memstate-ai/memstate-mcp

**Versioned memory for AI agents.** Store facts, detect conflicts, and track how decisions change over time — exposed as a hosted MCP server.
Dashboard · Docs · Pricing
---
Why Memstate?
| | RAG (most other memory systems) | Memstate AI |
|---|---|---|
| Token usage per conversation | ~7,500 | ~1,500 |
| Agent visibility | Black box | Full transparency |
| Memory versioning | None | Full history |
| Token growth as memories scale | O(n) | O(1) |
| Infrastructure required | Yes | None — hosted SaaS |
Other memory systems dump everything into your context window and hope for the best. Memstate gives your agent a **structured, versioned knowledge base** it navigates precisely — load only what you need, know what changed, know when facts conflict.
---
Benchmarks
We built an open-source benchmark suite that tests what actually matters for agent memory: can your system store facts, recall them accurately across sessions, detect conflicts when things change, and maintain context as a project evolves?
Head-to-Head: Memstate AI vs Mem0
Both systems were tested under identical conditions using the same agent (Claude Sonnet 4.6, temperature 0), the same scenarios, and the same scoring rubric.
| Metric | Memstate AI | Mem0 | Winner |
|--------|:-----------:|:----:|--------|
| **Overall Score** | **69.1** | 15.4 | Memstate |
| Accuracy (fact recall) | 74.1 | 12.6 | Memstate |
| Conflict Detection | 85.5 | 19.0 | Memstate |
| Context Continuity | 63.7 | 10.1 | Memstate |
| Token Efficiency | 22.3 | 30.6 | Mem0 |
*Scoring weights: Accuracy 40%, Conflict Detection 25%, Context Continuity 25%, Token Efficiency 10%.*
Per-Scenario Breakdown
The benchmark runs five real-world scenarios that simulate multi-session agent workflows:
| Scenario | Memstate AI | Mem0 |
|----------|:-----------:|:----:|
| Web App Architecture Evolution | 43.2 | 55.6 |
| Auth System Migration | 66.2 | 10.2 |
| Database Schema Evolution | 72.7 | 7.0 |
| API Versioning Conflicts | 86.5 | 0.9 |
| Team Decision Reversal | 77.2 | 3.3 |
Mem0 won the first scenario (simple architecture tracking), but struggled severely on scenarios requiring contradiction handling, cross-session context, and decision reversal tracking — scoring near zero on three of five scenarios.
Why Memstate Wins
The benchmark reveals a fundamental architectural difference:
**Mem0 uses embedding-based semantic search.** Facts are chunked, embedded, and retrieved by similarity. This works for simple lookups but breaks down when:
- Facts contradict earlier facts (the system can't distinguish current vs. outdated)
- Precise recall is needed (embeddings return "similar" results, not exact ones)
- Write-to-read latency matters (new memories take seconds to become searchable)
**Memstate uses structured, versioned key-value storage.** Every fact lives at an explicit keypath with a full version history. This means:
- **Conflict detection is built in** — when a new fact contradicts an old one, the system knows and preserves both versions
- **Recall is deterministic** — you get back exactly what was stored, not an approximate match
- **Cross-session continuity is reliable** — the agent navigates a structured tree rather than hoping semantic search surfaces the right context