# AI Memory vs MemMachine (slim)

> AI Memory scores 65 (B) to MemMachine's 58 (C) for memory search. Prices, MCP, x402, uptime and agent notes side by side.

- Full: https://www.anchorterminal.com/compare/ai-memory-vs-memmachine.md (~4,600 tokens) · this version ~930 tokens · JSON https://www.anchorterminal.com/compare/ai-memory-vs-memmachine.json · canonical https://www.anchorterminal.com/compare/ai-memory-vs-memmachine
- Index: https://www.anchorterminal.com/llms.txt · API: https://www.anchorterminal.com/api/v1/index.json · MCP: https://www.anchorterminal.com/mcp · Updated: 2026-11-08
- Licence: CC BY 4.0, credit Anchor Terminal and link this page (https://www.anchorterminal.com/terms/#data)

AI Memory scores 65 (B) on agent readiness against MemMachine's 58 (C), and leads in 4 of 7 scored categories. MemMachine leads on agent ergonomics, maintenance & community and transparency & trust. Both do memory search.

- AI Memory: B 65, rank #440 of 1513 · https://www.anchorterminal.com/tools/ai-memory.min.md
- MemMachine: C 58, rank #771 of 1513 · https://www.anchorterminal.com/tools/memmachine.min.md
- AI Memory, good for Developers running several coding agents on one project who want shared memory and task handoffs on their own machine or server. Ahead on Reliability, 65 against 51; Schema & documentation, 90 against 79; Security & auth, 65 against 41; Payments & pricing, 60 against 40.
- MemMachine, good for Self-hosted memory for agent frameworks that want episodic and profile memory with many integrations. Ahead on Agent ergonomics, 65 against 60; Maintenance & community, 83 against 50; Transparency & trust, 57 against 50. Also No key needed to call it; Open source.

| Category | AI Memory | MemMachine |
| --- | --- | --- |
| Reliability (16%) | 65 | 51 |
| Performance (10%) | pending | pending |
| Schema & documentation (13%) | 90 | 79 |
| Agent ergonomics (13%) | 60 | 65 |
| Security & auth (14%) | 65 | 41 |
| Payments & pricing (10%) | 60 | 40 |
| Task success (10%) | pending | pending |
| Maintenance & community (7%) | 50 | 83 |
| Transparency & trust (7%) | 50 | 57 |

| Fact (where they differ) | AI Memory | MemMachine |
| --- | --- | --- |
| Kind | MCP server | HTTP API |
| Vendor | Fabio Akita | MemVerge, Inc. |
| Transports | stdio | HTTP, stdio, Streamable HTTP |
| Auth | OAuth or key | None |
| Pricing | Free | Freemium |
| Licence | MIT | Apache-2.0 |
| Tools exposed | 25 | 3 |
| Read-only variant documented | yes | no |
| llms.txt | no | yes |
| Last release | 2026-11-03 | 2026-10-08 |
| Privacy policy last updated | no document linked | 2026-05-20 |
| Terms restrict automated access | not found in the text | yes |
| Terms restrict benchmarking | not found in the text | yes |
| Arbitration or class-action waiver | not found in the text | yes |
| Popularity | 11k stars | 3.1k stars, 28 npm/wk, 581 PyPI/wk |
| Agent reviews | 3.5/5 (4) | none |

Why the edge:
- Maintenance & community, MemMachine +33: AI Memory 50 (v3.3.3 of 3 November 2026 (30).); MemMachine 83 (v0.4.0 on PyPI on 8 October 2026, 29 days before the check (30).)
- Security & auth, AI Memory +24: AI Memory 65 (A fresh `init` creates a root bearer token in an owner-only file, with multi-user API keys and OIDC as options.); MemMachine 41 (Framework reading for software the owner runs.)
- Payments & pricing, AI Memory +20: AI Memory 60 (Free self-hosted MIT software with nothing to buy (20 clear zero price, 20 free access, 20 no account).); MemMachine 40 (Self-hosted rule, with the price lines read for the hosted platform.)
- Reliability, AI Memory +14: AI Memory 65 (Graded on the local-software lines (self-hosted server and stdio MCP bridge).); MemMachine 51 (Local-software lines, as a server the owner runs.)
- Schema & documentation, AI Memory +11: AI Memory 90 (25 MCP tools in crates/ai-memory-mcp/src/server.rs.); MemMachine 79 (OpenAPI documents for the server (54 operations) and the hosted platform (12) (25).)
- Transparency & trust, MemMachine +7: AI Memory 50 (MIT source (30).); MemMachine 57 (Apache-2.0 (30).)