02 akitaonrails (open source) Open sourceDev toolsAgents

ai-memory 3.1: shared memory for Claude Code, Codex and other coding agents, now with supported Windows install

ai-memory GitHub repository card
Image: GitHub Concept illustration (generated)

What is it?

ai-memory is an MIT-licensed tool that lets more than 20 coding agents, including Claude Code, Codex, Cursor, Gemini CLI and OpenCode, share a single memory. It keeps work history as a plain Markdown wiki and hands off what you were doing, and what already failed, when you switch agents. In 3.1 the Windows install.ps1 and setup service step became production-ready, and switching agents with ai-memory run passes along part of the previous agent's conversation history, locally only.

curl -fsSL https://github.com/akitaonrails/ai-memory/releases/download/v3.1.1/install.sh | AI_MEMORY_VERSION=3.1.1 sh
ai-memory setup

Why does it matter?

If your team re-explains the whole project every time Claude Code hits its usage limit and someone switches to Codex, this is worth a try. The default path makes no LLM calls, and with one shared server teammates can pool project memory. 3.1.1 also adds security fixes that stop OIDC logins and LLM requests from going to non-TLS endpoints or being redirected to another origin.

Maturity

GAStable release. It's a project led by one developer, though, and versions move very quickly.

How to track it

  • Releases: follow GitHub releases for 3.1.x fixes and changes to the desktop installer preview.
  • Security: watch issues and fixes around the privacy boundary for captured hook data.
  • Real-world use: look for reports on the write ceiling (about 700 per secondVendor claim) when it runs as a team server.

More from the same day