Memory (reference) vs Basic Memory
Both are memory & reasoning MCP servers, and we ran both through the same test (recall across sessions) in each app. Memory (reference) passed 4 of 4 apps we tested it in; Basic Memory passed 3 of 3.
Test results side by side
| Memory (reference) | Basic Memory | |
|---|---|---|
| Claude Code | Passed 2026-10-19 | Passed 2026-10-21 |
| Cursor | Passed 2026-10-19 | Passed 2026-10-21 |
| Claude Desktop | Passed 2026-10-21 | Not tested yet |
| ChatGPT (Codex) | Passed 2026-10-20 | Passed 2026-10-22 |
| Tools exposed (protocol check) | 9 tools | 21 tools |
| GitHub stars | 91,266 (shared repo) | 4,266 |
| License | NOASSERTION | AGPL-3.0 |
| Last push | 2026-10-13 | 2026-10-16 |
Results from our own harness runs, dated per cell. Stars and last push from GitHub at our last data refresh. We don’t pick a winner here: which one fits depends on your app and setup.
What each does
Memory (reference): A simple knowledge-graph memory the agent can add to and search across sessions, stored in a local JSON file.
Basic Memory: Local-first knowledge base over MCP: your agent reads and writes plain Markdown notes on your own disk, so context carries across chats. Optional paid cloud sync.
