mairp

Qmd Memory Stack — AI skill for Claude Code

AI community

Local, GPU-accelerated RAG memory for coding agents (Claude Code + OpenClaw) — hierarchical 3-tier memory over local GGUF embeddings + an MCP server.

How to install Qmd Memory Stack

This entry records only its repository, not the path inside it, so there is no exact command to give. Open mairp/qmd-memory-stack and copy the folder into ~/.claude/skills/, or the file into ~/.claude/agents/.

What Qmd Memory Stack does

Local, GPU-accelerated RAG memory for coding agents (Claude Code + OpenClaw) — hierarchical 3-tier memory over local GGUF embeddings + an MCP server.

Alternatives in AI

Nocturne Memory — A lightweight, rollbackable, and visual Long-Term Memory Server for MCP Agents 1.3k ★
Iai Personal Memory Engine — A cyber brain for your AI 866 ★
Wax — Shared Single-file memory layer for all your agents, sub mili-second RAG over text, photo and video on Apple S 791 ★

README

qmd-memory-stack

Local, GPU-accelerated **RAG memory** for coding agents — [Claude Code](https://claude.com/claude-code) and [OpenClaw](https://github.com/) — built on [`qmd`](https://www.npmjs.com/package/@tobilu/qmd) with **fully local Qwen3 GGUF models** (no cloud embeddings) and optional **Intel/NVIDIA GPU offload**.

It gives an agent a hierarchical, retrieval-augmented memory:

L1 — MEMORY.md: a lean always-loaded index of one-line facts.
L2 — topic leaf files (infra/, projects/, …): retrieved on demand via semantic + keyword search.
L3 — sessions (optional): long-form transcripts.

Recall is wired into Claude Code through **hooks** (auto-injected on every prompt) and an **MCP server** (on-demand deep recall), and can **share OpenClaw's memory read-only** so both agents see the same facts.

Why

Private & offline: embeddings/expansion/reranking run on local GGUF models (Qwen3-Embedding-0.6B, a 1.7B query-expansion model, Qwen3-Reranker-0.6B). Nothing leaves the box. Works with providers that have no embeddings endpoint (e.g. Core42 Compass).
Fast where it matters: the always-on auto-inject path is pure BM25 (~0.4s, no model load); heavier semantic/hybrid recall is on-demand. On an Intel Arc iGPU via Vulkan, full hybrid query went 110.7s → 5.7s (~19×) — see docs/OPTIMIZATIONS.md.
Fail-open: memory recall never blocks or breaks a turn (hard timeouts, swallow errors, exit 0).

Quickstart

git clone https://github.com/mairp/qmd-memory-stack.git
cd qmd-memory-stack
./install.sh                       # auto-detects OS, qmd, GPU, memory dir, OpenClaw
# then start a NEW Claude Code session (loads the hooks + MCP server)

Prerequisites on the target machine: **`node`** and the **`qmd`** binary on `PATH` (`npm i -g @tobilu/qmd`), and Claude Code. OpenClaw is optional (auto-detected for the read-only share).

Useful flags: