#agent-harness

N

Give AI agents ambitious work without losing the plot. nac is an open-source harness for long-running tasks, using a central orchestrator, threads, and structured episodes to…

S

The harness layer for Claude Code, a reference implementation of harness engineering with hook-enforced dual review, state-machine gates that survive context compaction, and…

C

The Loop Engine for Claude Code, engineer the loop, not the prompt. 1 router · 9 agents · 16 skills · 4 workflows. Fail-closed gates, test honesty, anti-anchored review.

E

EOC: open-source operating system for OpenAI Codex workflows with agents, skills, hooks, rules, memory, safety gates, and cross-harness adapters.

A

The local-first control plane for long-horizon coding agents: cross-session project memory (ContextDB), adaptive workflow routing, multi-agent teams, resumable overnight runs…

V

Rust CLI with scoped review rules, native Bash and Git hooks, and installation diagnostics for Claude Code and Codex.

M

Make every model cheaper or better. Zero-config behavioral harness for Claude Code, with a reproducible 408-run benchmark

N

A minimal, evidence-gated harness for Codex and Claude Code: reuse what works, add only what is missing, verify before evolving.

M

All-in-one agent harness for OpenAI Codex CLI, Boss meta-orchestrator, 17 curated agents (+17 opt-in AI specialists), 123 curated skills, 3 MCP servers. Install once, curated…

A

Your AI coding harness, ported to every client you use. Capture Claude Code (or Codex) rules, hooks, skills, subagents, commands and MCP servers once; apply them identically to…

O

Build AI workflows you can test like software.

O

Skill letting Agents scan a repo, ask what it cannot infer, then generate a complete open source file collection i.e. README, LICENSE, contributing, security, changelog, CI…

S

Spec Driven, orchestrator-first Agent Skills for spec-driven development. The orchestrator skill turns a PRD or idea into approved SPECs, tracked GitHub Issues…