Comparison
hippo vs mem0
Both are open-source memory for AI agents. The difference is philosophy. mem0 saves and searches: it extracts facts and retrieves them by similarity. hippo runs a memory lifecycle: it forgets by default and earns persistence through use, so the store stays small and current instead of growing without bound.
Feature comparison
| Feature | hippo | mem0 |
|---|---|---|
| Core model | Memory lifecycle: forget by default | Save everything, search later |
| Decay by default | Yes | No |
| Retrieval strengthening | Yes | No |
| Reward-proportional decay | Yes | No |
| Conflict detection + resolution | Yes | No |
| Search | BM25 + optional embeddings | Embeddings only |
| Zero runtime dependencies | Yes | No |
| Storage | Local SQLite + markdown | Vector store |
| MCP server | Yes | No |
| License | MIT | Apache-2.0 |
Feature rows are from hippo's comparison table. mem0 reports its own LongMemEval figures under its own conditions; hippo's per-haystack results are on the benchmarks page.
When to choose which
Choose hippo You want the store to stay small and current over time, local-first with no cloud or account, zero runtime dependencies, and a memory that forgets the noise and keeps what gets used.
Choose mem0 You mainly want to extract, store, and search facts, and a hosted or vector-store-backed setup fits your stack.