goldenwo/universal-memory

Self-hosted, markdown-first memory for LLM agents across devices and sessions

Latest release v1.30.0 · 29 Oct 2026

1 file for Claude Code, Codex and OpenCode: universal-memory AGENTS.md — 221 tokens loaded in every session.

Open on GitHub

2Stars on the repository

1Files it configures its agents with

221Tokens loaded in every session

3Agents configured

Instructions

universal-memory AGENTS.md AGENTS.md A 221 tok

These files are goldenwo/universal-memory's own configuration — they tell Claude Code, Codex and OpenCode how to work on this repository, so they are not mods to install elsewhere. Copy one as a starting point and replace the parts that are about this project.