LoopCraft runtime harness plugin for Hermes with evidence-first execution, verification-first workflows, and self-correcting AI agent behavior. Installs as proofrail for compatibility.
Execution harness for OpenClaw agents: evidence-first changes, verification gates, dangerous command controls, and codex-harness / claude-code-harness discoverability.
Reverse-engineered specification of the OpenAI Codex CLI harness — agent loop, tools registry, compaction, and context management — as a navigable knowledge graph (1028 rules / 588 structures / 325 use-cases across 18 SRC modules). For agent instruction authors and harness engineers.
Add a description, image, and links to the codex-harness topic page so that developers can more easily learn about it.
To associate your repository with the codex-harness topic, visit your repo's landing page and select "manage topics."