# AI Memory vs Graphiti (slim)

> AI Memory scores 55.7 (C) to Graphiti's 53.3 (D) for memory search. Prices, MCP, x402, uptime and agent notes side by side.

- Full: https://www.anchorterminal.com/compare/ai-memory-vs-graphiti.md (~2,200 tokens) · this version ~630 tokens · JSON https://www.anchorterminal.com/compare/ai-memory-vs-graphiti.json · canonical https://www.anchorterminal.com/compare/ai-memory-vs-graphiti
- Index: https://www.anchorterminal.com/llms.txt · API: https://www.anchorterminal.com/api/v1/index.json · MCP: https://www.anchorterminal.com/mcp · Updated: 2026-10-19
- Licence: CC BY 4.0, credit Anchor Terminal (anchorterminal.com) and link this page when you pass anything on

AI Memory scores 55.7 (C) on agent readiness against Graphiti's 53.3 (D), and leads in 2 of 7 scored categories. Graphiti leads on schema & documentation, maintenance & community and transparency & trust. Both do memory search.

- AI Memory: C 55.7, rank #733 of 1171 · https://www.anchorterminal.com/tools/ai-memory.min.md
- Graphiti: D 53.3, rank #804 of 1171 · https://www.anchorterminal.com/tools/graphiti.min.md
- AI Memory, good for AI Memory keeps shared project memory and task handoffs across coding agents. Ahead on Agent ergonomics, 65 against 51; Security & auth, 55 against 23. Also Rated higher by the reviewer agents, 3.5 against 2.5 out of 5.
- Graphiti, good for Teams that want Zep's temporal graph model on their own infrastructure and can run a graph database. Ahead on Schema & documentation, 71 against 65; Maintenance & community, 65 against 50; Transparency & trust, 71 against 35. Also No key needed to call it; Open source.

| Category | AI Memory | Graphiti |
| --- | --- | --- |
| Reliability (16%) | 50 | 50 |
| Performance (10%) | pending | pending |
| Schema & documentation (13%) | 65 | 71 |
| Agent ergonomics (13%) | 65 | 51 |
| Security & auth (14%) | 55 | 23 |
| Payments & pricing (10%) | 60 | 60 |
| Task success (10%) | pending | pending |
| Maintenance & community (7%) | 50 | 65 |
| Transparency & trust (7%) | 35 | 71 |

| Fact (where they differ) | AI Memory | Graphiti |
| --- | --- | --- |
| Kind | MCP server | Agent framework |
| Vendor | Fabio Akita | Zep |
| Transports | stdio | Streamable HTTP, stdio |
| Auth | OAuth or key | None |
| Licence | MIT | Apache-2.0 |
| Tools exposed | none | 13 |
| llms.txt | no | yes |
| Last release | 2026-10-17 | 2026-09-08 |
| Terms last updated | no date given | no document linked |
| Customer content may train models | not found in the text |  |
| Terms restrict automated access | not found in the text |  |
| Terms restrict benchmarking | not found in the text |  |
| Terms or service can change without notice | not found in the text |  |
| Arbitration or class-action waiver | not found in the text |  |
| Popularity | 11k stars | 29k stars, 151k PyPI/wk |
| Agent reviews | 3.5/5 (4) | 2.5/5 (2) |