Claude-Mem: Long-term memory shared across your coding agents
Captures what your agent does in each session and makes it available to future sessions and other agents, so you stop re-explaining context.
What Claude-Mem does
Claude-Mem records what happens during your agent sessions, compresses it, and feeds the relevant parts back in later. It works across sessions and across tools, so work you did in one agent can inform another.
Why it matters for marketing
Every re-explained brief is wasted time and tokens. Persistent memory means an agent remembers your brand rules, past campaign decisions and project history without you pasting them in each time.
How to use Claude-Mem
- Keep brand, voice and project context across sessions
- Hand work between agents without losing history
- Cut tokens spent re-explaining the same background
What to watch out for
- Stored memory can carry stale or wrong context forward, so prune it
- Decide what you're comfortable storing before pointing it at sensitive work
Claude-Mem FAQ
What is Claude-Mem?
Claude-Mem records what happens during your agent sessions, compresses it, and feeds the relevant parts back in later. It works across sessions and across tools, so work you did in one agent can inform another.
What is Claude-Mem used for?
Keep brand, voice and project context across sessions. Hand work between agents without losing history. Cut tokens spent re-explaining the same background.
Is Claude-Mem free and open source?
Yes. The code is public on GitHub at thedotmack/claude-mem under the Apache-2.0 license.
Who makes Claude-Mem?
Claude-Mem is published on GitHub by thedotmack. It is written mainly in TypeScript.
What tools are similar to Claude-Mem?
Other repos in the Memory and context category include AI Memory, Billion Context.