Back to directory

project-butler

A project-memory skill for AI coding assistants that saves session logs, a project wiki, rules, and TODOs between sessions, so Claude Code, Cursor, or Codex can resume a project without re-explaining it.

project-butler

project-butler helps Claude Code, Cursor, Codex, and similar AI coding assistants behave like long-term project teammates instead of starting from scratch every session. Four commands cover normal use: setting up project memory, ending a session to save progress and next steps, continuing to resume where the last session left off, and checking status.

For projects that need stronger alignment on product, architecture, roadmap, research, or evaluation, it can create a project profile during setup and offer profile-aware close-out behavior at the end of a session. It checks for updates once a day per machine by comparing the local skill checkout against its own upstream repository, offering to pull a fast-forward update, remind the user later, or stop checking; the check never modifies the working tree unless the user chooses to update.

It installs as a Claude Code skill by cloning into the user's skills directory, and is licensed under MIT.

More in Agent memory

See all 450
  • A long technical guide to AI agent memory: why stateless LLMs need it, the different memory architectures from vector stores to knowledge graphs, and how Cognee implements one as an open-source memory layer.

  • A local, file-based long-term memory layer for a personal AI that never summarizes conversations, keeping every line with a timestamp and searching by time first and words second, rather than retrieving only similar-seeming chunks.

  • NEOTH

    deepwiki.com

    A local-first personal AI daemon in Rust with five memory tiers, consent-gated tools, a WASM plugin sandbox, multi-provider model routing and signed audit logs, aimed at people who want both a daily assistant and a serious coding helper.