A local-first, LLM-agnostic memory layer for AI assistants
Latest release @psraghuveer/[email protected] · 17 May 2026
3 files for GitHub Copilot, Codex, OpenCode and Claude Code: memento copilot-instructions.md, memento AGENTS.md, memento CLAUDE.md — 4,591 tokens loaded in every session.
.github/copilot-instructions.md A 744 tok AGENTS.md A 3,844 tok CLAUDE.md A 3 tok These files are veerps57/memento's own configuration — they tell GitHub Copilot, Codex, OpenCode and Claude Code 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.