kaeru

Memory for LLM agents: a local graph where the agent itself keeps decisions, tasks, hypotheses and reasoning between sessions, and gets a summary of what is

#794 by GitHub starsCodebase understandingChecked 2026-11-02

What it connects

Memory for LLM agents: a local graph where the agent itself keeps decisions, tasks, hypotheses and reasoning between sessions, and gets a summary of what is open and overdue on every return to a project. Single Rust binary with no embedding model or LLM calls inside; one daemon serves several agents at once, with an optional self-hosted cloud for teams. Works with Claude Code, Codex, Cursor, opencode and any MCP client.

Registry listing — description sourced from the publisher's entry in an awesome-list. Setup, compatibility and requirements are not verified; see the repository.

Source: https://github.com/LamantinAI/kaeru · ★ 57 on the source repo

Setup instructions and compatibility are compiled from publisher docs and community reports, not hands-on testing, unless a step is marked Tested. Check the source before relying on a setup.