MemOS is a memory operating system that stores, retrieves, and manages long-term memory for large language models and AI agents. It supports context-aware interactions by organizing text, images, tool traces, personas, and knowledge bases for reuse across tasks.
Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/MemTensor/MemOSnpx agentmods add skills/memtensor/memos/browserwing-adminWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/memtensor/memos/browserwing-admin)<a href="https://agentmods.dev/skills/memtensor/memos/browserwing-admin"><img src="https://agentmods.dev/badge/skills/memtensor/memos/browserwing-admin/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/memtensor/memos/browserwing-admin"><img src="https://agentmods.dev/badge/skills/memtensor/memos/browserwing-admin.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 8 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Tool Misuse · line 28 Tool calls are chained to bypass individual safety checks or escalate capabilities beyond what any single tool call would allow.Fix: Limit tool chaining depth and validate the output of each tool before passing it to the next. Require explicit user approval for multi-step chains.
- high Tool Misuse · line 29 Tool calls are chained to bypass individual safety checks or escalate capabilities beyond what any single tool call would allow.Fix: Limit tool chaining depth and validate the output of each tool before passing it to the next. Require explicit user approval for multi-step chains.
- medium Privilege Escalation · line 28 Commands invoke sudo or root privileges. Verify this elevated access is necessary and justified.Fix: Avoid sudo/root unless strictly required. Prefer least-privilege patterns. If elevation is needed, document the justification and scope.
- medium Privilege Escalation · line 29 Commands invoke sudo or root privileges. Verify this elevated access is necessary and justified.Fix: Avoid sudo/root unless strictly required. Prefer least-privilege patterns. If elevation is needed, document the justification and scope.
- medium Privilege Escalation · line 30 Commands invoke sudo or root privileges. Verify this elevated access is necessary and justified.Fix: Avoid sudo/root unless strictly required. Prefer least-privilege patterns. If elevation is needed, document the justification and scope.
- medium Privilege Escalation · line 31 Commands invoke sudo or root privileges. Verify this elevated access is necessary and justified.Fix: Avoid sudo/root unless strictly required. Prefer least-privilege patterns. If elevation is needed, document the justification and scope.
- medium Data Exfiltration · line 68 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
- medium Data Exfiltration · line 80 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00047 | $0.04463 |
| Opus 5.5 | $0.00019 | $0.01785 |
| Sonnet 5.5 | $0.00009 | $0.00893 |
| Haiku 4.5 | $0.00005 | $0.00446 |
Grade B, and why
browserwing-admin scanned grade B with 2 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
wget -q -O - https://dl-ssl.google.com/linux/linux_signing_key.pub | sudo apt-key add - Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
wget -q -O - https://dl-ssl.google.com/linux/linux_signing_key.pub | sudo apt-key add - How it starts
The opening of the file, as written. The whole thing — 522 lines — stays where its author put it; the contents beside it link to each section on GitHub.
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)
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
brew install --cask google-chrome
Windows
Download and install from: https://www.google.com/chrome/
Verify Installation
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:
google-chrome --remote-debugging-port=9222 --remote-debugging-address=0.0.0.0 --no-sandbox
Then configure BrowserWing's config.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
curl -X GET 'http://localhost:8080/api/v1/llm-configs'
Add LLM Config
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.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 1mo ago First seen · 522 lines · 47 tokens per session scan B 488fa241acce
browserwing-admin is a skill published in the GitHub repository MemTensor/MemOS (11,880 stars, last pushed 6d ago), licensed Apache-2.0. It adds 47 tokens to every session and 4,463 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it B with 2 findings (asks for root, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
mem0-status
Diagnoses mem0 connectivity, API key validity, and memory read/write functionality. Use when memory operations fail, searches return empty, addmemory errors occur, or to verify the plugin is working correctly.
local-embedding
Run embedding on-device with ONNX Runtime. Build from source, model selection, offline mode. Use when setting up local embedding without an API key.
dify
Use when building LLM applications with visual workflow — RAG knowledge bases, AI agents, chatbots with drag-and-drop orchestration. Dify: open-source LLM app platform supporting 30+ models (OpenAI, Claude, DeepSeek, Ollama, Qwen, GLM) with Docker deployment.
ai-skills
Use when building LLM applications, RAG knowledge bases, AI agents, terminal coding agents, multi-model orchestration, plugin-based agent harnesses, or file translation. Index of 14 skills: Dify, LangChain, LlamaIndex, Ollama, Transformers, Hermes Agent, OpenClaw, OpenCode, Pi, DocuTranslate, DeepSeek Harness and more.
mcp-builder
Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external agents through well-designed tools. Use when building MCP servers to integrate external APIs or agents, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).
pinecone-research
Agent RAG and long-term memory with Pinecone.