Skip to content

LuizEduPP/rememb

v0.3.0 Feature

This release adds 3 notable features for engineering teams evaluating rollout.

✓ No known CVEs patched
Read the diff → Tool health → What is this tool? →

✓ No known CVEs patched in this version

Topics

agent-memory ai-agents ai-memories ai-memory cherry-studio claude
+14 more
clawdbot context-persistence copilot cursor fastapi llm llm-memory mcp mcp-server memory model-context-protocol moltbot persistent-memory windsurf

Summary

AI summary

MCP Server Support adds native IDE integration with local semantic search and six memory sections.

Full changelog

What's New

MCP Server Support — Native integration with Windsurf, Cursor, and Claude Desktop. No CLI commands needed, your IDE manages memory automatically.

Installation

pip install rememb[mcp]

Quick Setup

Add to your IDE's MCP config:

{
  "mcpServers": {
    "rememb": {
      "command": "rememb",
      "args": ["mcp"]
    }
  }
}

| IDE | Config file |
|-----|-------------|
| Windsurf | ~/.codeium/windsurf/mcp_config.json |
| Cursor | .cursor/mcp.json |
| Claude Desktop | ~/Library/Application Support/Claude/claude_desktop_config.json |

How it works

  1. Agent starts → automatically calls rememb_read → loads your context
  2. You chat normally
  3. Agent learns something → automatically calls rememb_write → saves to .rememb/

Zero servers. Zero API keys. Your data stays in your project.

Features

  • MCP server for native IDE integration
  • Local semantic search (no cloud calls)
  • Import from .md, .txt, .pdf
  • 6 memory sections: project, actions, systems, requests, user, context

Weekly OSS security release digest.

The CVE patches and breaking changes that affected production tools this week. One email, every Sunday.

No spam, unsubscribe anytime.

Share this release

Track LuizEduPP/rememb

Get notified when new releases ship.

Sign up free

About LuizEduPP/rememb

Persistent memory for AI agents with sectioned entries (project/user/context/etc), semantic search, CLI, and per-project scope. Local JSON, zero config, no server required.

All releases →

Beta — feedback welcome: [email protected]