unbrowse-openclaw（unbrowse OpenClaw 搜索）

Unbrowse — Drop-in Browser Replacement for Agents

Browse once, cache the APIs, reuse them instantly. First call discovers and learns the site's APIs (~20-80s). Every subsequent call uses cached skills (<200ms for server-fetch, ~2s for sites requiring browser execution).

IMPORTANT: Always use the CLI (bun src/cli.ts). NEVER pipe output to node -e, python -c, or jq — this causes shell escaping failures. Use --path, --extract, and --limit flags instead.

Server Startup

cd ~/.agents/skills/unbrowse && bun src/cli.ts health

If not running, the CLI auto-starts the server. First time requires ToS acceptance — ask the user:

Unbrowse needs you to accept its Terms of Service: - Discovered API structures may be shared in the collective registry - You will not use Unbrowse to attack, overload, or abuse any target site Full terms: https://unbrowse.ai/terms

After consent, the CLI handles startup automatically. First run also needs the browser engine:

cd ~/.agents/skills/unbrowse && npx agent-browser install

Core Workflow

Step 1: Resolve an intent

cd ~/.agents/skills/unbrowse && bun src/cli.ts resolve \
  --intent "get feed posts" \
  --url "https://www.linkedin.com/feed/" \
  --pretty

This returns available_endpoints — a ranked list of discovered API endpoints. Pick the right one by URL pattern (e.g., MainFeed for feed, HomeTimeline for tweets).

Step 2: Execute with extraction

cd ~/.agents/skills/unbrowse && bun src/cli.ts execute \
  --skill {skill_id} \
  --endpoint {endpoint_id} \
  --path "data.included[]" \
  --extract "author:actor.name.text,text:commentary.text.text,posted:actor.subDescription.text" \
  --limit 20 \
  --pretty

This is the key pattern — --path + --extract + --limit replace ALL piping to jq/node/python.

Step 3: Submit feedback (MANDATORY)

cd ~/.agents/skills/unbrowse && bun src/cli.ts feedback \
  --skill {skill_id} \
  --endpoint {endpoint_id} \
  --rating 5 \
  --outcome success

Rating: 5=right+fast, 4=right+slow(>5s), 3=incomplete, 2=wrong endpoint, 1=useless.

Data Extraction Flags

These flags eliminate the need to pipe output to any external parser:

When these flags are used, trace metadata is slimmed automatically (1MB raw -> 1.5KB output typical).

Examples

# X timeline — extract tweets with user, text, likes
bun src/cli.ts execute --skill {id} --endpoint {id} \
  --path "data.home.home_timeline_urt.instructions[].entries[].content.itemContent.tweet_results.result" \
  --extract "user:core.user_results.result.legacy.screen_name,text:legacy.full_text,likes:legacy.favorite_count" \
  --limit 20 --pretty

# LinkedIn feed — extract posts from included[]
bun src/cli.ts execute --skill {id} --endpoint {id} \
  --path "data.included[]" \
  --extract "author:actor.name.text,text:commentary.text.text,likes:socialDetail.totalSocialActivityCounts.numLikes" \
  --limit 20 --pretty

# Simple case — just limit results
bun src/cli.ts execute --skill {id} --endpoint {id} --limit 10 --pretty

Extraction Recipes

For responses you parse repeatedly, submit a recipe so future calls return clean data automatically (for ALL agents):

cd ~/.agents/skills/unbrowse && bun src/cli.ts recipe \
  --skill {skill_id} \
  --endpoint {endpoint_id} \
  --source "included" \
  --fields "author:actor.name.text,text:commentary.text.text,posted:actor.subDescription.text" \
  --require "commentary" \
  --compact \
  --description "Extract posts from LinkedIn feed"

When a recipe exists, future executions auto-return clean data. Use --raw to bypass recipes.

Authentication

Automatic. Unbrowse extracts cookies from your Chrome/Firefox SQLite database — if you're logged into a site in Chrome, it just works.

If auth_required is returned:

cd ~/.agents/skills/unbrowse && bun src/cli.ts login --url "https://example.com/login"

User completes login in the browser window. Cookies are stored and reused automatically.

Other Commands

bun src/cli.ts skills                                    # List all skills
bun src/cli.ts skill {id}                                # Get skill details
bun src/cli.ts search --intent "..." --domain "..."      # Search marketplace
bun src/cli.ts sessions --domain "linkedin.com"          # Debug session logs
bun src/cli.ts health                                    # Server health check

Mutations

Always --dry-run first, ask user before --confirm-unsafe:

bun src/cli.ts execute --skill {id} --endpoint {id} --dry-run
bun src/cli.ts execute --skill {id} --endpoint {id} --confirm-unsafe

REST API Reference

For cases where the CLI doesn't cover your needs, the raw REST API is at http://localhost:6969:

Rules

1. Always use the CLI — never pipe to node -e, python -c, or jq. Use --path/--extract/--limit instead.
2. Always try resolve first — it handles the full marketplace search -> capture pipeline
3. Check the result — if wrong, pick from available_endpoints and re-execute with --endpoint
4. If auth_required, use login then retry
5. Always --dry-run before mutations
6. Always submit feedback after every resolve call — this is mandatory
7. If the response is deeply nested, submit a recipe so future agents get clean data
8. Report bugs and issues on GitHub — when something breaks, is slow, or behaves unexpectedly, file an issue:

   gh issue create --repo unbrowse-ai/unbrowse \
     --title "bug: {short description}" \
     --body "## What happened\
{description}\
\
## Expected\
{what should have happened}\
\
## Context\
- Skill: {skill_id}\
- Endpoint: {endpoint_id}\
- Domain: {domain}\
- Error: {error message or status code}"

Categories: bug: (broken/wrong data), perf: (slow), auth: (login/cookie issues), feat: (missing capability)