Corpus Agentis
The field book to agent ecosystems
The field book to agent ecosystems
Catalogue · OSS

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
swarm agent topology diagramswarm
hermes-agent
OSS Python
swarm agent topology diagramswarm
AutoGPT
OSS Python
swarm agent topology diagramswarm
langchain
OSS Python
swarm agent topology diagramswarm
firecrawl
OSS TypeScript
swarm agent topology diagramswarm
gemini-cli
OSS TypeScript
swarm agent topology diagramswarm
browser-use
OSS Python
archive agent topology diagramarchive
ragflow
OSS Python
swarm agent topology diagramswarm
claude-mem
OSS JavaScript
swarm agent topology diagramswarm
Prompt-Engineering-Guide
OSS MDX
swarm agent topology diagramswarm
Front-End-Checklist
OSS MDX
swarm agent topology diagramswarm
daytona
OSS TypeScript
swarm agent topology diagramswarm
deer-flow
OSS Python
swarm agent topology diagramswarm
ai-agents-for-beginners
OSS Jupyter Notebook
swarm agent topology diagramswarm
open-design
OSS TypeScript
swarm agent topology diagramswarm
awesome-claude-skills
OSS Python
swarm agent topology diagramswarm
oh-my-openagent
OSS TypeScript
swarm agent topology diagramswarm
anything-llm
OSS JavaScript
swarm agent topology diagramswarm
ruflo
OSS TypeScript
swarm agent topology diagramswarm
mem0
OSS Python
swarm agent topology diagramswarm
claude-code-best-practice
OSS HTML
swarm agent topology diagramswarm
crewAI
OSS Python
swarm agent topology diagramswarm
goose
OSS Rust
swarm agent topology diagramswarm
CowAgent
OSS Python
swarm agent topology diagramswarm
nanobot
OSS Python
swarm agent topology diagramswarm
antigravity-awesome-skills
OSS Python
swarm agent topology diagramswarm
awesome-ai-agents
OSS agent
swarm agent topology diagramswarm
agenticSeek
OSS Python
swarm agent topology diagramswarm
planning-with-files
OSS Python
swarm agent topology diagramswarm
GenAI_Agents
OSS Jupyter Notebook
swarm agent topology diagramswarm
pentagi
OSS Go
archive agent topology diagramarchive
SuperAGI
OSS Python
swarm agent topology diagramswarm
edict
OSS Python
archive agent topology diagramarchive
AutoResearchClaw
OSS Python
swarm agent topology diagramswarm
PocketFlow-Tutorial-Codebase-Knowledge
OSS Python
swarm agent topology diagramswarm
hive
OSS Python
swarm agent topology diagramswarm
Upsonic
OSS Python
swarm agent topology diagramswarm
ShortGPT
OSS Python
swarm agent topology diagramswarm
Bindu
OSS Python
swarm agent topology diagramswarm
harness-sdk
OSS Python
swarm agent topology diagramswarm
agents
OSS Python
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.

Show more

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.

From the corpus, curated by Brandon Chaplin
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). 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