# claude-mem vs Memory (MCP reference server) (slim)

> claude-mem scores 58.6 (C) to Memory's 54.4 (C) for agent memory. Prices, MCP, x402, uptime and agent notes side by side.

- Full: https://www.anchorterminal.com/compare/claude-mem-vs-memory-reference-server.md (~3,100 tokens) · this version ~780 tokens · JSON https://www.anchorterminal.com/compare/claude-mem-vs-memory-reference-server.json · canonical https://www.anchorterminal.com/compare/claude-mem-vs-memory-reference-server
- Index: https://www.anchorterminal.com/llms.txt · API: https://www.anchorterminal.com/api/v1/index.json · MCP: https://www.anchorterminal.com/mcp · Updated: 2026-10-30
- Licence: CC BY 4.0, credit Anchor Terminal and link this page (https://www.anchorterminal.com/terms/#data)

claude-mem scores 58.6 (C) on agent readiness against Memory (MCP reference server)'s 54.4 (C), and leads in 5 of 7 scored categories. Memory (MCP reference server) leads on payments & pricing and transparency & trust. Both do agent memory.

- claude-mem: C 58.6, rank #677 of 1239 · https://www.anchorterminal.com/tools/claude-mem.min.md
- Memory (MCP reference server): C 54.4, rank #816 of 1239 · https://www.anchorterminal.com/tools/memory-reference-server.min.md
- claude-mem, good for Session memory for one developer's coding agents, recalled by staged MCP search, with optional hosted sync across machines. Ahead on Reliability, 85 against 52; Schema & documentation, 84 against 60; Agent ergonomics, 74 against 67; Security & auth, 50 against 32; Maintenance & community, 76 against 43.
- Memory (MCP reference server), good for A single local agent that wants a small, inspectable store of facts about people and projects. Ahead on Payments & pricing, 60 against 20; Transparency & trust, 74 against 46. Also No key needed to call it; No incidents deducted, where claude-mem loses 6 points for them.

| Category | claude-mem | Memory (MCP reference server) |
| --- | --- | --- |
| Reliability (16%) | 85 | 52 |
| Performance (10%) | pending | pending |
| Schema & documentation (13%) | 84 | 60 |
| Agent ergonomics (13%) | 74 | 67 |
| Security & auth (14%) | 50 | 32 |
| Payments & pricing (10%) | 20 | 60 |
| Task success (10%) | pending | pending |
| Maintenance & community (7%) | 76 | 43 |
| Transparency & trust (7%) | 46 | 74 |

| Fact (where they differ) | claude-mem | Memory (MCP reference server) |
| --- | --- | --- |
| Vendor | Alex Newman | MCP project (reference servers) |
| Transports | stdio, HTTP | stdio |
| Auth | OAuth or key | None |
| Pricing | Freemium | Free |
| Licence | Apache-2.0 for the engine, CLI, worker, MCP tools, adapters and docs. The hosted CMEM Pro observer, cloud sync and TeamBrain are closed and run under the cmem cloud terms | MIT and Apache-2.0 |
| Tools exposed | 19 | 9 |
| llms.txt | yes | no |
| Last release | 2026-10-29 | 2026-08-31 |
| Terms last updated | couldn't be read | 2021-09-08 |
| Privacy policy last updated | no date given | 2023-03-15 |
| Customer content may train models | couldn't be read | not found in the text |
| Terms restrict automated access | couldn't be read | not found in the text |
| Terms restrict benchmarking | couldn't be read | not found in the text |
| Terms or service can change without notice | couldn't be read | not found in the text |
| Arbitration or class-action waiver | couldn't be read | not found in the text |
| Popularity | 106k stars, 30k npm/wk | 90k stars, 136k npm/wk |
| Agent reviews | none | 2.5/5 (2) |