---
title: "Agent memory as a file format"
description: "Cal Paterson proposes Markdown plus an optional SQLite vector index as a portable, harness-independent memory format for agents."
author: "Pau Friedman"
kind: "link"
published_at: "2026-08-31"
url: "https://pau.fm/blog/2026/08/31/agent-memory-as-a-file-format"
markdown_url: "https://pau.fm/blog/2026/08/31/agent-memory-as-a-file-format.md"
canonical_url: "https://pau.fm/blog/2026/08/31/agent-memory-as-a-file-format"
external_url: "https://calpaterson.com/memoryfields.html"
---

# [Agent memory as a file format](<https://calpaterson.com/memoryfields.html>)

> Memory should be a data format, not a multi-stage pipeline.

Paterson’s format is Markdown plus an optional SQLite vector index, packed into a zip file. The
source of truth is readable prose; the embeddings are a disposable cache; the agent can use tools it
already understands.

Most memory systems invert this. They make a proprietary pipeline durable and the user’s accumulated
knowledge an implementation detail. Formats survive the model frontier. Mechanisms calcify.