Best Open Source AI Agent Frameworks
Ranked by GitHub stars and 295 days of tracked growth. The top open source AI agent frameworks below are updated daily — pick two to see a full side-by-side comparison.
1
ECC
The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
2
hermes-agent
The agent that grows with you
3
deepseek-harness
DeepSeek Harness: Everything is a Plugin.
4
AutoGPT
AutoGPT is the vision of accessible AI for everyone, to use and to build on. Our mission is to provide the tools, so that you can focus on what matters.
5
firecrawl
The context API to search, scrape, and interact with the web at scale. 🔥
6
JavaGuide
Java 面试 & 后端通用面试指南，覆盖计算机基础、数据库、分布式、高并发、系统设计与 AI 应用开发
7
dify
Build Agentic workflows, RAG pipelines, with rich AI model and tool support on one collaborative workspace. Deploy on cloud, VPC, or self-hosted, so teams move from prototype to production without rebuilding the stack.
8
langchain
The agent engineering platform.
9
ponytail
Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.
10
graphify
Turn any codebase, with its docs, SQL schemas, configs, and PDFs, into a queryable knowledge graph. A /graphify skill for Claude Code, Cursor, Codex, and Gemini CLI: local deterministic AST parsing, every edge explained, no vector store.
11
browser-use
🌐 Make websites accessible for AI agents. Automate tasks online with ease.
12
gemini-cli
An open-source AI agent that brings the power of Gemini directly into your terminal.
⚖️ Compare AI agent frameworks head-to-head
Real adoption data, side by side.