#129 · Primary category: AI Coding Assistants
ouroboros
Agent OS: Stop prompting. Start specifying.
Project last updated:08/29/26
GitHub Stars
5.7K
Forks
577
Contributors
80
License
MIT
Why we included this project
Rather than trusting a coding agent to guess from a throwaway prompt, Ouroboros turns the workflow into a specification-first process: you talk through a vague idea, the tool crystallizes it into a fixed spec, and then runs the work until the results pass verification. It sits as a local runtime layer on top of existing CLI agents like Claude Code, Codex, Gemini, and GitHub Copilot, recording every step as a replayable event so the same spec gives consistent outcomes. Teams that repeat similar tasks, deal with nondeterministic agent behavior, or need policy boundaries and audit trails around automated coding will find this useful. A companion terminal UI lets you drive multiple coding agents from one session, which helps when you juggle several CLIs on a single project.
Articles for this project
No articles for this project yet.
To suggest a topic or contribute an article, contact us.
Related projects in this category
superpowers
An agentic skills framework & software development methodology that works.
ECC
The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
skills
Skills for Real Engineers. Straight from my .agents directory.
opencode
The open source coding agent.
andrej-karpathy-skills
A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.