ouroboros
Ouroboros is an open-source AI agent with persistent identity, agent swarms, autonomous evolution, and reproducible self-reported SOTA results on Terminal-Bench 2.1, OSWorld-Verified, and CL-Bench.
ouroboros at a Glance
- Pricing
- Free
- How you use it
- Desktop app or CLI
- Who it's for
- People working on software projects
ouroboros Key Features
- Coordinates agent swarms
- Maintains persistent identity
- Modifies its implementation
- Verifies task outcomes
- Works on projects
Can't Find What You're Looking For?
We build custom AI agents tailored to your specific business needs. From ideation to deployment, TinyAI.Tools is your partner in AI innovation.
No commitment required. Let's discuss your ideas.
ouroboros Alternatives
DM-Code-Agent
Local-first, auditable Python code agent. Ships its own 30-task hidden-test benchmark plus SWE-bench Verified scored by the official harness -- every number reproducible, negative results included. - hwfengcs/DM-Code-Agent
Agents
Agentsis an open-source library/framework for building autonomous language agents.
EloPhanto
EloPhanto is an open-source autonomous AI agent that works on its own, learns from every task, and builds the tools it's missing. A real self-model – identity, ego, and affect – grounded in published psychology. Run it on your own machine or in the c
Yunjue-Agent
Yunjue Agent: A Fully Reproducible, Zero-Start In-Situ Self-Evolving Agent System for Open-Ended Tasks - YunjueTech/Yunjue-Agent
codehamr
A minimal, local-first coding agent for the terminal. - plaxtoris/codehamr
CUAWright
A simple SWE-style browser+desktop agent framework that achieves SOTA results on long-horizon CUA tasks - microsoft/CUAWright