Menu

How I made Claude Code, Codex and OpenCode share one memory over MCP
📰

How I made Claude Code, Codex and OpenCode share one memory over MCP

DEV Community: opensource·joexk·about 3 hours ago
#8R5Gk6td
#devtoopensource#devto#dev#agent#facts
Long article (783 words) — no AI summary yet.
Reading 0:00
15s threshold

Claude Code, Codex and OpenCode each start every session knowing nothing about the last one. If I spend an hour with Claude Code working out that the test suite needs Postgres on port 5433, Codex finds that out again the next day, the hard way.

I wanted one memory that all of them read and write, that I can look at myself, and that doesn't need a server or a model call to keep tidy. Here is how I built it in JoeBro , the free, open-source Mac app I make. The Python part is standard library only.

The shape: a local MCP server over SQLite

All three agents speak MCP, so the shared piece is a small MCP server that the app installs into each agent's config. It exposes a handful of tools, mainly memory_remember and memory_recall , plus memory_supersede and memory_forget . Everything lands in one local SQLite file. There is no account and nothing leaves the machine.

Memory is scoped.…

Continue reading — create a free account

Join HashtagPLUS to read full articles, follow hashtags, vote, and join the conversation.