ouroboros
llms.txt897 starsChanged 4 months agoMITArchived repositoryView on GitHub
Ouroboros is an open-source AI agent with a continuing identity, durable memory, agent swarms, autonomous evolution, and an implementation it can rewrite. Canonical site: https://ouroboros-agent.ai/ Source: https://github.com/razzant/ouroboros License: MIT Ouroboros publishes self-reported benchmark results with status labels and links to available runs, traces, methodology, and submissions. The GAIA result states that its scrubbed trace capsule is pending. Upstream leaderboard acceptance is reported separately when it happens.
1 other project uses a version of this.
Adopted by
Steady: 0 new projects took it in the last 4 weeks, none the 4 weeks before.thin data
Other versions1 project uses a version of this.
Word for word · 1
- joi-lab/ouroboros-desktop★ 209100% same
Edited · 0
None found.
Wrote their own version · 0
None found.
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository11 other files it gives its agents.
- Browser speechSkill
- Device voiceSkill
- gemini_liveSkill
- grok_realtimeSkill
- live_conversationSkill
- openai_realtimeSkill
- telegramSkill
- TemplatesSkill
- ui_designSkill
- unix_computer_useSkill
- windows_computer_useSkill
The file
Files
# Ouroboros > Ouroboros is an open-source AI agent with a continuing identity, durable memory, agent swarms, autonomous evolution, and an implementation it can rewrite. Canonical site: https://ouroboros-agent.ai/ Source: https://github.com/razzant/ouroboros License: MIT Ouroboros publishes self-reported benchmark results with status labels and links to available runs, traces, methodology, and submissions. The GAIA result states that its scrubbed trace capsule is pending. Upstream leaderboard acceptance is reported separately when it happens. ## Start here - [Install](https://ouroboros-agent.ai/install/): Packaged downloads for normal use; clone the source only for development. - [Technical report](https://ouroboros-agent.ai/paper/): Paper metadata, authors, citation, code, and public evidence links. - [About](https://ouroboros-agent.ai/about/): What Ouroboros is and how it works. - [Privacy and account connections](https://ouroboros-agent.ai/privacy/): Connected data, local records, configured providers and disconnection. - [Terms and software license](https://ouroboros-agent.ai/terms/): The MIT license and operating a self-hosted installation. - [Benchmark evidence](https://ouroboros-agent.ai/benchmarks/): Scores, publication status, runs, traces, and methodology. - [Architecture](https://github.com/razzant/ouroboros/blob/ouroboros/docs/ARCHITECTURE.md): Runtime structure, data flow, and operating boundaries. - [Constitution](https://github.com/razzant/ouroboros/blob/ouroboros/BIBLE.md): Identity and governing principles. - [Releases](https://github.com/razzant/ouroboros/releases): Published versions and assets. ## Related software - [Claudexor](https://claudexor.ai/): The local execution layer Ouroboros uses for delegated coding and hosted-agent review. - [Claudexor source](https://github.com/razzant/claudexor): Routing, execution, and durable evidence for connected coding harnesses. ## Machine-readable resources - [Install metadata](https://ouroboros-agent.ai/install.json): Stable release discovery, artifact name templates, and verification metadata. - [GitHub releases API](https://api.github.com/repos/razzant/ouroboros/releases/latest): Current stable release and asset records. - [Sitemap](https://ouroboros-agent.ai/sitemap.xml): Canonical indexable pages.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.