技能目录

为 AI Agent 发现可复用技能。

按任务搜索真实的 GitHub 技能,并在使用前查看 Stars、信任、审计、分类和安装路径。

每个推荐都保留与其仓库、审计和安装路径的明确关联。

搜索结果: harness

英文目录

Harness Open Source is an end-to-end developer platform with Source Control Management, CI/CD Pipelines, Hosted Developer Environments, and Artifact Registries.

37K
Stars
85/100
信任
分类: devops审计

An open-source long-horizon SuperAgent harness that researches, codes, and creates. With the help of sandboxes, memories, tools, skill, subagents and message gateway, it handles different levels of tasks that could take minutes to hours.

71K
Stars
87/100
信任
分类: agent-frameworks审计

Bash is all you need - A nano claude code–like 「agent harness」, built from 0 to 1

68K
Stars
84/100
信任
分类: agent-frameworks审计

omo/lazycodex: The coding agent for tokenmaxxers;the one and only agent harness for complex codebases. For your Codex, for your OpenCode

63K
Stars
79/100
信任
分类: agent-frameworks审计

The first open-source harness builder for AI coding. Make AI coding deterministic and repeatable.

22K
Stars
84/100
信任
分类: coding-agents审计

Build reliable customer-facing AI agents with Parlant: an interaction control harness optimized for controlled, consistent, and predictable LLM interactions.

18K
Stars
87/100
信任
分类: agent-frameworks审计

Browser Harness | Self-healing harness that enables LLMs to complete any task.

16K
Stars
80/100
信任
分类: agent-frameworks审计

Omnigent is an open-source AI agent framework and meta-harness: orchestrate Claude Code, Codex, Cursor, Pi, and custom agents — swap harnesses without rewriting, enforce policies and sandboxing, and collaborate in real time from any device.

8.8K
Stars
82/100
信任
分类: coding-agents审计

Multi-Agent Harness for Production AI

11K
Stars
82/100
信任
分类: agent-skills审计

An agent skill that enforces ASD-STE100 Simplified Technical English in LLM-generated documentation, reducing AI slop and improving clarity.

1.8K
Stars
86/100
信任
分类: utility审计

Comet: agent skill harness phase-guarded automation from idea to archive

2.8K
Stars
81/100
信任
分类: agent-skills审计