# Send Browserbase Persist with captcha to your agent Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually. ## Fast path - Download the package from Yavira. - Extract it into a folder your agent can access. - Paste one of the prompts below and point your agent at the extracted folder. ## Suggested prompts ### New install ```text I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Then review README.md for any prerequisites, environment setup, or post-install checks. Tell me what you changed and call out any manual steps you could not complete. ``` ### Upgrade existing ```text I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Then review README.md for any prerequisites, environment setup, or post-install checks. Summarize what changed and any follow-up checks I should run. ``` ## Machine-readable fields ```json { "schemaVersion": "1.0", "item": { "slug": "browserbase", "name": "Browserbase Persist with captcha", "source": "tencent", "type": "skill", "category": "通讯协作", "sourceUrl": "https://clawhub.ai/JamesFincher/browserbase", "canonicalUrl": "https://clawhub.ai/JamesFincher/browserbase", "targetPlatform": "OpenClaw" }, "install": { "downloadUrl": "/downloads/browserbase", "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=browserbase", "sourcePlatform": "tencent", "targetPlatform": "OpenClaw", "packageFormat": "ZIP package", "primaryDoc": "SKILL.md", "includedAssets": [ "references/api-quick-ref.md", "README.md", "scripts/browserbase_manager.py", "scripts/requirements.txt", "SKILL.md" ], "downloadMode": "redirect", "sourceHealth": { "source": "tencent", "slug": "browserbase", "status": "healthy", "reason": "direct_download_ok", "recommendedAction": "download", "checkedAt": "2026-04-29T07:25:37.850Z", "expiresAt": "2026-05-06T07:25:37.850Z", "httpStatus": 200, "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=browserbase", "contentType": "application/zip", "probeMethod": "head", "details": { "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=browserbase", "contentDisposition": "attachment; filename=\"browserbase-1.0.0.zip\"", "redirectLocation": null, "bodySnippet": null, "slug": "browserbase" }, "scope": "item", "summary": "Item download looks usable.", "detail": "Yavira can redirect you to the upstream package for this item.", "primaryActionLabel": "Download for OpenClaw", "primaryActionHref": "/downloads/browserbase" }, "validation": { "installChecklist": [ "Use the Yavira download entry.", "Review SKILL.md after the package is downloaded.", "Confirm the extracted package contains the expected setup assets." ], "postInstallChecks": [ "Confirm the extracted package includes the expected docs or setup files.", "Validate the skill or prompts are available in your target agent workspace.", "Capture any manual follow-up steps the agent could not complete." ] } }, "links": { "detailUrl": "https://openagent3.xyz/skills/browserbase", "downloadUrl": "https://openagent3.xyz/downloads/browserbase", "agentUrl": "https://openagent3.xyz/skills/browserbase/agent", "manifestUrl": "https://openagent3.xyz/skills/browserbase/agent.json", "briefUrl": "https://openagent3.xyz/skills/browserbase/agent.md" } } ``` ## Documentation ### Browserbase Sessions Skill Manage persistent cloud browser sessions via Browserbase. This skill creates browser sessions that preserve authentication (cookies, local storage) across interactions, automatically solve CAPTCHAs, and record sessions for later review. ### Step 1 — Get your Browserbase credentials Sign up at browserbase.com if you haven't already. Go to Settings → API Keys and copy your API key (starts with bb_live_). Go to Settings → Project and copy your Project ID (a UUID). ### Step 2 — Install dependencies cd {baseDir}/scripts && pip install -r requirements.txt playwright install chromium Or with uv: cd {baseDir}/scripts && uv pip install -r requirements.txt uv run playwright install chromium ### Step 3 — Set environment variables export BROWSERBASE_API_KEY="bb_live_your_key_here" export BROWSERBASE_PROJECT_ID="your-project-uuid-here" Or configure via OpenClaw's skills.entries.browserbase-sessions.env in ~/.openclaw/openclaw.json. ### Step 4 — Run the setup test This