Open source
ai-memory
Source: akitaonrails/ai-memory · ★ 3019 · Rust
Last updated 2026-08-19 · benchmark checked 2026-11-04 · unchanged since 2026-09-23 — deterministic & reproducible
Solution for long term memory for agent coding CLIs and to facilitate handoff between different agent vendors
ai-memory at a glance
ai-memory is a tool that gives AI coding assistants a shared, long-term memory so a developer can switch between different AI coding agents (or hand off work to a teammate) without re-explaining the project's context.
Good for
- Switching from one AI coding agent to another mid-task without losing context on what was tried and what is still open
- Teams who want everyone's AI coding agents to share project knowledge while keeping personal work notes private
- Developers who move between machines (laptop, homelab server) and want the same project memory available everywhere
- People who want agent memory to work without sending data to an LLM API or needing an API key
Questions people ask
What AI coding tools does ai-memory work with?
It works with more than twenty coding agent harnesses, including Claude Code, Codex, Cursor, Gemini CLI, OpenCode, Grok, Devin, Kimi, and Kiro.
Do I need an API key or LLM subscription to use it?
No. The default path for capturing, searching, and handing off memory uses zero LLM calls and works with no API key.
Where does my memory actually get stored?
It's stored as plain markdown files in a git-backed wiki that you can open, edit, or search directly; the database is just a derived index that can be rebuilt from those files.
Can a whole team share the same memory?
Yes. Pointing everyone at one server lets project knowledge be shared across the team, while personal handoffs stay private to each person; multi-user authentication, per-person attribution, and an audit log are included and not a paid tier.
Does it send my data anywhere outside my control?
Memory lives on a server you run yourself, such as your own laptop or a homelab box, and when using ai-memory run to start another agent, the remote server only receives the harness and session identity, not the local transcript.
Written by Legit.Show from github.com on 2026-11-17. It does not change the score.
Are you the maker of ai-memory? Claim this listing. It is free, takes a meta tag, a DNS record or GitHub admin rights, and never changes the score.
Launched something? Add your product, free.
To cite this score: legit.show/s/gh-akitaonrails-ai-memory/2026-11-04. That address never changes; this page moves with every re-measure.
Legit.Show scored ai-memory 63/100 on 2026-11-04, measured across 3 of 7 frames from its public surface. legit.show/s/gh-akitaonrails-ai-memory/2026-11-04
Is ai-memory production-ready?
Legit.Show scores ai-memory 63 out of 100 — the simple average of its 3 measured frames. Legit.Show ran its deterministic 7-Frame production-readiness benchmark on ai-memory (github assessment), measured from the public surface with no LLM in the scoring path. Its strongest frame is Security; its weakest is Discoverability. 3 of the seven frames returned a score; Performance, Accessibility, Privacy and Reliability were not measurable on this service and are recorded as null — not as zero. Maintenance is an additional frame from the open-source teardown, scored separately from the seven. Every frame it averages is published with its evidence on the Legit.Show listing.
The 7 Frames
- Performance — not measurable on this service (null — not scored as 0)
- Accessibility — not measurable on this service (null — not scored as 0)
- Security — 80/100How this compares across the catalogue: The Web Security Baseline
- Privacy — not measurable on this service (null — not scored as 0)
- Reliability — not measurable on this service (null — not scored as 0)
- Standards — 75/100
- Discoverability — 35/100
Open-source teardown
Scored separately — not one of the seven.
- Maintenance — 100/100
What we measured
- No Content-Security-Policy and no HSTS.
- No privacy policy found.
- Sets cookies / loads scripts with no consent prompt.
Who built it
Fabio Akita (@AkitaOnRails)
Sources and updates
- Description
- Taken from github.com's own website on 2026-08-19.
- Code
- github.com/akitaonrails/ai-memory.
- Benchmark
- Measured by Legit.Show from the live site, the way any visitor sees it — with no access to its code or accounts. Same method for every product, and no AI decides the score. Last checked 2026-11-04.
Put together from public information, without ai-memory's involvement. If anything here is wrong, tell us and a person will check it.