Basic Memory vs Everything (reference)
Both are memory & reasoning MCP servers, and we ran both through the same test (recall across sessions) in each app. Basic Memory passed 3 of 3 apps we tested it in; Everything (reference) passed 2 of 2.
Test results side by side
| Basic Memory | Everything (reference) | |
|---|---|---|
| Claude Code | Passed 2026-10-21 | Passed 2026-10-13 |
| Cursor | Passed 2026-10-21 | Passed 2026-10-13 |
| Claude Desktop | Not tested yet | Not tested yet |
| ChatGPT (Codex) | Passed 2026-10-22 | Not tested yet |
| Tools exposed (protocol check) | 21 tools | 13 tools |
| GitHub stars | 4,266 | 91,266 (shared repo) |
| License | AGPL-3.0 | NOASSERTION |
| Last push | 2026-10-16 | 2026-10-13 |
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
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.
Everything (reference): Reference test server from the MCP maintainers that exercises every protocol feature (tools, prompts, resources). Useful for checking a client, not for daily work.
