by jj-valentine · MCP Server · ★ 35
A personal, database-backed memory system that speaks MCP. Any AI tool — Claude, Cursor, ChatGPT, whatever ships next year — queries the same memory store without integration work. One protocol, every engine. Raw thoughts don't go straight to the database. Three layers stand between capture and storage. Quickstart Paste into the Supabase SQL Editor and run it. Then: The [
| Stars | 35 |
| Forks | 4 |
| Language | TypeScript |
| Category | MCP Server |
| License | MIT |
| Quality Score | 66.5155155699442/100 |
| Last Updated | 2026-05-23 |
| Created | 2026-03-06 |
| Platforms | mcp, node |
| Est. Tokens | ~15k |
Explore other popular mcp server tools:
cerebellum is Agent-readable second brain using PostgreSQL + pgvector for semantic search and memory storage.. It is categorized as a MCP Server with 35 GitHub stars.
cerebellum is primarily written in TypeScript. It covers topics such as ai-agents, mcp, personal-knowledge-base.
You can find installation instructions and usage details in the cerebellum GitHub repository at github.com/jj-valentine/cerebellum. The project has 35 stars and 4 forks, indicating an active community.
cerebellum is released under the MIT license, making it free to use and modify according to the license terms.