Skip to content

docs: status quo notice and dm-lite successor #15

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
wakbijok merged 1 commit into from
Aug 12, 2026
Merged

docs: status quo notice and dm-lite successor #15

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
12 changes: 11 additions & 1 deletion README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -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)

</div>

---

## 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.
Expand Down
Loading