AI Memory: Shared memory across Claude Code, Codex and other agents
Long-term memory for coding agents stored as shared files, so you can hand work between vendors and machines.
What AI Memory does
AI Memory keeps a shared set of memory files that different coding agents can all read. Start a task in one agent, pick it up in another on a different machine, and it knows what happened.
Why it matters for marketing
If you switch between Claude, Codex and others, this avoids rebuilding context each time and keeps project knowledge in files you own.
How to use AI Memory
- Hand work between agent vendors
- Keep project memory in plain files you control
- Resume work on another machine
What to watch out for
- Shared files need housekeeping
- Overlaps with Claude-Mem; compare before committing
AI Memory FAQ
What is AI Memory?
AI Memory keeps a shared set of memory files that different coding agents can all read. Start a task in one agent, pick it up in another on a different machine, and it knows what happened.
What is AI Memory used for?
Hand work between agent vendors. Keep project memory in plain files you control. Resume work on another machine.
Is AI Memory free and open source?
Yes. The code is public on GitHub at akitaonrails/ai-memory under the MIT license.
Who makes AI Memory?
AI Memory is published on GitHub by akitaonrails. It is written mainly in Rust.
What tools are similar to AI Memory?
Other repos in the Memory and context category include Claude-Mem, Billion Context.