From c99da84f9c780d4292d74ef8ed365713572326c2 Mon Sep 17 00:00:00 2001 From: Muhammad Arif <101164030+wakbijok@users.noreply.github.com> Date: Thu, 13 Aug 2026 01:35:26 +0800 Subject: [PATCH] docs: mark status quo and point to dm-lite as successor Clarify that daimon-memory is status quo, dm-lite is the successor and primary AI memory focus, and the future of this repo is undecided. --- README.md | 12 +++++++++++- 1 file changed, 11 insertions(+), 1 deletion(-) diff --git a/README.md b/README.md index c15ed4e..b6553d2 100644 --- a/README.md +++ b/README.md @@ -4,12 +4,22 @@ **Persistent typed memory for AI agents. Deterministic, LLM-free recall across every tool.** -![status](https://img.shields.io/badge/status-experimental-orange) ![license](https://img.shields.io/badge/license-MIT-blue) ![rust](https://img.shields.io/badge/rust-edition%202024-orange) +![status](https://img.shields.io/badge/status-status%20quo-lightgrey) ![license](https://img.shields.io/badge/license-MIT-blue) ![rust](https://img.shields.io/badge/rust-edition%202024-orange) --- +## Project status + +**Status quo.** daimon-memory is not receiving primary development focus right now. + +Its successor is **[dm-lite](https://github.com/wakbijok/dm-lite)** (daimon-memory v2): one binary, hybrid keyword + vector recall, and the shared memory engine for Hermes, Codex, Claude Code, and other agents. New AI memory work is focused there. + +The future of this repository is undecided. It remains available and usable as documented below. If you are starting fresh, prefer dm-lite. + +--- + ## What it is daimon-memory is a self-hostable memory backend for AI agents. It stores typed records (decisions, lessons, incidents, reminders, and more) in PostgreSQL as the canonical source, with Qdrant as a rebuildable semantic index. Recall is hybrid keyword + vector search fused by Reciprocal Rank Fusion -- no LLM in the recall path, so it is fast, cheap, and reproducible.