Self-Evolving Agent Runtime
Help agents improve their execution strategy from verifiable outcomes while keeping grading rules separate from implementation.
Project overview
It gets smarter on its own. We just hold the line. Skip the prompt engineering. The agent runs, fails, and gets smarter every generation. The grading command and expected result never make it into the success contract we hand it. The Agent OS for replayable AI coding workflows
Four separate runs, four hosts. Different tasks on purpose — the engine is what is shared, not the prompt
Terminal CLI — a task-management CLI: ouroboros init start asking about ordering and scope, then reporting an ambiguity score ChatGPT (Codex) — called as an integration, on a video-publishing harness: the interview, its advisory lanes, and the ambiguity ledger