96.6% recall on LongMemEval in raw mode. Local-first, open source, and usable without an API key.
Store source text directly instead of extracting facts up front. The raw benchmark result comes from retrieving verbatim content.
Wings and rooms give retrieval useful structure. In the project benchmarks, narrowing search scope outperformed flat search.
ChromaDB-powered vector search lets the model retrieve past discussions by topic, project, or room.
Temporal entity-relationship triples in SQLite. Facts can be added, queried, and invalidated over time.
MCP tools expose search, filing, knowledge graph, graph navigation, and diary operations to compatible clients.
Core storage and retrieval run locally on ChromaDB and SQLite. Optional reranking features can add an API dependency.
MemPalace starts from a simple premise: store the source text and retrieve it well. The benchmarked raw mode does not require an LLM extraction step.
| System | LongMemEval R@5 | API Required | Cost |
|---|---|---|---|
| MemPalace (hybrid) | 100% | Optional | Free |
| Supermemory ASMR | ~99% | Yes | — |
| MemPalace (raw) | 96.6% | None | Free |
| Mastra | 94.87% | Yes | API costs |
| Mem0 | ~85% | Yes | $19–249/mo |
The raw 96.6% LongMemEval result is the baseline story: strong recall without requiring an API key or an LLM in the retrieval pipeline.