browser-cdp

What is browser-cdp?#

browser-cdp connects directly to your local Chrome via Chrome DevTools Protocol (CDP), giving the AI agent:

• Full login state — your cookies and sessions are carried through
• Anti-bot bypass — pages that block static fetchers (search results, video platforms)
• Interactive operations — click, fill forms, scroll, drag, file upload
• Dynamic content extraction — read JavaScript-rendered DOM
• Screenshots — capture any page at any point

Architecture#

text

Chrome (remote-debugging-port=9222)
    ↓ CDP WebSocket
CDP Proxy (cdp-proxy.mjs) — HTTP API on localhost:3456
    ↓ HTTP REST
OpenClaw AI Agent

Setup#

1. Start Chrome with debugging port#

bash

# macOS — must use full binary path (not `open -a`)
pkill -9 "Google Chrome"; sleep 2
"/Applications/Google Chrome.app/Contents/MacOS/Google Chrome" \
  --remote-debugging-port=9222 \
  --user-data-dir=/tmp/chrome-debug-profile \
  --no-first-run &

Verify:

bash

curl -s http://127.0.0.1:9222/json/version

2. Start CDP Proxy#

bash

node ~/.openclaw/skills/browser-cdp/scripts/cdp-proxy.mjs &
sleep 3
curl -s http://localhost:3456/health
# {"status":"ok","connected":true,"sessions":0,"chromePort":9222}

API Reference#

bash

# List all tabs
curl -s http://localhost:3456/targets

# Open URL in new tab
curl -s "http://localhost:3456/new?url=https://example.com"

# Execute JavaScript
curl -s -X POST "http://localhost:3456/eval?target=TARGET_ID" \
  -d 'document.title'

# JS click (fast, preferred)
curl -s -X POST "http://localhost:3456/click?target=TARGET_ID" \
  -d 'button.submit'

# Real mouse click
curl -s -X POST "http://localhost:3456/clickAt?target=TARGET_ID" \
  -d '.upload-btn'

# Screenshot
curl -s "http://localhost:3456/screenshot?target=TARGET_ID&file=/tmp/shot.png"

# Scroll (lazy loading)
curl -s "http://localhost:3456/scroll?target=TARGET_ID&direction=bottom"

# Navigate
curl -s "http://localhost:3456/navigate?target=TARGET_ID&url=https://..."

# Close tab
curl -s "http://localhost:3456/close?target=TARGET_ID"

Tool Selection: Three-Layer Strategy#

ScenarioUseReasonPublic pages (GitHub, Wikipedia, blogs)agent-reachFast, low token, structuredSearch results (Bing/Google/YouTube)**browser-cdpagent-reach blockedLogin-gated content****browser-cdpNo cookies in agent-reachJS-rendered pagesbrowser-cdp**Reads rendered DOMSimple automation, isolated screenshotsagent-browserNo Chrome setupLarge-scale parallel scrapingagent-reach + parallelbrowser-cdp gets rate-limited

Decision flow:

text

Public content → agent-reach (fast, cheap)
Search results / blocked → browser-cdp
Still fails → agent-reach fallback + record in site-patterns

Known Limitations#

• Chrome must use a separate profile ( /tmp/chrome-debug-profile)
• Same-site parallel tabs may get rate-limited
• Node.js 22+ required (native WebSocket)
• macOS: use full binary path to start Chrome, not open -a

Site Patterns & Usage Log#

bash

~/.openclaw/skills/browser-cdp/references/site-patterns/   # per-domain experience
~/.openclaw/skills/browser-cdp/references/usage-log.md    # per-use tracking

Origin#

Adapted from eze-is/web-access (MIT) for OpenClaw. A bug in the original ( require() in ES module, reported here) is fixed in this version.