# browserwing-admin

Adopt this skill: https://proskills.md/skills/other/memtensor-memos-apps-memos-local-openclaw-skill-browserwing-admin

Page: https://proskills.md/skills/other/memtensor-memos-apps-memos-local-openclaw-skill-browserwing-admin
This document is the public skill bundle for that page. It contains SKILL.md and every helper file the catalog carries. No login is required.

## File: apps/memos-local-openclaw/skill/browserwing-admin/SKILL.md
size: 8006
upstream: https://github.com/memtensor/memos/blob/main/apps/memos-local-openclaw/skill/browserwing-admin/SKILL.md

````text
---
name: browserwing-admin
description: Manage and operate BrowserWing — an intelligent browser automation platform. Install dependencies, configure LLM, create/manage/execute automation scripts, use AI-driven exploration to generate scripts, browse the script marketplace, and troubleshoot issues.
---

# BrowserWing Admin Skill

## Overview

BrowserWing is an intelligent browser automation platform that allows you to:
- Record, create, and replay browser automation scripts
- Use AI to autonomously explore websites and generate replayable scripts
- Execute scripts via HTTP API or MCP protocol
- Manage LLM configurations for AI-powered features

**API Base URL:** `http://localhost:8080/api/v1`

**Authentication:** Use `X-BrowserWing-Key: <api-key>` header or `Authorization: Bearer <token>`

---

## 1. Installing Google Chrome (Prerequisite)

BrowserWing requires Google Chrome to be installed on the host machine.

### Linux (Debian/Ubuntu)
```bash
wget -q -O - https://dl-ssl.google.com/linux/linux_signing_key.pub | sudo apt-key add -
echo "deb [arch=amd64] http://dl.google.com/linux/chrome/deb/ stable main" | sudo tee /etc/apt/sources.list.d/google-chrome.list
sudo apt-get update
sudo apt-get install -y google-chrome-stable
```

### macOS
```bash
brew install --cask google-chrome
```

### Windows
Download and install from: https://www.google.com/chrome/

### Verify Installation
```bash
google-chrome --version
# or on macOS:
# /Applications/Google\ Chrome.app/Contents/MacOS/Google\ Chrome --version
```

### Using Remote Chrome (Alternative)
If Chrome is running on a remote machine with debugging enabled:
```bash
google-chrome --remote-debugging-port=9222 --remote-debugging-address=0.0.0.0 --no-sandbox
```
Then configure BrowserWing's `config.toml`:
```toml
[browser]
control_url = 'http://<remote-host>:9222'
```

---

## 2. LLM Configuration

AI features (AI Explorer, Agent chat, smart extraction) require an LLM configuration.

### List LLM Configs
```bash
curl -X GET 'http://localhost:8080/api/v1/llm-configs'
```

### Add LLM Config
```bash
curl -X POST 'http://localhost:8080/api/v1/llm-configs' \
  -H 'Content-Type: application/json' \
  -d '{
    "name": "my-openai",
    "provider": "openai",
    "api_key": "sk-xxx",
    "model": "gpt-4o",
    "base_url": "https://api.openai.com/v1",
    "is_active": true,
    "is_default": true
  }'
```
**Supported providers:** `openai`, `anthropic`, `deepseek`, or any OpenAI-compatible endpoint.

### Test LLM Config
```bash
curl -X POST 'http://localhost:8080/api/v1/llm-configs/test' \
  -H 'Content-Type: application/json' \
  -d '{"name": "my-openai"}'
```

### Update LLM Config
```bash
curl -X PUT 'http://localhost:8080/api/v1/llm-configs/<config-id>' \
  -H 'Content-Type: application/json' \
  -d '{"api_key": "sk-new-key", "model": "gpt-4o-mini"}'
```

### Delete LLM Config
```bash
curl -X DELETE 'http://localhost:8080/api/v1/llm-configs/<config-id>'
```

---

## 3. AI Autonomous Exploration (Generate Scripts Automatically)

Use AI to browse a website, perform a task, and automatically generate a replayable script.

### Start Exploration
```bash
curl -X POST 'http://localhost:8080/api/v1/ai-explore/start' \
  -H 'Content-Type: application/json' \
  -d '{
    "task_desc": "Go to bilibili.com, search for 'AI', and get the first page of video results",
    "start_url": "https://www.bilibili.com",
    "llm_config_id": "my-openai"
  }'
```
**Response:** Returns a session `id` for tracking.

### Stream Exploration Events (SSE)
```bash
curl -N 'http://localhost:8080/api/v1/ai-explore/<session-id>/stream'
```
Returns real-time Server-Sent Events: `thinking`, `tool_call`, `progress`, `error`, `script_ready`, `done`.

### Stop Exploration
```bash
