Sandbox
4 repos for evaluation · Harnesses · CursorClear

YAO = Yielding AI Outcomes. A rigorous engineering, evaluation, governance, and portability system for reusable agent skills.

2.6k
rpamis/cometHarnesses

Comet: agent skill harness for turning ideas into evaluated workflows

3k
Q00/ouroborosHarnesses

Agent OS: the agent gets smarter on its own. We just hold the line: Interview-gated, staged evaluation, budgeted evolution loop. MCP server, 14 runtimes: Claude Code, Codex CLI, Gemini CLI, OpenCode, Copilot, Kiro and more.

5.8k
greyhaven-ai/
autocontext

a recursive self-improving harness designed to help your agents (and future iterations of those agents) succeed on any task

1.3k