PRODUCTIVITY/效率应用
Picrew/awesome-agent-harness
An awesome list of Agent Harness engineering resources, including GitHub projects, tools, benchmarks, and practical guides.
02 / 现在的位置02 / Why now
首次发现FIRST SEEN
03 OCT 202603 OCT 2026
增长GROWTH
+0.4%+0.4%
1.8k → 1.8k stars · 3 个快照1.8k → 1.8k stars · 3 snapshots
状态STATUS
持续活跃Active
03 / 它能帮你做什么03 / What it helps you do
04 / 安装04 / Install
文档里没有找到可识别的安装命令。这类项目按发布规则不会进入榜单,只能在这里查看。No recognisable install command was found in the docs. Projects like this never enter the ranked list under our publishing rules — they are viewable here only.
05 / 限制与风险05 / Limits and risk
风险不是警告,是可信度的一部分。以下结论只基于文档静态扫描,我们不会执行项目里的任何代码。Risk here is evidence, not an alarm. These findings come from static scanning of the docs; we never execute a project’s code.
限制LIMITS
需检查Needs review
静态扫描STATIC SCAN
01控制浏览器Controls a browserreadme
| Browser Harness | [GitHub](https://github.com/browser-use/browser-harness) | [![star](https://img.shields.io/badge/star-17840-f4b400?style
这里只做静态扫描:读 README、SKILL.md 和依赖清单,不执行代码。没有命中不代表安全。This is static scanning only: we read the README, SKILL.md and dependency list, and never execute code. No findings does not mean safe.
{
"agents": [
{
"agent": "claude-code",
"evidence": "readme: …, and enterprise adoption. - [Claude Code auto mode](https://www.anthro…"
},
{
"agent": "claude-ai",
"evidence": "readme: …containment architecture for claude.ai, Claude Code, and Cowork, spa…"
},
{
"agent": "codex",
"evidence": "readme: …submission quality gates. | | OpenAI Codex Plugin for Claude Code | [Git…"
},
{
"agent": "cline",
"evidence": "readme: …ike systems from scratch. | | Cline | [GitHub](https://github.com…"
},
{
"agent": "gemini-cli",
"evidence": "readme: …nCode, Cursor CLI, Codex, and Gemini CLI with project, terminal, file,…"
},
{
"agent": "vscode",
"evidence": "readme: …-source coding agent spanning VS Code, JetBrains, CLI, cloud agents…"
},
{
"agent": "opencode",
"evidence": "readme: …| Multi-harness agent OS for OpenCode, Codex, Claude Code, and othe…"
},
{
"agent": "copilot",
"evidence": "readme: …apps, and durable state. | | GitHub Copilot CLI | [GitHub](https://github…"
}
],
"apiKey": null,
"docker": null,
"taxonomy": {
"scores": {
"design": 0,
"ai-tools": 2,
"dev-tools": 0,
"indie-web": 0,
"skill-agent": 0,
"productivity": 3
},
"primary": "productivity",
"secondary": null
},
"localRuntime": "inal-native coding agent that runs locally and exposes practical agent workflows f",
"skillMdTotal": 0,
"skillMdErrors": [],
"treeTruncated": false,
"categoryScores": {
"data": 0,
"agent": 3,
"media": 0,
"design": 1,
"browser": 0,
"devtool": 0,
"security": 0,
"marketing": 0,
"productivity": 0
},
"classification": [
{
"signal": "description mentions AI",
"weight": 0.2
}
],
"scannedSources": [
"readme"
],
"skillMdFetched": 0
}