---
title: "Deploy Brainkeep"
description: "Shared memory for AI agents and teams: MCP server with a web panel"
category: "AI/ML"
url: https://railway.com/deploy/brainkeep
---

# Deploy Brainkeep

Shared memory for AI agents and teams: MCP server with a web panel

**[Deploy Brainkeep on Railway](https://railway.com/template/brainkeep)**

Machine-readable deploy manifest (JSON, validated by TemplateCI): https://railway.com/deploy/brainkeep/manifest.json

- **Creator:** Ale Depaoli Gampel's Projects
- **Category:** AI/ML
- **Total deploys:** 2

## Template content

### Brainkeep https://brainkeep.dev/favicon.svg

- **Source:** https://github.com/aledepaoligampel/brainkeep
- **Public domain:** Yes

## Documentation

# Deploy and Host brainkeep on Railway

Brainkeep is shared, user-controlled memory for AI agents: a small MCP server (Rust + SQLite) that Claude Code, claude.ai, Codex or any MCP client uses to save and recall decisions, discoveries, progress and links across sessions, tools and people, with revision history and verified authorship.

## About Hosting brainkeep

One container serves MCP at `/mcp` and a web panel at `/panel`. Memories and generated credentials live in a volume mounted at `/data`, so restarts and redeploys keep them. On first start the server generates its internal keys. Sign in to `/panel` with `PANEL_ADMIN_KEY`, which the template generates and you can copy from the service's Variables tab, then invite your team by email: each person gets the MCP URL and a personal token. Keep a single replica, because one process owns the SQLite database.

## Common Use Cases

- Give a team's coding agents one shared memory of decisions, discoveries and progress
- Connect claude.ai as an organization connector with Google sign-in
- Share projects read-only or read-write, with full history and instant revocation

## Dependencies for brainkeep Hosting

- A volume mounted at `/data` (included in the template)
- Optional: a Google OAuth client for Google sign-in (`GOOGLE_CLIENT_ID`, `GOOGLE_CLIENT_SECRET`)

### Deployment Dependencies

- Source code: https://github.com/aledepaoligampel/brainkeep
- Railway guide: https://github.com/aledepaoligampel/brainkeep/blob/main/docs/railway.md
- Connecting clients: https://github.com/aledepaoligampel/brainkeep/blob/main/docs/clients.md

### Implementation Details

Login rate limits use `X-Real-IP`, which Railway's edge sets to each client's address. For Google sign-in, set the OAuth redirect URI to `https:///oauth/google/callback`.

## Why Deploy brainkeep on Railway?


Railway is a singular platform to deploy your infrastructure stack. Railway will host your infrastructure so you don't have to deal with configuration, while allowing you to vertically and horizontally scale it.

By deploying brainkeep on Railway, you are one step closer to supporting a complete full-stack application with minimal burden. Host your servers, databases, AI agents, and more on Railway.


## Similar templates

- [Chat Chat](https://railway.com/deploy/-WWW5r) — Chat Chat, your own unified chat and search to AI platform.
- [Weaviate](https://railway.com/deploy/weaviate-1) — Vector database with hybrid search and an API key-protected API
- [Möbius Personal AI OS](https://railway.com/deploy/mobius-v01-personal-ai-os) — Self-hosted AI agent that builds and runs apps for you, with memory.

Open this page in a browser: https://railway.com/deploy/brainkeep