curl -X POST 'http://localhost:8080/api/v1/ai-explore/<session-id>/stop'
```

### Get Generated Script
```bash
curl -X GET 'http://localhost:8080/api/v1/ai-explore/<session-id>/script'
```

### Save Generated Script
```bash
curl -X POST 'http://localhost:8080/api/v1/ai-explore/<session-id>/save'
```
Saves the generated script to the local script library for future replay.

---

## 4. Script Management

### List All Scripts
```bash
curl -X GET 'http://localhost:8080/api/v1/scripts'
```
Returns all local scripts with their `id`, `name`, `description`, `actions`, `tags`, `group`, etc.

### Get Script Details
```bash
curl -X GET 'http://localhost:8080/api/v1/scripts/<script-id>'
```

### Get Script Schema / Summary
```bash
curl -X GET 'http://localhost:8080/api/v1/scripts/summary'
```
Returns a concise summary of all scripts, including names, descriptions, input parameters (variables), and action counts. Useful for programmatic discovery.

### Create a New Script
```bash
curl -X POST 'http://localhost:8080/api/v1/scripts' \
  -H 'Content-Type: application/json' \
  -d '{
    "name": "Search Bilibili",
    "description": "Search for a keyword on Bilibili",
    "url": "https://www.bilibili.com",
    "actions": [
      {"type": "navigate", "url": "https://www.bilibili.com"},
      {"type": "click", "identifier": ".nav-search-input"},
      {"type": "type", "identifier": ".nav-search-input", "value": "${keyword}"},
      {"type": "press_key", "key": "Enter"},
      {"type": "wait", "timeout": 3}
    ]
  }'
```
**Variables:** Use `${variable_name}` syntax in action values. These become input parameters when the script is executed.

### Update a Script
```bash
curl -X PUT 'http://localhost:8080/api/v1/scripts/<script-id>' \
  -H 'Content-Type: application/json' \
  -d '{"name": "Updated Name", "description": "Updated description"}'
```

### Delete a Script
```bash
curl -X DELETE 'http://localhost:8080/api/v1/scripts/<script-id>'
```

### Export Scripts as Skill (Convert to SKILL.md)

Convert one or more scripts into a SKILL.md file that can be imported by AI agents (e.g., Claude, Cursor). This allows other AI agents to discover and execute your BrowserWing scripts.

#### Export Selected Scripts
```bash
curl -X POST 'http://localhost:8080/api/v1/scripts/export/skill' \
  -H 'Content-Type: application/json' \
  -d '{
    "script_ids": ["script-id-1", "script-id-2", "script-id-3"]
  }'
```
Merges multiple scripts into a single SKILL.md with all their actions, variables, and descriptions.

#### Export All Scripts
```bash
curl -X POST 'http://localhost:8080/api/v1/scripts/export/skill' \
  -H 'Content-Type: application/json' \
  -d '{"script_ids": []}'
```
Pass an empty `script_ids` array to export **all** scripts into one SKILL.md.

#### Export Executor Skill (Browser Control API)
```bash
curl -X GET 'http://localhost:8080/api/v1/executor/export/skill'
```
Exports the low-level browser automation API as a skill, allowing an AI agent to directly control the browser (navigate, click, type, extract, etc.).

**Workflow: Script → Skill → AI Agent**
```
1. Create scripts (manually, by recording, or via AI exploration)
2. Export them as SKILL.md: POST /scripts/export/skill
3. Place the SKILL.md in your AI agent's skill directory
4. The AI agent can now discover and call your scripts via POST /scripts/<id>/play
```

---

## 5. Execute Scripts

### Run a Script by ID
```bash
curl -X POST 'http://localhost:8080/api/v1/scripts/<script-id>/play' \
  -H 'Content-Type: application/json' \
  -d '{
    "variables": {
      "keyword": "deepseek"
    }
  }'
```
**Variables:** Pass values for `${variable_name}` placeholders defined in the script actions.

### Get Play Result (Extracted Data)
```bash
curl -X GET 'http://localhost:8080/api/v1/scripts/play/result'
```
Returns data extracted during the last script execution (e.g., scraped content from `execute_js` actions).

### List Script Execution History
```bash
curl -X GET 'http://localhost:8080/api/v1/script-executions?page=1&page_size=20'
```

---

## 6. Script Marketplace (Remote Scripts)

*Note: The remote script marketplace feature is under development. The following APIs may not be available yet.*

### Browse Marketplace
```bash
# TODO: curl -X GET 'http
````

## File: README.md
upstream: https://github.com/memtensor/memos/blob/main/README.md

