#agent-harness

OS

Model-independent agent harness with persistent memory, MCP orchestration, skills, tools and local-first governance.

Agentit

Open-source, provider-neutral reliability layer for AI coding agents: independent review, JIT skills, resumable state, and verifiable execut...

Nac

Give AI agents ambitious work without losing the plot. nac is an open-source harness for long-running tasks, using a central orchestrator, t...

Codex Host

Run Pi and Claude Code directly in Codex Desktop. 在 Codex Desktop 中直接运行 Pi 和 Claude Code。

Build Your Own Agent

Loadable skill and scaffold for building source-grounded agent harnesses

Garcon: Browser Workspace for Coding Agents

Self-hosted browser workspace to run coding agents in parallel, steer work as it runs, review diffs, and ship.

sd0x-dev-flow: Claude Code Harness Engineering

The harness layer for Claude Code — a reference implementation of harness engineering with hook-enforced dual review, state-machine gates th...

Oh My Agent: Vendor-Agnostic Multi-Agent Harness

Portable, vendor-agnostic agent harness for project-specific skills, workflows, and agent teams aligned with your codebase, conventions, and...

BossConsole: Open-Source AI Agent Operator

Open-source, multi-platform harness for AI agents — a native, multi-threaded operator's console (JVM, not Electron) to run Claude Code, Code...

Grok Build Arsenal

Production-grade skills, custom MCP servers, and real projects built with Grok Build 0.1 (grok-build-0.1). The definitive toolkit + living s...

AI-native agent harness for coding workflows by python: multi-model LLM orchestration, stateful sessions, tool governance, traceable deliv...

LACP: Policy Controls for CLI Coding Agents

Local-first policy, evidence, memory, and recovery controls for Claude, Codex, Hermes, and other CLI coding agents.