Databases / memo
memo
io.github.jagoff/memo · v4.16.0
Memory for AI agents — MLX (Apple Silicon) or CPU (Linux), sqlite-vec + BM25, zero cloud.
Description supplied by the publisher in the MCP Registry. We have not tested this server.
Install
uvx mlx-memoAssembled from the package metadata in the official MCP Registry (including any subcommand or flag the publisher lists). Some publishers do not list the subcommand that starts MCP mode, so confirm the command in the README, along with any required configuration and credentials, before connecting it to real data.
Signals
| GitHub stars | 21 |
| npm weekly downloads | - |
| Last push | 2d ago |
| Licence | MIT |
| Open issues | 0 |
| SECURITY.md | Yes |
| Language | Python |
| Latest version published | 2026-09-01 |
Signals captured from GitHub, npm and the official MCP Registry on October 15, 2026. See the scoring method.
Similar servers compare all →
Local Memory
Score 80Persistent local AI memory. SQLite + FTS5 + vector search, knowledge graph. No cloud, no API keys.
tinycontext
Score 79Token-light local memory with SQLite hybrid retrieval for MCP agents.
statecore-mcp
Score 78Auditable memory for coding agents: evidence chains, supersession history, keyless embedded SQLite