````text
<div align="center">
  <h1 align="center">
    <a href="https://memos.openmem.net/">
      <img src="https://statics.memtensor.com.cn/logo/memos_color_m.png" alt="MemOS Logo" width="48"/>
    </a>&nbsp;
    MemOS 2.0&ensp;Stardust（星尘）
  </h1>

  <p align="center">
    <a href="https://memos-docs.openmem.net/home/overview/"><img src="https://img.shields.io/badge/Docs-Get--Start-002FA7?labelColor=gray&style=for-the-badge&logo=googledocs&logoColor=white" alt="Docs"></a>
    <a href="https://arxiv.org/abs/2507.03724"><img src="https://img.shields.io/badge/ArXiv-2507.03724-B31B1B?labelColor=gray&style=for-the-badge&logo=arxiv&logoColor=white" alt="ArXiv"></a>
    <a href="https://x.com/MemOS_dev"><img src="https://img.shields.io/badge/Follow-MemOS-000000?labelColor=gray&style=for-the-badge&logo=x&logoColor=white" alt="X"></a>
    <a href="https://discord.gg/Txbx3gebZR"><img src="https://img.shields.io/badge/dynamic/json?url=https%3A%2F%2Fdiscord.com%2Fapi%2Fv10%2Finvites%2FTxbx3gebZR%3Fwith_counts%3Dtrue&query=%24.approximate_presence_count&suffix=%20online&label=Discord&color=404EED&labelColor=gray&style=for-the-badge&logo=discord&logoColor=white" alt="Discord"></a>
    <br>
    <a href="https://github.com/IAAR-Shanghai/Awesome-AI-Memory"><img src="https://img.shields.io/badge/Resources-Awesome--AI--Memory-8A2BE2?labelColor=gray&style=for-the-badge&logo=awesomelists&logoColor=white" alt="Resources"></a>
  </p>

  <p align="center">
    <strong>Give your Agent persistent memory and the ability to grow.</strong><br/>
  </p>

  <p align="center">
<a href="https://trendshift.io/repositories/18526?utm_source=repository-badge&amp;utm_medium=badge&amp;utm_campaign=badge-repository-18526" target="_blank" rel="noopener noreferrer"><img src="https://trendshift.io/api/badge/repositories/18526" alt="MemTensor%2FMemOS | Trendshift" width="250" height="55"/></a>
  </p>

  <p align="center">
    <strong>English</strong> | <a href="README_ZH.md">中文</a>
  </p>
</div>

<div align="center">
  <img width="1660" alt="MemOS agent ecosystem: OpenClaw, Hermes, and DeepSeek Harness" src="./assets/readme/memos-agent-ecosystem.png" />
</div>

> [!TIP]
> **New: Connect MemOS to DeepSeek Harness (`dsh`)**
>
> Add automatic recall, background capture, hybrid retrieval, and a local Memory Viewer to DeepSeek Harness—powered by the same MemOS core used across agent ecosystems.
>
> **[Get started →](#memos-plugin)**

---

## 👾 MemOS: Memory Operating System for LLM & AI Agents

**MemOS** is a Memory Operating System for LLMs and AI agents that unifies **store / retrieve / manage** for long-term memory, enabling **context-aware and personalized** interactions with **KB**, **multi-modal**, **tool memory**, and **enterprise-grade** optimizations built in.

### Key Features

- **Unified Memory API**: A single API to add, retrieve, edit, and delete memory—structured as a graph, inspectable and editable by design, not a black-box embedding store.
- **Multi-Modal Memory**: Natively supports text, images, tool traces, and personas, retrieved and reasoned together in one memory system.
- **Multi-Cube Knowledge Base Management**: Manage multiple knowledge bases as composable memory cubes, enabling isolation, controlled sharing, and dynamic composition across users, projects, and agents.
- **Asynchronous Ingestion via MemScheduler**: Run memory operations asynchronously with millisecond-level latency for production stability under high concurrency.
- **Memory Feedback & Correction**: Refine memory with natural-language feedback—correcting, supplementing, or replacing existing memories over time.

