{"data":{"slug":"skyvern-ai-skyvern","name":"skyvern","tagline":"Automate browser based workflows with AI","github_url":"https://github.com/Skyvern-AI/skyvern","owner":"Skyvern-AI","repo":"skyvern","owner_avatar_url":"https://avatars.githubusercontent.com/u/141457985?v=4","primary_language":"Python","stars":22994,"forks":2160,"topics":["ai","api","automation","browser","browser-automation","computer","gpt","llm","playwright","powerautomate","puppeteer","python","rpa","selenium","vision","workflow"],"archived":false,"github_pushed_at":"2026-09-14T05:32:06+00:00","maintenance_label":"Very active","stars_delta_30d":274,"url":"https://www.graphcanon.com/tools/skyvern-ai-skyvern","markdown_url":"https://www.graphcanon.com/tools/skyvern-ai-skyvern.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/skyvern-ai-skyvern","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=skyvern-ai-skyvern","description":"Automate browser based workflows with AI","homepage_url":"https://www.skyvern.com","license":"AGPL-3.0","open_issues":238,"watchers":103,"ai_summary":"Skyvern-AI/skyvern automates browser-based workflows using Python and integrates various browser automation libraries like Playwright, Puppeteer, Selenium.","readme_excerpt":"### Option A: pip install (Recommended for Python-managed local setup)\n\nDependencies needed:\n- [Python 3.11, 3.12, or 3.13](https://www.python.org/downloads/)\n\nAdditionally, for Windows:\n- [Rust](https://rustup.rs/)\n- VS Code with C++ dev tools and Windows SDK\n\n#### 1. Install Skyvern\n\n```bash\npip install \"skyvern[all]\"\n```\n\n#### 2. Run Skyvern\n\n```bash\nskyvern quickstart\n```\n\nThe pip quickstart uses SQLite by default. To use a local Postgres container instead, run `skyvern quickstart` (Postgres container is started unless you pass `--no-postgres`), or connect to an existing database with `--database-string=postgresql+psycopg://user:pass@host:5432/dbname`.\n\n---\n\n### Option B: Docker Compose\n\nUse this option if you want everything containerized (Postgres, API, UI) and don't want to install Python/Node locally.\n\n1. Install [Docker Desktop](https://www.docker.com/products/docker-desktop/)\n2. Clone the repository:\n   ```bash\n   git clone https://github.com/skyvern-ai/skyvern.git && cd skyvern\n   ```\n3. Configure your LLM provider in `.env` (the `quickstart --docker-compose` command below will create it from `.env.example` if missing):\n   ```bash\n   cp .env.example .env  # if not already created\n   # edit .env to add your LLM API key\n   ```\n4. Start everything:\n   ```bash\n   docker compose up -d\n   ```\n5. Open http://localhost:8080\n\n---\n\n### Quick Start Examples\n\n**Run via UI:**\n```bash\nskyvern run all\n```\nNavigate to http://localhost:8080 to run tasks through the web interface. If the packaged UI is missing, `skyvern run ui` will offer to install the matching UI package.\n\nTo run only the packaged UI against an existing Skyvern API, install `skyvern[ui]` and set the\nenvironment variables below before running `skyvern run ui`:\n\n- `VITE_API_BASE_URL` (e.g. `http://localhost:8000/api/v1`) — points the UI at your Skyvern API\n- `VITE_SKYVERN_API_KEY` — the API key if your API requires one\n- `VITE_WSS_BASE_URL` — WebSocket endpoint (inferred from `VITE_API_BASE_URL` if unset)\n- `VITE_ARTIFACT_API_BASE_URL` — base URL for artifact downloads\n- `VITE_BROWSER_STREAMING_MODE` — browser viewport streaming mode\n\n**Python SDK:**\n```python\nfrom skyvern import Skyvern\n\n---\n\n# License\nSkyvern's open source repository is supported via a managed cloud. All of the core logic powering Skyvern is available in this open source repository licensed under the [AGPL-3.0 License](LICENSE), with the exception of anti-bot measures available in our managed cloud offering.\n\nIf you have any questions or concerns around licensing, please [contact us](mailto:support@skyvern.com) and we would be happy to help.","github_created_at":"2024-02-28T15:45:19+00:00","created_at":"2026-07-15T10:45:42.96619+00:00","updated_at":"2026-09-20T04:26:43.883884+00:00","categories":[{"slug":"ai-agents","name":"AI Agents","url":"https://www.graphcanon.com/categories/ai-agents","markdown_url":"https://www.graphcanon.com/categories/ai-agents.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/ai-agents"},{"slug":"developer-tools","name":"Developer Tools","url":"https://www.graphcanon.com/categories/developer-tools","markdown_url":"https://www.graphcanon.com/categories/developer-tools.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/developer-tools"}],"tags":[{"slug":"ai","name":"ai"},{"slug":"api","name":"api"},{"slug":"automation","name":"automation"},{"slug":"browser-automation","name":"browser-automation"},{"slug":"llm","name":"llm"},{"slug":"powerautomate","name":"powerautomate"},{"slug":"rpa","name":"rpa"},{"slug":"vision","name":"vision"}],"trust":{"provenance":{"is_fork":false,"github_id":764723738,"owner_type":"Organization","methodology":"github_public_v1","parent_repo":null,"near_duplicate_slugs":[]},"computed_at":"2026-09-14T06:00:29.354Z","maintenance":{"label":"Very active","score":96,"methodology":"github_public_v1","releases_90d":12,"days_since_push":0,"last_release_at":"2026-09-09T23:57:28Z","stars_delta_30d":274,"open_issues_delta_30d":18},"security_summary":{"status":"findings","scanner":"mcp_manifest@v1","low_count":2,"high_count":0,"last_scan_at":"2026-07-15T10:45:44.504Z","medium_count":0,"scan_profile":"mcp_manifest","critical_count":0}},"capability_facts":{"scan":{"source":"repo_scan","observed_at":"2026-09-14T06:00:29.988Z"},"deploy":{"source":"dockerfile:Dockerfile","self_host":true,"observed_at":"2026-09-14T06:00:29.988Z","managed_saas":false},"has_cli":{"value":true,"source":"pyproject.toml:[project.scripts]","observed_at":"2026-09-14T06:00:29.988Z"},"languages":{"value":["python"],"source":"github.language+pyproject.toml","observed_at":"2026-09-14T06:00:29.988Z"},"has_docker":{"value":true,"source":"dockerfile:Dockerfile","observed_at":"2026-09-14T06:00:29.988Z"},"license_spdx":{"value":"AGPL-3.0","source":"github.license","observed_at":"2026-09-14T06:00:29.988Z"}},"decision_facts":{"hosting":null,"pricing":null,"requirements":null,"constraints":null,"when_to_use":["When you require an AI-driven approach to automate browser tasks through a user interface or a Python SDK.","For environments where integrating multiple automation libraries like Playwright, Puppeteer, and Selenium is beneficial.","If your setup involves SQLite for local testing or requires Docker containers for full-stack services including Postgres, API, and UI."],"when_not_to_use":["When your project strictly requires proprietary or closed-source software incompatible with AGPL-3.0 licensing conditions.","For deployments where manual configuration of each dependency and integration is not feasible or desirable due to complexity."],"source":"enrich:decision_facts","observed_at":"2026-07-16T19:53:18.880Z"},"constraint_facets":null,"decision_summary":[{"label":"Adopt for","value":"Skyvern automates browser-based workflows with Python, using libraries such as Playwright and Selenium."}]}}