validates everything end-to-end (credentials, SDK, Playwright, API connection, and a live smoke test): python3 {baseDir}/scripts/browserbase_manager.py setup You should see "status": "success" with all steps passing. If any step fails, the error message tells you exactly what to fix. ### Defaults Every session is created with these defaults to support research workflows: Captcha solving: ON — Browserbase automatically solves CAPTCHAs so login flows and protected pages work without manual intervention. Disable with --no-solve-captchas. Session recording: ON — Every session is recorded as a video you can download later for review or sharing. Disable with --no-record. Auth persistence — Use contexts with --persist to stay logged in across sessions. ### Available Commands All commands are run via the manager script: python3 {baseDir}/scripts/browserbase_manager.py [options] ### Setup & Validation Run the full setup test: python3 {baseDir}/scripts/browserbase_manager.py setup ### Context Management (for authentication persistence) Create a named context to store login state: python3 {baseDir}/scripts/browserbase_manager.py create-context --name github List all saved contexts: python3 {baseDir}/scripts/browserbase_manager.py list-contexts Delete a context (by name or ID): python3 {baseDir}/scripts/browserbase_manager.py delete-context --context-id github ### Session Lifecycle Create a new session (captcha solving and recording enabled by default): # Basic session python3 {baseDir}/scripts/browserbase_manager.py create-session # Session with saved context (persist=true saves cookies on close) python3 {baseDir}/scripts/browserbase_manager.py create-session --context-id github --persist # Keep-alive session for long research (survives disconnections) python3 {baseDir}/scripts/browserbase_manager.py create-session --context-id github --persist --keep-alive --timeout 3600 # Full options python3 {baseDir}/scripts/browserbase_manager.py create-session \\ --context-id github \\ --persist \\ --keep-alive \\ --timeout 3600 \\ --region us-west-2 \\ --proxy \\ --block-ads \\ --viewport-width 1280 \\ --viewport-height 720 List all sessions: python3 {baseDir}/scripts/browserbase_manager.py list-sessions python3 {baseDir}/scripts/browserbase_manager.py list-sessions --status RUNNING Get session details: python3 {baseDir}/scripts/browserbase_manager.py get-session --session-id Terminate a session: python3 {baseDir}/scripts/browserbase_manager.py terminate-session --session-id ### Browser Automation Navigate to a URL: # Navigate and get page title python3 {baseDir}/scripts/browserbase_manager.py navigate --session-id --url "https://example.com" # Navigate and extract text python3 {baseDir}/scripts/browserbase_manager.py navigate --session-id --url "https://example.com" --extract-text # Navigate and save screenshot python3 {baseDir}/scripts/browserbase_manager.py navigate --session-id --url "https://example.com" --screenshot /tmp/page.png # Navigate and take full-page screenshot python3 {baseDir}/scripts/browserbase_manager.py navigate --session-id --url "https://example.com" --screenshot /tmp/full.png --full-page Take a screenshot of the current page (without navigating): python3 {baseDir}/scripts/browserbase_manager.py screenshot --session-id --output /tmp/current.png python3 {baseDir}/scripts/browserbase_manager.py screenshot --session-id --output /tmp/full.png --full-page Execute JavaScript: python3 {baseDir}/scripts/browserbase_manager.py execute-js --session-id --code "document.title" Get cookies: python3 {baseDir}/scripts/browserbase_manager.py get-cookies --session-id ### Recordings, Logs & Debug Download a session recording video (session must be terminated first): python3 {baseDir}/scripts/browserbase_manager.py get-recording --session-id --output /tmp/session.webm Get session logs: python3 {baseDir}/scripts/browserbase_manager.py get-logs --session-id Get the live debug URL (for visual inspection of a running session): python3 {baseDir}/scripts/browserbase_manager.py live-url --session-id ### Workflow 1: Multi-session research with persistent login # 1. One-time: create a named context for the site python3 {baseDir}/scripts/browserbase_manager.py create-context --name myapp # 2. Start a research session (captchas auto-solved, recording on) python3 {baseDir}/scripts/browserbase_manager.py create-session --context-id myapp --persist --keep-alive --timeout 3600 # 3. Navigate to login — captchas solved automatically python3 {baseDir}/scripts/browserbase_manager.py navigate --session-id --url "https://myapp.com/login" # Use execute-js to fill forms and submit # 4. Do research, take screenshots python3 {baseDir}/scripts/browserbase_manager.py navigate --session-id --url "https://myapp.com/dashboard" --extract-text python3 {baseDir}/scripts/browserbase_manager.py screenshot --session-id --output /tmp/dashboard.png # 5. Terminate (cookies saved to context) python3 {baseDir}/scripts/browserbase_manager.py terminate-session --session-id # 6. Download recording to share python3 {baseDir}/scripts/browserbase_manager.py get-recording --session-id --output /tmp/research.webm # 7. Next day: new session, already logged in! python3 {baseDir}/scripts/browserbase_manager.py create-session --context-id myapp --persist --keep-alive --timeout 3600 ### Workflow 2: Screenshot documentation python3 {baseDir}/scripts/browserbase_manager.py create-session python3 {baseDir}/scripts/browserbase_manager.py navigate --session-id --url "https://docs.example.com" --screenshot /tmp/docs_home.png python3 {baseDir}/scripts/browserbase_manager.py navigate --session-id --url "https://docs.example.com/api" --screenshot /tmp/docs_api.png --full-page python3 {baseDir}/scripts/browserbase_manager.py terminate-session --session-id ### Workflow 3: Record and share a walkthrough # Session recording is ON by default python3 {baseDir}/scripts/browserbase_manager.py create-session --context-id myapp --persist # ... do your walkthrough (navigate, click, etc.) ... python3 {baseDir}/scripts/browserbase_manager.py terminate-session --session-id # Download the video python3 {baseDir}/scripts/browserbase_manager.py get-recording --session-id --output /tmp/walkthrough.webm ### Important Notes Captcha solving is ON by default. Browserbase handles CAPTCHAs automatically during login flows and page loads. Use --no-solve-captchas to disable. Recording is ON by default. Every session is recorded. Download with get-recording after termination. Use --no-record to disable. Connection timeout: 5 minutes to connect after creation before auto-termination. Keep-alive sessions survive disconnections and must be explicitly terminated. Context persistence: Wait a few seconds after terminate-session --persist before creating a new session with the same context. Named contexts: Use --name with create-context to save friendly names (e.g. github, slack). Use the name anywhere a context ID is expected. One context per site: Use separate contexts for different authenticated sites. Avoid concurrent sessions on the same context. Regions: us-west-2 (default), us-east-1, eu-central-1, ap-southeast-1. Session timeout: 60–21600 seconds (max 6 hours). ### Error Handling All commands return JSON output. On error, the output includes an "error" key. Common errors: APIConnectionError: Browserbase API unreachable RateLimitError: Too many concurrent sessions for your plan APIStatusError: Invalid parameters or authentication failure Missing env vars: Set BROWSERBASE_API_KEY and BROWSERBASE_PROJECT_ID ### Reference For full API details, read {baseDir}/references/api-quick-ref.md. ## Trust - Source: tencent - Verification: Indexed source record - Publisher: JamesFincher - Version: 1.0.0 ## Source health - Status: healthy - Item download looks usable. - Yavira can redirect you to the upstream package for this item. - Health scope: item - Reason: direct_download_ok - Checked at: 2026-04-29T07:25:37.850Z - Expires at: 2026-05-06T07:25:37.850Z - Recommended action: Download for OpenClaw ## Links - [Detail page](https://openagent3.xyz/skills/browserbase) - [Send to Agent page](https://openagent3.xyz/skills/browserbase/agent) - [JSON manifest](https://openagent3.xyz/skills/browserbase/agent.json) - [Markdown brief](https://openagent3.xyz/skills/browserbase/agent.md) - [Download page](https://openagent3.xyz/downloads/browserbase)