### News

- **2026-08-17** · 🐋 **MemOS Connects with DeepSeek Harness**
  MemOS now brings persistent memory to **DeepSeek Harness** through both local and cloud plugins. DSH can automatically recall relevant context before a task and retain new experience after a successful turn, without modifying its core.

- **2026-07-02** · 🏆 **MemOS Advances Agent and User Memory Benchmarks**
  With MemOS, **OpenClaw** improves average task completion from **36.63% to 50.87%** across five agent tasks. MemOS also achieves **88.83 on LoCoMo** and **89.20 on LongMemEval**, and leads in **OmniMemEval**, a unified evaluation of 14 commercial memory products across ten datasets.

- **2026-05-09** · 🧠 **memos-local-plugin 2.0**
  Official local memory plugin for **Hermes Agent** and **OpenClaw**. One core powers self-evolving memory across L1 traces, L2 policies, L3 world models, and crystallized Skills, with local-first storage and feedback-driven retrieval.

- **2026-04-10** · 👧🏻 **MemOS Hermes Agent Local Plugin**
  Official Hermes Agent memory plugins launched: Hybrid retrieval (FTS5 + vector), smart dedup, tiered skill evolution, multi-agent collaboration. 100% local, zero cloud dependency.

- **2026-03-08** · 🦞 **MemOS OpenClaw Plugin — Cloud & Local**
  Official OpenClaw memory plugins launched. **Cloud Plugin**: hosted memory service with 72% lower token usage and multi-agent memory sharing ([MemOS-Cloud-OpenClaw-Plugin](https://github.com/MemTensor/MemOS-Cloud-OpenClaw-Plugin)). **Local Plugin** (`v1.0.0`): 100% on-device memory with persistent SQLite, hybrid search (FTS5 + vector), task summarization & skill evolution, multi-agent collaboration, and a full Memory Viewer dashboard.

## 📊 Performance

MemOS leads across multiple benchmarks — evaluated against mainstream commercial memory products across 5 user memory and 5 agent memory tasks.

| Benchmark       | Score |
| --------------- | ----- |
| LoCoMo          | 88.83 |
| LongMemEval     | 89.20 |
| PersonaMem v2   | 40.58 |
| HaluMem         | 80.91 |
| BEAM-10M        | 56.75 |
| GDPVal          | 62.07 |
| LiveCodeBench   | 64.96 |
| OmniMath        | 61.00 |
| SWE-Bench       | 38.46 |
| BrowseComp-Plus | 23.85 |

Evaluated via OmniMemEval — [https://github.com/MemTensor/OmniMemEval](https://github.com/MemTensor/OmniMemEval).

## 🎯 What MemOS Is For

MemOS gives AI agents long-term memory. Common uses:

- AI assistants with consistent, context-rich conversations
- Customer support that recalls past tickets and user history
- Personalized agents that adapt to individual preferences
- Multi-agent collaboration with shared or isolated memory

## 🚀 Quick Start

MemOS is built around four entry points. Pick the one that matches your scenario.

|              | Cloud API               | Self-Host          | MemOS Cloud Plugin       | Local Plugin                                     |
| ------------ | ----------------------- | ------------------ | ------------------------ | ------------------------------------------------ |
| Best for     | Your app, fully managed | Teams on own infra | OpenClaw users, zero ops | DeepSeek Harness, Hermes, or OpenClaw; on-device |
| Setup        | Get an API key          | docker compose up  | openclaw plugins install | npm install + agent-specific setup               |
| Infra needed | None (hosted)           | Neo4j + Qdrant     | None (uses MemOS Cloud)  | None (local SQLite)                              |
| Data lives   | MemOS Cloud             | Your servers       | MemOS Cloud              | Your machine                                     |

### ☁️ Use the Cloud API (Hosted)

You want to add memory to your app through a fully managed service — no infrastructure to run.

**1. Get an API key:**

- Sign up on the [MemOS dashboard](https://memos-dashboard.openmem.net/cn/quickstart/?source=landing).
- Go to **API Keys** and copy your key (starts with `mpg-`). Keep it server-side.

**2. Add and search memories:**

```python
import requests

API_KEY = "mpg-..."                  # keep this server-side
base = "https://memos.memtensor.cn/api/openmem/v1"
headers = {"Authorization": f"Token {API_KEY}", "Content-Type": "application/json"}

# 1. Add a memory
requests.post(f"{base}/add/message", headers=headers, json={
    "user_id": "alice",
    "conversation_id": "conv_001",
    "messages": [{"role": "user", "content": "I like s
````
