<?xml version="1.0" encoding="utf-8"?>
<feed xmlns="http://www.w3.org/2005/Atom">
    <id>https://www.statewave.ai/blog</id>
    <title>Statewave blog</title>
    <updated>2026-05-25T00:00:00.000Z</updated>
    <generator>https://github.com/jpmonette/feed</generator>
    <author>
        <name>Statewave team</name>
        <uri>https://www.statewave.ai</uri>
    </author>
    <link rel="alternate" href="https://www.statewave.ai/blog"/>
    <link rel="self" href="https://www.statewave.ai/blog/atom.xml"/>
    <subtitle>Notes from the Statewave project — memory infrastructure for AI agents, deployment patterns, and design choices behind a Postgres-only self-hosted memory runtime.</subtitle>
    <logo>https://www.statewave.ai/og-image.png</logo>
    <icon>https://www.statewave.ai/favicon.svg</icon>
    <rights>Statewave, 2026. Apache-2.0.</rights>
    <entry>
        <title type="html"><![CDATA[Agent memory provenance: why your LLM app needs an audit trail]]></title>
        <id>https://www.statewave.ai/blog/agent-memory-provenance-audit-trails</id>
        <link href="https://www.statewave.ai/blog/agent-memory-provenance-audit-trails"/>
        <updated>2026-05-25T00:00:00.000Z</updated>
        <summary type="html"><![CDATA[When an AI agent answers from memory, you need to know where it learned the answer. This post explains the provenance model in Statewave — what we store, what it costs, and what it enables for compliance, debugging, and trust.]]></summary>
        <content type="html"><![CDATA[When an AI agent answers from memory, you need to know where it learned the answer. This post explains the provenance model in Statewave — what we store, what it costs, and what it enables for compliance, debugging, and trust.]]></content>
        <author>
            <name>Statewave team</name>
        </author>
        <category label="provenance"/>
        <category label="audit"/>
        <category label="compliance"/>
        <category label="architecture"/>
    </entry>
    <entry>
        <title type="html"><![CDATA[AI agent memory vs RAG — what's the difference?]]></title>
        <id>https://www.statewave.ai/blog/ai-agent-memory-vs-rag</id>
        <link href="https://www.statewave.ai/blog/ai-agent-memory-vs-rag"/>
        <updated>2026-05-25T00:00:00.000Z</updated>
        <summary type="html"><![CDATA[Retrieval-augmented generation and an agent memory runtime overlap at the embedding store, but they answer different questions. Here's where the two diverge and which to reach for.]]></summary>
        <content type="html"><![CDATA[Retrieval-augmented generation and an agent memory runtime overlap at the embedding store, but they answer different questions. Here's where the two diverge and which to reach for.]]></content>
        <author>
            <name>Statewave team</name>
        </author>
        <category label="memory"/>
        <category label="rag"/>
        <category label="architecture"/>
    </entry>
    <entry>
        <title type="html"><![CDATA[How to add persistent memory to your AI support agent]]></title>
        <id>https://www.statewave.ai/blog/persistent-memory-for-ai-support-agents</id>
        <link href="https://www.statewave.ai/blog/persistent-memory-for-ai-support-agents"/>
        <updated>2026-05-25T00:00:00.000Z</updated>
        <summary type="html"><![CDATA[A practical walkthrough of giving a support agent durable memory of customers across sessions — what to record, how to compile it, how to retrieve it, and what to expect from the support workflow benchmark.]]></summary>
        <content type="html"><![CDATA[A practical walkthrough of giving a support agent durable memory of customers across sessions — what to record, how to compile it, how to retrieve it, and what to expect from the support workflow benchmark.]]></content>
        <author>
            <name>Statewave team</name>
        </author>
        <category label="support"/>
        <category label="tutorial"/>
        <category label="memory"/>
    </entry>
    <entry>
        <title type="html"><![CDATA[Self-hosted AI memory with Postgres and pgvector]]></title>
        <id>https://www.statewave.ai/blog/self-hosted-memory-postgres-pgvector</id>
        <link href="https://www.statewave.ai/blog/self-hosted-memory-postgres-pgvector"/>
        <updated>2026-05-25T00:00:00.000Z</updated>
        <summary type="html"><![CDATA[Why Statewave is Postgres-only by design, what pgvector buys you over a dedicated vector database, and what the deployment shape looks like in production.]]></summary>
        <content type="html"><![CDATA[Why Statewave is Postgres-only by design, what pgvector buys you over a dedicated vector database, and what the deployment shape looks like in production.]]></content>
        <author>
            <name>Statewave team</name>
        </author>
        <category label="postgres"/>
        <category label="pgvector"/>
        <category label="deployment"/>
        <category label="self-hosted"/>
    </entry>
</feed>