QMD

Overview

QMD is a search and retrieval concept referenced as a memory or knowledge index used to surface information from a large personal or operational knowledge base. In the newsletter mentions, it appears in two practical contexts: as a QMD-based memory index for OpenClaw’s Felix agent, and as the search layer Ryan Wiggs used to ingest roughly 5 million words of past PM work into Claude Code. In both cases, QMD functions less like a standalone end-user app and more like retrieval infrastructure that helps AI systems find relevant prior knowledge when generating outputs or taking action.

For AI Product Managers, QMD matters because it represents a recurring pattern in modern AI products: the value is not just in the model, but in the system that lets the model access the right context at the right time. Whether framed as a “second brain,” memory index, or retrieval layer, QMD points to an important product design principle: durable, searchable knowledge stores can dramatically improve agent quality, personalization, and workflow leverage.

Key Developments

• 2026-02-23: QMD is mentioned in Nat Eliason’s OpenClaw workflow as a QMD-based memory index powering Felix, alongside APIs, cron jobs, and operational tooling. This positions QMD as part of an autonomous agent stack where memory retrieval supports execution.
• 2026-04-23: Ryan Wiggs describes using QMD search to ingest five years of PM work—about 5 million words—into Claude Code, creating a “second brain” that reportedly doubled his productivity. This highlights QMD as retrieval infrastructure for large-scale personal knowledge augmentation.

Relevance to AI PMs

• Design better retrieval-backed AI products: QMD illustrates the importance of a memory layer behind agents and copilots. AI PMs should think beyond model choice and define how user notes, docs, tickets, decisions, and past work are indexed, searched, and retrieved.
• Turn historical artifacts into product leverage: The Ryan Wiggs example shows how years of PM output can become reusable context. AI PMs can apply this by structuring product specs, research notes, meeting summaries, and roadmap decisions into searchable corpora for internal copilots.
• Evaluate memory as a product capability: QMD suggests that persistent memory can be a core differentiator for agent products. PMs should specify retrieval quality metrics, freshness requirements, privacy boundaries, and workflows for updating the underlying knowledge base.

Related

• Nat Eliason: Referenced QMD in the context of OpenClaw’s Felix agent, where it served as part of a memory-enabled autonomous business workflow.
• OpenClaw: An agent framework/workflow environment where QMD appears to function as a memory index supporting agent actions and continuity.
• memory-system: QMD is closely related to the broader concept of AI memory systems, especially retrieval layers that preserve and surface prior context.
• Ryan Wiggs: Described using QMD search to ingest a large archive of PM work into Claude Code as a productivity-enhancing “second brain.”
• Claude Code: The coding environment or assistant into which QMD-backed knowledge was ingested, demonstrating how retrieval can extend an AI tool’s usefulness.