---
title: "Open-source AI agents · public, self-hostable agent projects · Agent Fieldbook"
url: https://agentfieldbook.org/catalog/oss/
description: "Open-source agents and frameworks: public code you can read, run and modify, trading a vendor's convenience for transparency, portability and control. Reference specimens drawn from tracked projects with live repository signal, each tracing to its public source."
section: "Catalogue · OSS"
source: Agent Fieldbook — generated from the published page
---

# Open-source agents

Open-source agents and frameworks: public code you can read, run and modify, trading a vendor's convenience for transparency, portability and control. Much of the modern agent stack started here. These specimens are shown as reference cards, since their full entity pages are not built yet; each still traces to its public repository.

## 40 agents Live data · click a specimen for its anatomy

## Field notes

Public code you can read, run and change, on your terms

Forty open-source agents sit alongside the commercial catalogue, and they occupy different ground. Open projects lead on harnesses, frameworks and experimental topologies; commercial products lead on managed operation and vertical depth.

The traffic between the two runs mostly one way: patterns are proven in the open, then absorbed into managed platforms once they stabilise. Watching what the open projects are building is a reasonable forward indicator of what the commercial tier ships next.

- [Brandon Chaplin](https://www.linkedin.com/in/brandon-chaplin-digital-marketing-strategist)

## Common questions

### What is an open-source AI agent?

An agent or agent framework whose code is public under a licence that lets you read, run and change it. You can host it on your own infrastructure and modify how it behaves, rather than consuming it as somebody else’s hosted product.

### Are open-source AI agents free?

The code is; running it is not. You still pay for model calls to whichever provider you point it at, plus hosting and the engineering time to keep it working. For a small team that can easily cost more than a commercial seat.

### Should I use an open-source agent or a commercial one?

Open source when you need to see inside the system, keep data on your own infrastructure or change the behaviour. Commercial when you want the operating work handled: hosting, upgrades, support and access control. Prototyping on open source and buying for production is a common route.

### Can I self-host an AI agent?

Yes. Most open-source frameworks run on your own servers and can call either a hosted model API or a local open-weights model. Only the fully local setup keeps data entirely in-house, and it needs serious hardware to be usable.

### What counts as open source?

A licence that permits use, modification and redistribution, as set out in the Open Source Definition [(OSI)](https://opensource.org/osd). Several well-known agent projects and open-weights models ship under more restrictive terms, so read the licence before assuming commercial use is allowed.

## Next in the learning path

- [The full catalogue The commercial agents with full spec sheets](https://agentfieldbook.org/catalog/all/)

- [Harnesses & SDKs The build layer many OSS agents live in](https://agentfieldbook.org/software/frameworks/)

- [Agent topologies The shapes these frameworks coordinate through](https://agentfieldbook.org/design/topologies/)

- [Communities Where agents gather, multi-agent worlds and collectives](https://agentfieldbook.org/catalog/communities/)

