Sequentialthinking (reference) vs MemPalace
Both are memory & reasoning MCP servers, and we ran both through the same test (recall across sessions, stepwise reasoning) in each app. Sequentialthinking (reference) passed 4 of 4 apps we tested it in; MemPalace passed 3 of 3.
Test results side by side
| Sequentialthinking (reference) | MemPalace | |
|---|---|---|
| Claude Code | Passed 2026-10-20 | Passed 2026-10-22 |
| Cursor | Passed 2026-10-20 | Passed 2026-10-22 |
| Claude Desktop | Passed 2026-10-14 | Not tested yet |
| ChatGPT (Codex) | Passed 2026-10-21 | Passed 2026-10-22 |
| Tools exposed (protocol check) | 1 tools | 47 tools |
| GitHub stars | 91,266 (shared repo) | 59,654 |
| License | NOASSERTION | MIT |
| Last push | 2026-10-13 | 2026-10-20 |
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
Sequentialthinking (reference): A scratchpad tool that lets the agent break a problem into numbered, revisable thoughts.
MemPalace: Free, open-source long-term memory system for AI assistants, with an MCP server so agents can save and recall what they learned.
