Xpersona
B

Browserbase Persist with captcha

CLAWHUB · Unverified

Create and manage persistent Browserbase cloud browser sessions with authentication persistence. Use when the user needs to automate browsers, maintain logged-in sessions across interactions, scrape authenticated pages, or manage cloud browser instances. Handles session creation, context-based auth persistence, keep-alive reconnection, captcha solving, session recording, screenshots, and session cleanup.

62
Rank
84
Safety
30k
Downloads

About

What it does, and when to use it.

Capability contract not published. No trust telemetry is available yet. 30.3K downloads reported by the source. Last updated 11/16/2026.

Avoid when

  • Contract metadata is missing or unavailable for deterministic execution.

Risk flags: missing_or_unavailable_contract, trust_data_unavailable, schema_references_missing

Install and run

Setup complexity: medium.

clawhub skill install s174wn02jek6gfrgczfqg8bnn9884ymx:browserbase
  1. Install using `clawhub skill install s174wn02jek6gfrgczfqg8bnn9884ymx:browserbase` in an isolated environment before connecting it to live workloads.
  2. No published capability contract is available yet, so validate auth and request/response behavior manually.
  3. Review the upstream CLAWHUB listing at https://clawhub.ai/jamesfincher/browserbase before using production credentials.

Contract: missing

curl -s "https://www.xpersona.co/api/v1/agents/clawhub-jamesfincher-browserbase-wserbase-2/snapshot"

Run-check

$0.02 USD

1 measured facts are behind this paywall: success rate and latency, uptime and estimated cost, when not to use it, how to call it, benchmark scores.

Agents pay $0.02 in USDC. A card payment is $0.50, the smallest a card allows.

Documentation

CLAWHUB

21,199 characters of source documentation, loaded on request.

Extracted files

5 files captured from the source.

SKILL.md

---
name: browserbase-sessions
description: Create and manage persistent Browserbase cloud browser sessions with authentication persistence. Use when the user needs to automate browsers, maintain logged-in sessions across interactions, scrape authenticated pages, or manage cloud browser instances. Handles session creation, context-based auth persistence, keep-alive reconnection, captcha solving, session recording, screenshots, and session cleanup.
license: MIT
metadata:
  author: custom
  version: "2.0.0"
  openclaw:
    emoji: "🌐"
    requires:
      bins: ["python3"]
      anyBins: ["uv", "pip"]
      env: ["BROWSERBASE_API_KEY", "BROWSERBASE_PROJECT_ID"]
    primaryEnv: "BROWSERBASE_API_KEY"
---

# 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.

## First-Time Setup

### Step 1 — Get your Browserbase credentials

1. Sign up at [browserbase.com](https://www.browserbase.com/) if you haven't already.
2. Go to **Settings → API Keys** and copy your API key (starts with `bb_live_`).
3. Go to **Settings → Project** and copy your Project ID (a UUID).

### Step 2 — Install dependencies

```bash
cd {baseDir}/scripts && pip install -r requirements.txt
playwright install chromium
```

Or with uv:

```bash
cd {baseDir}/scripts && uv pip install -r requirements.txt
uv run playwright install chromium
```

### Step 3 — Set environment variables

```bash
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):

```bash
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:

```bash
python3 {baseDir}/scripts/browserbase_manager.py <command> [options]
```

### Setup & Validation

Run the full setup test:
```bash
python3 {baseDir}/scripts/browserbase_manager.py setup
```

### Context Management (for authentication persistence)

Create a named context to store login state

README.md

# Browserbase Sessions — OpenClaw Skill

A production-ready OpenClaw skill for creating and managing persistent Browserbase
cloud browser sessions with authentication persistence, automatic captcha solving,
session recording, and screenshot capture.

## What it does

This skill gives the OpenClaw agent the ability to:

- **Create cloud browser sessions** via Browserbase's infrastructure
- **Persist authentication** across sessions using Contexts (cookies, local storage,
  session storage are saved and restored automatically)
- **Solve CAPTCHAs automatically** — login flows and protected pages work without
  manual intervention (enabled by default)
- **Record sessions as video** — every session is recorded for later download and
  sharing (enabled by default)
- **Take screenshots** — viewport or full-page, during navigation or on demand
- **Reconnect to keep-alive sessions** that survive disconnections
- **Automate browsing** — navigate, execute JavaScript, extract page content, read cookies
- **Manage session lifecycle** — list, inspect, and terminate sessions

## Requirements

- Python 3.9+
- `browserbase` Python package
- `playwright` Python package + Chromium browser
- A Browserbase account with API key and project ID

