Back to directory

Recall

A fully local, offline memory plugin for Claude Code that keeps an append-only log of each session and condenses it into a compact resume-ready summary using a classical Python summarizer, spending no model tokens.

Recall

Recall gives Claude Code and OpenCode project memory that survives between sessions without calling any model or leaving the local machine. Every session is appended to a history log as it happens, capturing prompts, replies, files touched and commands run, and a separate context summary is rewritten after each session with the current goal, a condensed status, open next steps, and where work left off.

Because the summary is produced by a classical Python text summarizer rather than an additional LLM call, capturing and updating memory costs no model tokens, and resuming from the compact summary instead of re-explaining a project from scratch spends far fewer tokens overall, which matters for people running Claude Code on a metered subscription. It is complementary to hand-written CLAUDE.md instructions and to the built-in session-resume feature, rather than a replacement for either, since neither of those records what actually happened in a session.

It installs as a Claude Code plugin with no pip install, no local model and no API key to configure.

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.