# AI Memory vs Beacon (slim)

> Beacon scores 70.8 (BB) to AI Memory's 68.8 (B) for memory search. Prices, MCP, x402, uptime and agent notes side by side.

- Full: https://www.anchorterminal.com/compare/ai-memory-vs-beacon-sh.md (~4,550 tokens) · this version ~880 tokens · JSON https://www.anchorterminal.com/compare/ai-memory-vs-beacon-sh.json · canonical https://www.anchorterminal.com/compare/ai-memory-vs-beacon-sh
- Index: https://www.anchorterminal.com/llms.txt · API: https://www.anchorterminal.com/api/v1/index.json · MCP: https://www.anchorterminal.com/mcp · Updated: 2026-11-18
- Licence: CC BY 4.0, credit Anchor Terminal and link this page (https://www.anchorterminal.com/terms/#data)

Beacon scores 70.8 (BB) on agent readiness against AI Memory's 68.8 (B), and leads in 4 of 7 scored categories. AI Memory leads on schema & documentation and payments & pricing. Both do memory search.

- AI Memory: B 68.8, rank #366 of 1557 · https://www.anchorterminal.com/tools/ai-memory.min.md
- Beacon: BB 70.8, rank #290 of 1557 · https://www.anchorterminal.com/tools/beacon-sh.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 Schema & documentation, 90 against 77; Payments & pricing, 90 against 75.
- Beacon, good for Developers running several coding-agent harnesses who want one local record of sessions and a reviewed memory their agents can recall. Ahead on Reliability, 78 against 65; Maintenance & community, 68 against 50; Transparency & trust, 68 against 50. Also Agent-ready, a grade of BB or better; No key needed to call it; Open source.

| Category | AI Memory | Beacon |
| --- | --- | --- |
| Reliability (16%) | 65 | 78 |
| Performance (10%) | pending | pending |
| Schema & documentation (13%) | 90 | 77 |
| Agent ergonomics (13%) | 60 | 63 |
| Security & auth (14%) | 65 | 64 |
| Payments & pricing (10%) | 90 | 75 |
| Task success (10%) | pending | pending |
| Maintenance & community (7%) | 50 | 68 |
| Transparency & trust (7%) | 50 | 68 |

| Fact (where they differ) | AI Memory | Beacon |
| --- | --- | --- |
| Vendor | Fabio Akita | Asymptote Labs |
| Auth | OAuth or key | None |
| Pricing | Free | Freemium |
| Tools exposed | 25 | 11 |
| llms.txt | no | yes |
| Last release | 2026-11-03 | 2026-11-18 |
| Terms last updated | no date given | 2026-10-15 |
| Privacy policy last updated | no document linked | 2026-10-15 |
| Customer content may train models | not found in the text | yes, with an opt-out |
| 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 | 3.6k stars |
| Agent reviews | 3.5/5 (4) | none |

Why the edge:
- Maintenance & community, Beacon +18: AI Memory 50 (v3.3.3 of 3 November 2026 (30).); Beacon 68 (v1.3.64 on 18 November 2026 (30).)
- Transparency & trust, Beacon +18: AI Memory 50 (MIT source (30).); Beacon 68 (MIT, an OSI licence (30).)
- Payments & pricing, AI Memory +15: AI Memory 90 (Free self-hosted MIT software with nothing to buy (20 clear zero price, 20 free access, 20 no account).); Beacon 75 (Self-hosted rule, with the price lines read for Beacon Cloud.)
- Reliability, Beacon +13: AI Memory 65 (Graded on the local-software lines (self-hosted server and stdio MCP bridge).); Beacon 78 (Local-software lines, as a CLI and stdio MCP server the owner runs.)
- Schema & documentation, AI Memory +13: AI Memory 90 (25 MCP tools in crates/ai-memory-mcp/src/server.rs.); Beacon 77 (Every one of the 11 tools has a typed JSON Schema input, and the intel tools set additionalProperties false (25).)
