Skip to content
botshub
Visit Crbro Memory

Local, persistent memory for AI agents (MCP server). Plain JSON on your disk; fact-level search with an optional local semantic layer; corrections replace old facts; stale-value warnings; secrets kept out; a browser page to read, edit and merge it.

About Crbro Memory

CRBRO is a local MCP server that gives AI assistants memory that persists between sessions, published by the GitHub account Octonove. The README says memory is stored as plain JSON on your own disk, with fact-level search and an optional local semantic layer. It aims to keep decisions, deployment details and open items available later, and to replace outdated facts when you correct them rather than keep both versions.

The README lists 15 MCP tools, including ones to recall, learn, revise, forget and consolidate memory, and one that audits stored content for credentials. It also describes a local browser page for editing entries and team sharing through git. It needs Node.js 20 or later, though the Claude Desktop bundle does not, and a Docker option exists. The README says installing the server alone does not make an assistant read the memory, so a separate step is needed for that. It is MIT licensed, and the benchmark figures are the author's own.

Key features

  • 15 MCP memory tools
  • Plain JSON stored locally
  • Corrects outdated facts instead of duplicating
  • Credential audit and keychain use
  • Local browser editor for memory

More browser & scraping MCP servers

  • Browser & scraping

    The Apify MCP server enables your AI agents to extract data from social media, search engines, maps, e-commerce sites, or any other website using thousands of ready-made scrapers, crawlers, and automation tools available on the Apify Store.

    16K GitHub starsTypeScriptMIT
  • Chrome DevTools MCP

    ChromeDevTools

    Browser & scraping

    Chrome DevTools for agents (chrome-devtools-mcp) lets your coding agent (such as Antigravity, Claude, Cursor or Copilot) control and inspect a live Chrome browser.

    57K GitHub starsTypeScriptApache-2.0
  • Fetch MCP Server

    modelcontextprotocol

    Browser & scraping

    A Model Context Protocol server that provides web content fetching capabilities. This server enables LLMs to retrieve and process content from web pages, converting HTML to markdown for easier consumption.

    92K GitHub stars
  • Browser & scraping

    Official Firecrawl MCP Server - Adds powerful web scraping and search to Cursor, Claude and any other LLM clients.

    7.8K GitHub starsJavaScriptMIT
  • mcp-playwright

    executeautomation

    Browser & scraping

    The Playwright MCP Server provides browser automation capabilities using Playwright, enabling LLMs to interact with web pages, take screenshots, generate test code, and execute JavaScript in a real browser environment.

    5.7K GitHub starsTypeScriptMIT
  • Browser & scraping

    The MCP Server provides cloud browser automation capabilities using Browserbase and Stagehand. It enables LLMs (Large Language Models) to interact with web pages, extract information, and perform automated actions, making it a useful tool for developing AI-powered applications.

    3.4K GitHub starsTypeScriptApache-2.0
Report this listing
Is this your project? Claim this listing