If you're building an AI agent that has to remember things across sessions, you'll quickly land on the same shortlist: Mem0, Zep, Letta, and — if verifiability matters — Parametric Memory. They solve the same problem in genuinely different ways. Here's an honest comparison, including where each one wins, so you can pick the right tool rather than the loudest one.
The one-line version
- Mem0 — a vector-first memory layer you bolt onto any agent. Fastest path to cross-session personalization; the largest ecosystem.
- Zep — a temporal knowledge graph (Graphiti). Best when facts change over time and you need to know when something was true.
- Letta (formerly MemGPT) — a full agent runtime where the model pages its own memory like an operating system. Best for long-running autonomous agents that self-edit context.
- Parametric Memory — a verifiable memory substrate. The only one where every recalled fact carries a cryptographic proof, delivered MCP-native from $5/mo.
At a glance
| Mem0 | Zep | Letta | Parametric Memory | |
|---|---|---|---|---|
| Architecture | Vector memory layer | Temporal knowledge graph | Agent runtime (self-paging) | Verifiable substrate (Merkle + Markov + graph) |
| Cryptographic proof of memory | No | No | No | Yes — RFC 6962 Merkle |
| Integration | SDK / API | SDK / API | Runtime | MCP-native (one config block) |
| Hosting | OSS core + cloud | Graphiti OSS + cloud | Fully open-source | Managed; dedicated tier from $29 |
| Paid pricing | Pro (graph) ~$249/mo | Flex ~$125/mo | Free / self-host | $5–$79/mo |
| Standard benchmark | LongMemEval 94.4% (self-report) | LongMemEval 63.8% (GPT-4o) | — | Own retrieval + answer benchmark (/benchmark); LongMemEval planned |
| Best for | Personalization, big ecosystem | Time-changing facts | Autonomous self-editing agents | Verifiable cross-session memory over MCP |
Prices and benchmark figures as reported by each vendor / the LongMemEval literature, July 2026.
Where each one wins (honestly)
Choose Mem0 if you want the shortest path to "my chatbot remembers the user," a large integration ecosystem, and you're comfortable that recall is probabilistic. Its self-reported LongMemEval scores lead the pack.
Choose Zep if your domain has facts that change over time — account states, prices, statuses — and your agent needs to reason about when something was true. Its Graphiti temporal graph is purpose-built for that and is open-source.
Choose Letta if you're building a long-running autonomous agent that should manage its own memory — deciding what stays in context and what gets paged out — and you want a fully open-source runtime to self-host.
Choose Parametric Memory if you need memory you can trust and prove, with the least integration work:
- Verifiability no one else offers. Every fact is sealed in an RFC 6962 Merkle tree, so your agent can prove its memory wasn't altered — a hard requirement for regulated, audited, or high-stakes workflows.
- MCP-native, one config block. No SDK, no service to run. It drops into Claude Code, Cursor, Claude Desktop, or any MCP client.
- Graph + prediction included at every price. Knowledge-graph edges and a Markov prediction layer ship on every tier from $5/mo — where comparable graph features sit on $125–$249/mo plans elsewhere.
A note on benchmarks
The category is measured on LongMemEval (Mem0 self-reports 94.4%; Zep 63.8% on GPT-4o). We haven't published a LongMemEval number yet — and we'd rather say so than quote a bespoke figure that isn't comparable. What we have published is an honest, reproducible retrieval and answer-accuracy benchmark on our own production data, including where a well-crafted prompt and keyword RAG tie us. A LongMemEval result is on the roadmap; we'll publish it the same way — with the caveats visible.
Bottom line
There's no single winner — there's a right tool for your constraint. If you want ecosystem, pick Mem0. If you want temporal facts, pick Zep. If you want an autonomous self-hosted runtime, pick Letta. If you want memory you can prove, delivered over MCP without running any infrastructure, that's us — from $5/mo.