LongHorizon-Harness

AMAP-ML/LongHorizon-Harness

Long-horizon computer-use harness that runs on top of Claude Code and Codex, splitting work into Manager, Executor, and Auditor roles so only independently verified results enter persistent task state. The clearest August 2026 open-source reference for carrying desktop-and-CLI tasks through dozens of hours without state drift

Python MIT

View on GitHub → Find it in the atlas

Install

uv tool install lh-harness # or: pip install lh-harness

Repository reader

Explore before you clone

Read the project’s README, skills and supporting Markdown here. Rendered view is shown first; source is one click away when you need the exact text.

Fetched from GitHub
Open on GitHub
Loading the project’s README…

Public files are loaded on demand from the repository. The atlas does not copy or modify them.

Screenshot

Screenshot or social card for LongHorizon-Harness
GitHub's social card — no screenshot was found for this project, fetched from source rather than copied into this repository.

Platform support

Derived from the project's own README, install route, CI configuration and release assets — not from running it.
PlatformRuns hereOn what evidence
WindowsLikelyInferred from the language or runtime. Nothing in the project says so.
WSL2YesStated in the project's own README, install route, CI config or release assets.
macOSLikelyInferred from the language or runtime. Nothing in the project says so.
LinuxLikelyInferred from the language or runtime. Nothing in the project says so.
DockerNoNo evidence of support anywhere in the project.

Where it came from

Named by 3 of the 39 lists the atlas merges, independently of each other.

How it is classified

One topic, 4 harnesses. Each link is a prerendered page of everything else in that slice.

Orchestrators & Multi-AgentClaude CodeClaude / AnthropicopencodeCodex / OpenAI

Related in Orchestrators & Multi-Agent

Closest first — projects that plug into the same harnesses, then the ones the most lists agreed on.

  • bernsteinsipyourdrink-ltd/bernsteinDeterministic scheduler for 40+ CLI coding agents running in parallel git worktrees with an HMAC-signed audit chain, signed agent cards, and…
  • hcomaannoo/hcomby aannoo - Lightweight CLI tool for real-time communication between Claude Code sub agents using hooks. Enables multi-agent collaboration with…
  • Agent Teams777genius/agent-teams-aiDesktop app where you give high-level commands to autonomous coding-agent teams across Claude Code, Codex, OpenCode, Cursor, Grok, GitHub Copilot…
  • OrkasOrkas-AI/OrkasLocal-first multi-agent desktop application where a Commander coordinates specialist agents for research, coding, data analysis, documents, and…
  • 5dive5dive-ai/5diveSelf-hosted CLI that runs a team of coding agents on one Linux host: each agent is its own Linux user running claude, codex, opencode, hermes or…
  • clideckrustykuntz/clideckWhatsApp-like dashboard for managing multiple AI coding agents (including Gemini CLI) in one browser window. Live status, session resume, autopilot…
  • Crewlystevehuang0115/crewlyMIT-licensed, local platform that runs a team of role-based agents (developer, QA, PM, orchestrator) on Gemini CLI, Claude Code, and Codex, with…
  • agent-swarmdesplega-ai/agent-swarmSelf-hosted AI company operating system where a lead agent delegates goals to workers in isolated containers, with persistent memory, schedules, and…