Back to List
Notice:This resource is provided by a third-party author. Please review the code with AI tools or manually before use to ensure security and compatibility.
PythonAMAP-ML/LongHorizon-Harness

LongHorizon-Harness

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-context execution, durable verified state, independent auditing, recoverable progress, and native Claude Code / Codex / OpenClaw integration.

78.0/100
686Forks: 82
View on GitHubHomepage →
Loading report...

Similar Projects

loushang

70

AI-native agent harness for coding workflows by python: multi-model LLM orchestration, stateful sessions, tool governance, traceable delivery, and provider routing for GPT, Claude, DeepSeek, Qwen, Kimi, GLM, and MiniMax.

Python1.1K

serena

92

A powerful MCP toolkit for coding, providing semantic retrieval and editing capabilities - the IDE for your agent

Python28.0K

AutoR

67

AI handles execution, humans own the direction, and every run becomes an inspectable research artifact on disk.

Python805

agent-vision-toolkit

76

为纯文本模型"看图“设计更好的视觉工具箱和技能,支持多图理解,图片问答,前端UI还原、GUI 自动化等,并可选无缝接入多个主流agent,直接识别粘贴图片| A vision toolkit and skill designed for text-only llms — image Q&A, long-screenshot OCR, frontend UI restoration, and GUI automation, with optional seamless integration for Codex, Claude Code, Pi, Oh My Pi, and OpenCode

Python558
Back to List