AI Agent Skills

Evaluation harness for Apodex-1.0 on public deep-research benchmarks.

Official AHE code — Agentic Harness Engineering: observability-driven automatic evolution of coding-agent harnesses (concurrent w/ meta-harness). NexAU-AHE reaches 84.7%…

Comet: agent skill harness phase-guarded automation from idea to archive

🔬 Harness Vibe Research with Self-evolving AI Scientists

Turn approved specs into long-running autonomous implementation. A minimal, adaptable SDD harness with Agent Skills for Claude Code, Codex, Cursor, Copilot, Windsurf, Op…

The ultimate setup harness for OpenClaw. Deploy in minutes. Stay running for months. No CLI required.

Python wrapper for AutoHotkey with full type support. Harness the automation power of AutoHotkey with the beauty of Python.

Autonomously improve a real artifact (code, training recipe, agent harness, data pipeline, prompt) against an objective and an evaluator, using Hypothesis Tree Refinemen…

33 battle-tested skills + minimal .claude harness for any coding agent (Claude Code, Cursor, Codex, Gemini CLI).

Bundled multi-agent orchestration harness for OpenCode. One install, complete control.

Yet another coding agent harness, lightweight and written in go.

Harness framework to build world model based workflows for physical AI systems.