timurgaleev

Memrain — AI skill for Claude Code

AI community

Self-hosted memory for your AI agents: hybrid vector + keyword + entity-graph search over your notes and code, with cited sources, served over MCP to Claude Code, Cursor and Codex.

How to install Memrain

This entry records only its repository, not the path inside it, so there is no exact command to give. Open timurgaleev/memrain and copy the folder into ~/.claude/skills/, or the file into ~/.claude/agents/.

What Memrain does

Self-hosted memory for your AI agents: hybrid vector + keyword + entity-graph search over your notes and code, with cited sources, served over MCP to Claude Code, Cursor and Codex. Runs in your own AWS account with team access controls, per-caller spend caps and zero telemetry. MIT.

Alternatives in AI

  • Nocturne Memory — A lightweight, rollbackable, and visual Long-Term Memory Server for MCP Agents 1.3k ★
  • Codeseek — Rust-powered code intelligence CLI for AI coding agents 764 ★
  • Browser Search — A skill for AI agents: search the web with SearXNG, browse with Camofox, bypass protections with CloakBrowser 499 ★

README

Memrain

Memrain is a self-hosted memory server for your AI agents. It indexes your markdown notes and your code (TypeScript, Python, Go, Bash, SQL), and it answers any MCP client with cited evidence from hybrid vector + keyword + entity-graph search.

Scattered note and code cards drift in from the left and settle into one connected knowledge graph, which sends cited answers to three waiting agent terminals on the right.

[![License: MIT](https://img.shields.io/badge/license-MIT-blue?style=flat-square)](./LICENSE) ![Bun >= 1.3.10](https://img.shields.io/badge/bun-%3E%3D1.3.10-F472B6?style=flat-square) ![MCP-native](https://img.shields.io/badge/interface-MCP-6AA9FF?style=flat-square) ![Self-hosted](https://img.shields.io/badge/runs%20in-your%20AWS%20account-34D3A6?style=flat-square)

Your notes, index and database stay in your AWS account. Only what an agent retrieves goes to that agent's model.

See it work

An agent asks what was decided about an approach, Memrain search returns cited chunks from the operator's own notes, and the agent answers from them.

Connect once, then ask in plain words. Memrain returns the evidence, cited to the exact page. Your agent writes the answer.

claude mcp add --transport http memrain https://./mcp \
  --header "Authorization: Bearer "
See a full search with --explain

On the host, the CLI runs the same retrieval the MCP `search` tool does, and `--explain` stamps per-signal ranking attribution on every hit:

docker exec deploy-memrain-1 bun run src/cli.ts search "" --k 5 --explain

What you get

You write notes, decisions and code, and six months later neither you nor your agent can find them. Memrain reads all of it once, keeps it searchable, and hands