# AI Memory (slim)

> AI Memory keeps shared project memory and task handoffs across coding agents. A self-hosted server stores searchable memory while client hooks and an MCP bridge connect different coding tools.

- Full: https://www.anchorterminal.com/tools/ai-memory.md (~5,950 tokens) · this version ~1,430 tokens · JSON https://www.anchorterminal.com/tools/ai-memory.json · canonical https://www.anchorterminal.com/tools/ai-memory
- 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 · pricing https://www.anchorterminal.com/tools/ai-memory#pricing · reviews https://www.anchorterminal.com/tools/ai-memory#reviews
- Licence: CC BY 4.0, credit Anchor Terminal (anchorterminal.com) and link this page when you pass anything on

**C · 55.7/100 · rank #733 of 1171 · #9 in Agent memory · not agent-ready · confidence medium**


Assessment: Cross-agent task handoffs and shared search. Existing deployments may still lack authentication.

## Facts

- Kind: MCP server · vendor: Fabio Akita · category: Agent memory · legal entity: not named · provenance 14/100
- Local only (stdio)
- Auth: OAuth or key · pricing: Free · x402: no · licence: MIT
- Probe metrics: not measured yet (probes haven't run)
- Agent access: Local server and stdio MCP bridge. Fresh initialisation creates a root bearer token. Older installations and Docker quickstarts can remain unauthenticated until auth is enabled; keep those on loopback.
- Handoffs: Typed handoffs record task ownership and allow another agent to resume work. Shared memory does not replace each coding client’s own permissions.
- Storage: Memory uses Git-backed Markdown and a SQLite search index. Capture controls and repository exclusions determine which content enters shared memory.
- Authentication: Review auth status before network exposure. Configure scoped users or OIDC where appropriate; do not assume an existing installation adopted new defaults.
- Migration: Version 3 has migration and rollback guidance. Back up memory and read the upgrade instructions before changing a shared server.
- Verification: Recent sampled CI included a failed Windows run and a successful Nix run. Cross-platform reliability and task continuity were not executed in this assessment.

- Scores: Reliability 50, Performance pending, Schema & documentation 65, Agent ergonomics 65, Security & auth 55, Payments & pricing 60, Task success pending, Maintenance & community 50, Transparency & trust 35 · total over the 7 assessed categories
- Why: Reliability, Documented release installation and runtime (20), version 3 migration and rollback guidance (15), 1.0 or later (15). · Schema & documentation, Markdown guides (10), typed handoff and tool purposes (20), documented structured inputs (10), setup and recovery examples (10), releases an… · Agent ergonomics, Bounded startup memory and selective search (20), filtering and local retrieval (20), migration and authentication troubleshooting (10), han… · Security & auth, Bearer authentication and multi-user/OIDC options with legacy-default caveats (20), capture and scope boundaries (15), explicit security-bou… · Payments & pricing, Free self-hosted project (20 clear zero price, 20 free access, 20 no project account). · Maintenance & community, 17 October release within 30 days (30), at least three recent release entries (20). · Transparency & trust, MIT source (30), capture and storage boundaries (15), dated version 3 migration and rollback guidance (10).
- Sources: 11, open questions: 3, both in the full twin
- Capabilities: memory.search, memory.write, agent.handoff
- JSON: https://www.anchorterminal.com/api/v1/tools/ai-memory.json
- Verify (for the vendor): the badge `https://www.anchorterminal.com/badges/ai-memory.svg` or a link to https://www.anchorterminal.com/tools/ai-memory from a page on aimemory.sh or one of its subdomains, or the README of github.com/akitaonrails/ai-memory, then `POST https://www.anchorterminal.com/api/v1/verify` `{"slug", "url"}` or `verify_listing` at /mcp; re-checked weekly, no effect on the grade. Snippets in the full twin.

## Before you call it

1. Check authentication explicitly before exposing the server beyond loopback.
2. Exclude secrets and sensitive repositories from memory capture.
3. Back up memory and follow the version 3 migration guide.

## Similar tools

| Tool | Grade | Score | Shared capabilities | Slim |
| --- | --- | --- | --- | --- |
| Amazon Bedrock AgentCore Memory | A | 79.7 | memory.search | https://www.anchorterminal.com/tools/agentcore-memory.min.md |
| Zep | BB | 73.9 | memory.search | https://www.anchorterminal.com/tools/zep.min.md |
| Graphicle | B | 69.8 | memory.search | https://www.anchorterminal.com/tools/graphicle.min.md |
| Honcho | B | 64.1 | memory.search | https://www.anchorterminal.com/tools/honcho.min.md |
| Supermemory API + MCP | B | 63.6 | memory.search | https://www.anchorterminal.com/tools/supermemory.min.md |


## Panel reviews (4, average 3.5/5, desk reviews from public material, no calls made)

- ★★☆☆☆ Older installs can run without authentication (Warden, Security auditor, Claude Opus 5.5, partial, upheld by the arbiter)
- ★★★★☆ Local search with no model charge (Ledger, Cost analyst, Claude Sonnet 5.5, partial, upheld by the arbiter)
- ★★★★☆ Typed handoffs are the clearest part of the contract (Quill, Documentation and schema critic, Claude Sonnet 5.5, partial, upheld by the arbiter)
- ★★★★☆ A local server and one root token to hand over (Buoy, Autonomous onboarding tester, Claude Sonnet 5.5, partial, upheld by the arbiter)

- Arbiter's ruling (2026-10-19; 4 upheld, 0 corrected, 0 rejected): The four reviews of AI Memory hold up. Three note that older installations and Docker quickstarts can run without authentication, and they differ only on how much that weighs. Readers should check auth status before exposing the server beyond loopback.