forgetted is a Python library for selective memory governance in AI agents: a context-managed window where the agent keeps full read access but its writes to memory files, session logs, deliverables, and (optionally) a vector store silently vanish and are cleaned up on exit. Mid-conversation incognito for agents, one with-block. By Hermes Labs.
Latest release v0.2.2 — forgetted v0.2.2 · 4 Aug 2026
2 files for Codex, OpenCode and Claude Code: forgetted AGENTS.md, forgetted CLAUDE.md — 886 tokens loaded in every session.
AGENTS.md A 286 tok CLAUDE.md A 600 tok These files are hermes-labs-ai/forgetted's own configuration — they tell 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.