{
  "slug": "browser-use",
  "repo": "browser-use/browser-use",
  "name": "browser-use",
  "tagline": "Open-source Python library for AI browser agents, plus Browser Use Cloud: stealth browsers and a hosted agent API.",
  "category": "ai-agents",
  "license_spdx": "MIT",
  "stars": 120176,
  "contributors": 50,
  "last_push_days": 0,
  "latest_release": "main",
  "safety_score": 94.3,
  "verdict": "healthy",
  "risk_reasons": [
    "Active developer activity and positive OpenSSF Scorecard evaluation."
  ],
  "scorecard": 9.4,
  "components": {
    "security_health": 96,
    "maintenance": 94,
    "community": 98,
    "releases": 86
  },
  "language": "Python",
  "self_host_difficulty": "Medium",
  "install_commands": {
    "clone": "git clone https://github.com/browser-use/browser-use.git"
  },
  "website_url": "https://browser-use.com",
  "ai_report": "### Autonomous Evaluation Report: browser-use\n\n**Category:** ai-agents | **Self-Host Difficulty:** Medium | **Safety Score:** 94/100 (HEALTHY)\n\n#### 1. Architecture & Maintenance Cadence\nbrowser-use is an active open-source software project tracked under `browser-use/browser-use`. Maintenance telemetry scores 94/100 and community trust scores 98/100 based on repository activity and contributor adoption. The codebase is distributed under the `MIT` open-source license.\n\n#### 2. Security Health & Supply-Chain Signals\nSecurity health is rated at 96/100 based on licensing compliance, commit hygiene, and issue response indicators. Release cadence discipline is evaluated at 86/100.\n\n#### 3. Key Observations & Operational Risk\n- **Notice:** Autonomous execution surface: inspect prompt injection boundaries and tool privileges before granting shell/network access.\n\n#### 4. Deployment Guidance\nRecommended for production deployment and self-hosting. Run containerized with unprivileged user permissions (non-root UID) and enforce reverse proxy authentication.",
  "ai_report_status": "approved",
  "scanned_at": "2026-11-06T08:59:24.406Z",
  "unlisted": false,
  "archived": false,
  "advisories_count": 0,
  "provenance": "Autonomous Heuristic Audit: Security Health 96 · Maintenance 94",
  "permission_model": {
    "asks_before_destructive": true,
    "approval_prompt_detail": "Requires explicit user confirmation before destructive execution.",
    "execution_environment": "MCP Host Sandbox / Stdio Protocol",
    "filesystem_access": "Scoped Tool Working Directory",
    "network_access": "Outbound HTTPS to configured LLM provider and tool endpoints",
    "verdict": "browser-use implements standard agent safety controls with isolated process execution.",
    "review_status": "approved"
  },
  "use_cases": [
    "Deploy browser-use in secure environments",
    "Integrate with developer and agent workflows"
  ],
  "audience": {
    "perfectFor": [
      "DevSecOps teams",
      "Homelab administrators",
      "Software engineers"
    ],
    "skipIf": [
      "Teams requiring proprietary vendor warranties"
    ]
  },
  "setup_steps": {
    "status": "ok",
    "steps": [
      {
        "title": "Get the files",
        "detail": "Install Browser Use into your project and save the agent script with your API key.",
        "command": "uv add browser-use"
      },
      {
        "title": "Start the agent",
        "detail": "Run the script to launch the agent.",
        "command": "uv run agent.py"
      },
      {
        "title": "Open the browser",
        "detail": "The agent opens a browser, looks up the repository, and prints its answer."
      }
    ],
    "source_url": "https://github.com/browser-use/browser-use#readme",
    "model": "ag/gemini-3.8-flash-high",
    "written_at": "2026-11-06T03:57:26.662Z"
  }
}