<?xml version="1.0" encoding="UTF-8"?><rss version="2.0"><channel><title>incredlabs Blog</title><description>Notes on data infrastructure for the AI era — databases, agent memory, and Rust, from incredlabs.</description><link>https://www.incredlabs.com/</link><item><title>Programmable memory for AI agents: why fixed vector APIs fall short</title><link>https://www.incredlabs.com/blog/programmable-memory-for-ai-agents/</link><guid isPermaLink="true">https://www.incredlabs.com/blog/programmable-memory-for-ai-agents/</guid><description>Most agent memory is a fixed similarity-search call. Real tasks need custom retrieval logic — which is why Liath lets agents write sandboxed Lua to query their own memory.</description><pubDate>Mon, 22 Jun 2026 00:00:00 GMT</pubDate><author>Dipankar Sarkar</author></item><item><title>Introducing incredlabs: the data layer for AI-native software</title><link>https://www.incredlabs.com/blog/introducing-incredlabs/</link><guid isPermaLink="true">https://www.incredlabs.com/blog/introducing-incredlabs/</guid><description>Why we&apos;re building Rust-native databases and agent memory for the AI era — and what ORMDB and Liath are for.</description><pubDate>Mon, 15 Jun 2026 00:00:00 GMT</pubDate><author>Dipankar Sarkar</author></item></channel></rss>