI agents β€” including cross-session memory, knowledge graphs, and personalization

πŸ† Top 20 Ranking
πŸ›‘οΈ

Security & Guardrails

AI safety evaluation, red-teaming, LLM guardrails, vulnerability scanning, and compliance audit tools

πŸ† Top 20 Ranking
πŸ—οΈ

Sandbox & Execution

Secure execution environments, code sandboxes, and runtime isolation tools for AI agents

πŸ† Top 20 Ranking

Featured Projects

View all

Popular Projects

View all

Popular Comparisons

View all β†’
βš”οΈ

LangChain vs CrewAI

Compare LangChain and CrewAI across agent orchestration, multi-agent collaboration, ecosystem maturity, learning curve, and best-fit use cases.

LangChain 142.1k CrewAI 55.8k
βš”οΈ

AutoGen vs CrewAI

Compare Microsoft AutoGen and CrewAI for multi-agent collaboration, conversational workflows, task orchestration, and developer experience.

AutoGen 59.8k CrewAI 55.8k
βš”οΈ

LangChain vs LlamaIndex

Compare LangChain and LlamaIndex across RAG, data connectors, indexing, retrieval, agent capabilities, and application development.

LangChain 142.1k LlamaIndex 51.0k
βš”οΈ

PydanticAI vs Mastra

Compare Pydantic AI and Mastra across type safety, language ecosystem, tool calling, workflows, and production deployment.

PydanticAI 18.7k Mastra 26.3k
βš”οΈ

Dify vs Langflow

Compare Dify and Langflow across visual orchestration, app publishing, RAG, workflows, and team collaboration.

Dify 149.4k Langflow 152.1k
βš”οΈ

n8n vs Langflow

Compare n8n and Langflow for workflow automation, AI node orchestration, integration ecosystem, and visual development.

n8n 197.1k Langflow 152.1k
βš”οΈ

OpenAI Agents SDK vs Agent Development Kit

Compare OpenAI official Agents SDK and Google official Agent Development Kit across protocol, model support, tool calling, and deployment model.

OpenAI Agents SDK 15.0k Agent Development Kit 20.8k
βš”οΈ

Mastra vs LangGraph

Compare Mastra (TypeScript-first) and LangGraph (Python-first) across workflow, tool calling, state management, and observability.

Mastra 26.3k LangGraph 37.6k
βš”οΈ

browser-use vs Skyvern

Compare Browser-Use (DOM route) and Skyvern (vision route) two major browser Agent frameworks across technical route, performance, success rate, and use cases.

browser-use 105.6k Skyvern 22.5k
βš”οΈ

Ragas vs DeepEval

Compare RAGAS (RAG evaluation specialist) and DeepEval (general LLM evaluation) across evaluation metrics, testing methods, and CI/CD integration.

Ragas 14.9k DeepEval 17.0k
βš”οΈ

Mem0 vs Letta

Compare Mem0 (lightweight memory layer) and Letta (full stateful Agent platform) across memory model, retrieval capability, and deployment complexity.

Mem0 61.2k Letta 23.9k
βš”οΈ

Aider vs Continue

Compare Aider and Continue on AI coding assistant positioning, terminal/IDE integration, codebase comprehension, multi-file editing, and enterprise features.

Aider 47.5k Continue 35.0k
βš”οΈ

Open WebUI vs NextChat

Compare Open WebUI and NextChat on self-hosted chat UI capabilities, model support, user management, mobile experience, and deployment complexity.

Open WebUI 146.0k NextChat 88.5k
βš”οΈ

E2B vs CubeSandbox

Compare E2B and CubeSandbox on secure code execution for AI agents, isolation strength, startup latency, runtime duration, and language support.

E2B 13.0k CubeSandbox 10.5k
βš”οΈ

Langfuse vs Arize Phoenix

Compare Langfuse and Arize Phoenix on LLM observability, trace/prompt management, evaluation capabilities, integration options, and open-source licensing.

Langfuse 31.4k Arize Phoenix 10.6k
βš”οΈ

NeMo Guardrails vs Guardrails AI

Compare NeMo Guardrails and Guardrails AI: Colang DSL flow vs Pydantic Validator output across protection layers, structured output, scenarios, and ecosystem.

NeMo Guardrails 6.7k Guardrails AI 7.2k