## Quick Start

### 1. Copy the skill to your OpenClaw skills directory

```bash
cp -r browserbase-sessions/ ~/.openclaw/workspace/skills/browserbase-sessions/
```

### 2. Install dependencies

```bash
cd ~/.openclaw/workspace/skills/browserbase-sessions/scripts
pip install -r requirements.txt
playwright install chromium
```

### 3. Set credentials

```bash
export BROWSERBASE_API_KEY="bb_live_your_key_here"
export BROWSERBASE_PROJECT_ID="your-project-uuid-here"
```

### 4. Run the setup test

```bash
python3 ~/.openclaw/workspace/skills/browserbase-sessions/scripts/browserbase_manager.py setup
```

This validates everything end-to-end: credentials, SDK, Playwright, API connection, and runs a live smoke test (creates a session, navigates to example.com, terminates).

## Available Commands

| Command | Description |
|---|---|
| `setup` | Validate credentials and run full smoke test |
| `create-context` | Create a persistent context (with optional `--name`) |
| `delete-context` | Delete a context |
| `list-contexts` | List saved named contexts |
| `create-session` | Create a browser session (captchas + recording ON by default) |
| `list-sessions` | List all sessions |
| `get-session` | Get session details |
| `terminate-session` | Terminate a running session |
| `navigate` | Navigate to a URL (with optional screenshot and text extraction) |
| `screenshot` | Take a screenshot of the current page |
| `execute-js` | Execute JavaScript in a session |
| `get-cookies` | Get cookies from a session |
| `get-recording` | Download session recording video |
| `get-logs` | Get session logs |
| `live-url` | Get live debug URL for a running session |

## Key Design Decisions

**Captcha solving ON by default.** Browserbase's captcha solver handle

_meta.json

{
  "ownerId": "kn743w9z7ax79rga8s32df9ths802e4f",
  "slug": "browserbase",
  "version": "1.0.0",
  "publishedAt": 1770748803191
}

references/api-quick-ref.md

# Browserbase API Quick Reference

## Authentication
All REST endpoints require: `X-BB-API-Key: <your-api-key>`
Base URL: `https://api.browserbase.com/v1`

## Sessions

### Create Session
`POST /v1/sessions`
```json
{
  "projectId": "<string>",
  "browserSettings": {
    "context": { "id": "<context-id>", "persist": true },
    "blockAds": true,
    "recordSession": true,
    "solveCaptchas": true,
    "viewport": { "width": 1280, "height": 720 }
  },
  "timeout": 3600,
  "keepAlive": true,
  "proxies": true,
  "region": "us-west-2"
}
```
Response includes `id`, `connectUrl` (CDP WebSocket), `status`.

### List Sessions
`GET /v1/sessions` → Array of session objects

### Get Session
`GET /v1/sessions/{id}` → Single session object

### Terminate Session
`POST /v1/sessions/{id}` with `{"projectId": "...", "status": "REQUEST_RELEASE"}`

### Debug / Live URLs
`GET /v1/sessions/{id}/debug` → Debug connection URL, WebSocket URL, and page list

### Session Logs
`GET /v1/sessions/{id}/logs`

### Session Recording
`GET /v1/sessions/{id}/recording`

## Contexts (Authentication Persistence)

### Create Context
`POST /v1/contexts` with `{"projectId": "<project-id>"}`
Returns object with `id`.

### Delete Context
`DELETE /v1/contexts/{id}` → 204 No Content (permanent)

### Session Logs
`GET /v1/sessions/{id}/logs` → Array of log entries (timestamps, methods, params)

### Session Recording
`GET /v1/sessions/{id}/recording` → Recording data (webm video)

### Session Downloads
`GET /v1/sessions/{id}/downloads` → Binary archive of downloaded files

## Key Details
- **Connection timeout**: 5 min after creation
- **Session timeout**: 60–21600 seconds (max 6 hours)
- **Regions**: us-west-2, us-east-1, eu-central-1, ap-southeast-1
- **Statuses**: RUNNING, ERROR, TIMED_OUT, COMPLETED
- **Contexts never expire** on Browserbase's side
- **persist: true** saves cookies/storage changes back to context on close
- **keepAlive: true** lets sessions survive disconnections (must terminate manually)

## Python SDK
```python
from browserbase import Browserbase
client = Browserbase(api_key="...")
session = client.sessions.create(project_id="...", browser_settings={...})
print(session.connect_url)  # CDP WebSocket URL
```

scripts/requirements.txt

browserbase>=1.0.0
playwright>=1.40.0

Sponsored

Ads related to Browserbase Persist with captcha and adjacent AI workflows.