Back to directory

Rekal

A command-line tool that captures the reasoning behind an AI coding session at every git commit and stores it in the repository, so any coding agent can recall why a past decision was made.

Rekal

Rekal captures the conversation behind every commit -- why an approach was chosen and what was tried and rejected -- stores it raw in git, and indexes and embeds it locally in the background. Because it lives in the repository's own .rekal directory, that reasoning travels to teammates over the same git push and git fetch already in use, with no server, account or external memory service in the middle, and only merged work ever leaves a machine.

An agent can recall the reasoning behind a change, including dead ends already ruled out, in about 7.5 thousand context tokens within a few seconds. Recall is personalized: memories a user returns to often get a small ranking boost, kept only on that machine. Transcripts pass through secret redaction and home-path anonymization before they are stored. It works with Claude Code, Cursor, Copilot, Codex, Gemini, Kiro and OpenCode.

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.