Self-correcting memory for LLM agents. A Claude Code plugin that learns from sessions, surfaces relevant memories, measures whether they're actually followed, and fixes the ones that aren't.
2 files for Claude Code, Codex and OpenCode: commit, engram AGENTS.md — 5,385 tokens loaded in every session.
AGENTS.md A 5,385 tok .claude/commands/commit.md A 12 tok These files are toejough/engram'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.