What the agent still knows tomorrow.
| Option | What it does | Licence | Self-host |
|---|---|---|---|
| Mem0 | Extracts durable facts from conversations and recalls them on the next turn. | Open source | Yes |
| Zep | Temporal knowledge graph memory — facts with validity windows, not just embeddings. | Open source | Yes |
| Honcho | Treats memory as a reasoning problem, not a retrieval one — you ask its Dialectic API a question about the user and get a synthesised answer. | Open source | Yes |
| Supermemory | Memory graph plus automatic user profiles, with connectors that sync from Drive, Gmail, Notion and GitHub. | Proprietary | No |
| LangMem | Memory primitives that plug straight into LangGraph checkpoints. | Open source | Yes |
| Cognee | Builds a graph + vector memory layer over your agent's history and documents. | Open source | Yes |
| Postgres (rolled by hand) | A messages table and a summaries table. Boring, auditable, yours. | Open source | Yes |
Only figures with a published source appear here. A blank cell means nobody has published one for that pairing — which, for most of this category, is the honest answer.
| Benchmark | Mem0 | Zep | LangMem | Letta |
|---|---|---|---|---|
| LoCoMoQuestion-answering accuracy over long, multi-session conversations. | 92.5%self-reported62.47%independent | 79.09%independent58.44%independent | 78.05%independent | 83.2%self-reported |
LoCoMo. Treat every figure here as contested. Most headline LoCoMo numbers are produced by the vendor being measured, and independent re-runs have differed from vendor claims by as much as 30 points on the same benchmark name. The spread between rows is the story, not the winner.
What the agent still knows tomorrow. It is optional; plenty of working agents skip it.
This registry tracks 7. 6 are open source and 6 can run on your own infrastructure.
It depends on constraints rather than preference: whether you must self-host, whether the budget allows a hosted service, and which language your team writes. Describe what you are building and the advisor fills this layer along with the other 9.
Every page here answers to Accept: text/markdown and returns the same content at roughly a tenth the tokens. No separate site, no toggle — same URL.
curl -s -H "Accept: text/markdown" https://newagent.build/layers/memory