LongHorizon-Harness — security grade SAFE, quality 70/100

Security audit verdict: SAFE · quality 70/100

No red flags found in any of the 11 categories — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →

by AMAP-ML · Codex Skill · ★ 803

Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h

🔒 Is LongHorizon-Harness safe to install? View the security audit →

About LongHorizon-Harness

LongHorizon-Harness Advancing Long-Horizon Agents for Real-World Tasks Operate the whole computer like a human. Work across desktop apps and the command line for dozens of hours. No state drift. Verifiable progress. Complex tasks carried through to completion. [![Be

agentclaudeclaude-codeclaude-pluginclicodexcodex-desktopcodex-plugincuadeepseek-harness

Quick Facts

Stars803
Forks92
LanguagePython
CategoryCodex Skill
LicenseMIT
Quality Score69.6290790487111/100
Open Issues20
Last Updated2026-08-17
Created2026-08-04
Platformsclaude-code, cli, codex, python
Est. Tokens~17k

Compatible Skills

These tools work well together with LongHorizon-Harness for enhanced workflows:

  • agentic-grpo-longhorizon — semantic(0.36)+complementary+rare_topics+same_lang+similar_pop+shared_platform (67%)
  • Toolathlon — semantic(0.40)+complementary+same_lang+similar_pop+shared_platform (64%)

LongHorizon-Harness alternative? Top 6 similar tools

Looking for a LongHorizon-Harness alternative? If you're comparing LongHorizon-Harness with other codex skill tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.

  • codeg by xintaofei · ⭐ 2.8k

    Collaborative multi-agent AI coding workspace: aggregate sessions from Claude Code, Codex, OpenCode, Pi, Grok

  • skillshare by runkids · ⭐ 2.6k

    📚 Sync skills across all AI CLI tools with one command and simplify team sharing. Supporting Codex, Claude Co

  • memsearch by zilliztech · ⭐ 2.5k

    A persistent, unified memory layer for all your AI agents (e.g. Claude Code, Codex), backed by Markdown and Mi

  • zeroshot by the-open-engine · ⭐ 1.7k

    Independent executor–verifier orchestration for software changes.

  • penguin-harness by Prism-Shadow · ⭐ 1.5k

    🐧 Harness for RSI. Let AI Build AI

  • ospec by clawplays · ⭐ 488

    Spec-driven, agentic workflow framework for AI coding agents. Turn a request into a verifiable goal loop — pla

More Codex Skill Tools

Explore other popular codex skill tools:

View all Codex Skill tools →

Popular Python Agent Tools

Frequently Asked Questions

What is LongHorizon-Harness?

LongHorizon-Harness is The long-horizon computer-use harness. Run AI agents across desktop apps and the CLI for extended periods while preserving task state and making reliable progress on complex workflows. Features fresh-. It is categorized as a Codex Skill with 803 GitHub stars.

What programming language is LongHorizon-Harness written in?

LongHorizon-Harness is primarily written in Python. It covers topics such as agent, claude, claude-code.

How do I install or use LongHorizon-Harness?

You can find installation instructions and usage details in the LongHorizon-Harness GitHub repository at github.com/AMAP-ML/LongHorizon-Harness. The project has 803 stars and 92 forks, indicating an active community.

What license does LongHorizon-Harness use?

LongHorizon-Harness is released under the MIT license, making it free to use and modify according to the license terms.

What are the best alternatives to LongHorizon-Harness?

The top alternatives to LongHorizon-Harness on Agent Skills Hub include codeg, skillshare, memsearch. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.

View on GitHub → Browse Codex Skill tools