<?xml version='1.0' encoding='utf-8'?>
<rss version="2.0"><channel><title>Agent Memory Reference</title><link>https://aiagentmemory.com.de/</link><description>Runnable agent memory, retrieval evaluation and provenance</description><item><title>Practical Agent Memory Reference</title><link>https://aiagentmemory.com.de/</link><guid>https://aiagentmemory.com.de/</guid><description>A runnable, MIT‑licensed implementation of store, retrieve, provenance, and consolidate operations for AI agents — grounded in a small, reproducible test fixture.</description></item><item><title>Quickstart — Run the Agent Memory Reference</title><link>https://aiagentmemory.com.de/quickstart/</link><guid>https://aiagentmemory.com.de/quickstart/</guid><description>Two commands get you from a fresh archive to a working memory store and a reproducible evaluation. Tested on Python 3.14 only.</description></item><item><title>Architecture: an append-only agent memory reference</title><link>https://aiagentmemory.com.de/architecture/</link><guid>https://aiagentmemory.com.de/architecture/</guid><description>This page maps the actual modules and data flow of the reference implementation. It is a local, in-memory teaching/demo system — not a remote database or cloud…</description></item><item><title>Evaluation: Observed Fixture Metrics</title><link>https://aiagentmemory.com.de/evaluation/</link><guid>https://aiagentmemory.com.de/evaluation/</guid><description>Local verification on a synthetic corpus — exact numbers, formulas, and how to rerun. No implied general ranking quality.</description></item><item><title>Provenance: every memory traces to an origin</title><link>https://aiagentmemory.com.de/provenance/</link><guid>https://aiagentmemory.com.de/provenance/</guid><description>The reference implementation keeps an append-only ledger that maps each memory id to the observation that created it, and records any later consolidations. No silent…</description></item><item><title>Agent memory source, downloads and resources</title><link>https://aiagentmemory.com.de/resources/</link><guid>https://aiagentmemory.com.de/resources/</guid><description>A small, runnable Python reference for practical agent memory — not a production system, not a research benchmark.</description></item><item><title>About this reference</title><link>https://aiagentmemory.com.de/about/</link><guid>https://aiagentmemory.com.de/about/</guid><description>A practical, runnable agent memory reference — built and tested in the open, with clear provenance and no marketing gloss.</description></item><item><title>Contact</title><link>https://aiagentmemory.com.de/contact/</link><guid>https://aiagentmemory.com.de/contact/</guid><description>For corrections, API questions, code bugs, or media rights, email Guerin@novcog.com . We aim to respond within a few business days, but we do not offer formal SLAs,…</description></item><item><title>Image credits and source licenses</title><link>https://aiagentmemory.com.de/credits/</link><guid>https://aiagentmemory.com.de/credits/</guid><description>The hero image on this site is Nikon D4 HTTP Server Working... LOL (7711008596) by Takashi Hososhima , sourced from Wikimedia Commons , licensed under CC BY-SA 2.0 .…</description></item></channel></rss>