## Entries

_40 entries listed on this page._

| name | description | subjectOf |
| --- | --- | --- |
| hermes-agent | The agent that grows with you | https://github.com/NousResearch/hermes-agent |
| 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 w | https://github.com/Significant-Gravitas/AutoGPT |
| langchain | The agent engineering platform. | https://github.com/langchain-ai/langchain |
| firecrawl | The API to search, scrape, and interact with the web at scale. 🔥 | https://github.com/firecrawl/firecrawl |
| gemini-cli | An open-source AI agent that brings the power of Gemini directly into your terminal. | https://github.com/google-gemini/gemini-cli |
| browser-use | 🌐 Make websites accessible for AI agents. Automate tasks online with ease. | https://github.com/browser-use/browser-use |
| ragflow | RAGFlow is a leading open-source Retrieval-Augmented Generation (RAG) engine that fuses cutting-edge RAG with Agent capabilities to create a | https://github.com/infiniflow/ragflow |
| claude-mem | Persistent Context Across Sessions for Every Agent – Captures everything your agent does during sessions, compresses it with AI, and inject | https://github.com/thedotmack/claude-mem |
| Prompt-Engineering-Guide | 🐙 Guides, papers, lessons, notebooks and resources for prompt engineering, context engineering, RAG, and AI Agents. | https://github.com/dair-ai/Prompt-Engineering-Guide |
| Front-End-Checklist | 🗂 The essential checklist for modern web development, for humans and AI agents | https://github.com/thedaviddias/Front-End-Checklist |
| daytona | Daytona is a Secure and Elastic Infrastructure for Running AI-Generated Code | https://github.com/daytonaio/daytona |
| deer-flow | An open-source long-horizon SuperAgent harness that researches, codes, and creates. With the help of sandboxes, memories, tools, skill, suba | https://github.com/bytedance/deer-flow |
| ai-agents-for-beginners | 12 Lessons to Get Started Building AI Agents | https://github.com/microsoft/ai-agents-for-beginners |
| open-design | 🎨 Local-first, open-source Claude Design alternative. 🖥️ Native desktop app. ⚡ 259+ Skills · ✨ 142+ Design Systems 🖼️ Web · desktop · mob | https://github.com/nexu-io/open-design |
| awesome-claude-skills | A curated list of awesome Claude Skills, resources, and tools for customizing Claude AI workflows | https://github.com/ComposioHQ/awesome-claude-skills |
| oh-my-openagent | omo/lazycodex: The coding agent for tokenmaxxers;the one and only agent harness for complex codebases. For your Codex, for your OpenCode | https://github.com/code-yeongyu/oh-my-openagent |
| anything-llm | Stop renting your intelligence. Own it with AnythingLLM. Everything you need for a powerful local-first agent experience | https://github.com/Mintplex-Labs/anything-llm |
| ruflo | 🌊 The leading agent meta-harness for Claude. Deploy intelligent multi-agent swarms, coordinate autonomous workflows, and build conversation | https://github.com/ruvnet/ruflo |
| mem0 | Universal memory layer for AI Agents | https://github.com/mem0ai/mem0 |
| claude-code-best-practice | from vibe coding to agentic engineering - practice makes claude perfect | https://github.com/shanraisshan/claude-code-best-practice |
| crewAI | Framework for orchestrating role-playing, autonomous AI agents. By fostering collaborative intelligence, CrewAI empowers agents to work toge | https://github.com/crewAIInc/crewAI |
| goose | an open source, extensible AI agent that goes beyond code suggestions - install, execute, edit, and test with any LLM | https://github.com/aaif-goose/goose |
| CowAgent | Open-source super AI assistant & Agent Harness. Plans tasks, runs tools and skills, self-evolves with memory and knowledge. Multi-model, mul | https://github.com/zhayujie/CowAgent |
| nanobot | Lightweight, open-source AI agent for your tools, chats, and workflows. | https://github.com/HKUDS/nanobot |
| antigravity-awesome-skills | Installable GitHub library of 1,500+ agentic skills for Claude Code, Cursor, Codex CLI, Gemini CLI, Antigravity, and more. Includes speciali | https://github.com/sickn33/antigravity-awesome-skills |
| awesome-ai-agents | A list of AI autonomous agents | https://github.com/e2b-dev/awesome-ai-agents |
| agenticSeek | Fully Local Manus AI. No APIs, No $200 monthly bills. Enjoy an autonomous agent that thinks, browses the web, and code for the sole cost of | https://github.com/Fosowl/agenticSeek |
| planning-with-files | Persistent file-based planning for AI coding agents and long-running agentic tasks. Crash-proof markdown plans that survive context loss and | https://github.com/OthmanAdi/planning-with-files |
| GenAI_Agents | 50+ tutorials and implementations for Generative AI Agent techniques, from basic conversational bots to complex multi-agent systems. | https://github.com/NirDiamant/GenAI_Agents |
| pentagi | Fully autonomous AI Agents system capable of performing complex penetration testing tasks | https://github.com/vxcontrol/pentagi |
| SuperAGI | <⚡️> SuperAGI - A dev-first open source autonomous AI agent framework. Enabling developers to build, manage & run useful autonomous agents q | https://github.com/TransformerOptimus/SuperAGI |
| edict | 🏛️ 三省六部制 · OpenClaw Multi-Agent Orchestration System: 9 specialized AI agents with real-time dashboard, model config, and full audit trail | https://github.com/cft0808/edict |
| AutoResearchClaw | Fully autonomous & self-evolving research from idea to paper. Chat an Idea. Get a Paper. 🦞 | https://github.com/aiming-lab/AutoResearchClaw |
| PocketFlow-Tutorial-Codebase-Knowledge | Pocket Flow: Codebase to Tutorial | https://github.com/The-Pocket/PocketFlow-Tutorial-Codebase-Knowledge |
| hive | Multi-Agent Harness for Production AI | https://github.com/aden-hive/hive |
| Upsonic | Build autonomous AI agents in Python. | https://github.com/Upsonic/Upsonic |
| ShortGPT | 🚀🎬 ShortGPT - Experimental AI framework for youtube shorts / tiktok channel automation | https://github.com/RayVentura/ShortGPT |
| Bindu | Bindu: The identity, communication, and payments layer for AI agents. | https://github.com/GetBindu/Bindu |
| harness-sdk | Build an agent harness and control it end-to-end. Open-source SDK for production AI agents in Python & TypeScript - any model, any cloud. | https://github.com/strands-agents/harness-sdk |
| agents | An Open-source Framework for Data-centric, Self-evolving Autonomous Language Agents | https://github.com/aiwaves-cn/agents |