- China
-
11:21
(UTC +08:00)
Highlights
- Pro
Popular repositories Loading
-
agent-arena
agent-arena PublicEvidence-first multi-agent debate skill: get a second opinion by pitting Codex × Claude Code (or GLM/DeepSeek/Qwen) to independently review, red-team & judge high-stakes code and architecture decis…
-
-
agent-lessonbook
agent-lessonbook PublicGovernance-layer memory for AI agents — permission-separated control/state/lessons so an agent carries rules and lessons across tasks without rewriting its own authority. A trust boundary, not retr…
Python 1
-
agent-completion-gate
agent-completion-gate PublicMake AI coding agents prove they're done. A fail-closed completion gate: the agent only proposes done; CI reads the real artifacts and grants 'complete'. For Claude Code, Codex & any agent.
Python 1
-
If the problem persists, check the GitHub status page or contact support.
