comparison
MemOS vs Mem0 vs Zep vs Letta
Four ways to give an AI agent a memory. This page is written by the MemOS team, so salt accordingly — but the numbers are reproducible from the repo, and we note where competitors don't publish.
| MemOS | Mem0 | Zep | Letta | |
|---|---|---|---|---|
| Where your data lives | SQLite file on your machine | Hosted cloud (platform) or self-managed (OSS library) | Hosted cloud, or community edition self-hosted | Self-hosted server (Postgres-backed) |
| Price | Free — MIT, no paid tier | Free tier capped; $19–$249/mo platform plans | Free tier; paid plans for scale | Open source; managed cloud available |
| Memory model | Graph-native, temporal validity, trust scoring | Fact extraction + graph memory (Pro plan) | Temporal knowledge graph | Memory blocks + archival storage (MemGPT) |
| API keys / account | None | Account + API key for the platform | Account + API key for the cloud | None for self-hosted |
| Embeddings | Local (Gemma-300M) by default | Provider-hosted | Provider-hosted | Configurable |
| MCP integration | Built-in adapter (stdio + HTTP/SSE) | Via integrations | Via integrations | Agent-server centric |
| BEAM-1M recall @10 | 95.9% | 64.1% | not published on BEAM-1M | not published on BEAM-1M |
Pricing and feature details as published on each project's website, August 2026. Mem0 and Zep also publish open-source components; the comparison above covers the hosted platforms most teams actually run.
When to pick what
Pick MemOS when…
You want memory that never leaves the machine, no account or API key, long-horizon recall at production scale, and the freedom to modify the storage layer itself.
Pick a hosted service when…
You need managed infrastructure across a team, don't want to run anything yourself, and the per-month cost is worth the zero-ops trade-off.