Blog

Agent Memory in 2026: An Honest Comparison of Mem0, Zep, Letta, and the Rest

Miles Builds WordPress Sites. But Should It?

bymiles.ai is an agentic AI that spins up WordPress websites in minutes. Impressive. But in 2026, is WordPress still the right canvas for an AI to paint on? We compare WordPress to Starlight and make the case for a better default.

We Found Bugs in Our Own Benchmarks (The Real Numbers Are Better)

How we built rigorous evaluation infrastructure, found critical scoring bugs, and established honest baselines that beat CORE SOTA.

The AutoMem Docs Portal is Live

53 pages of production-grade documentation covering every corner of the memory system — from FalkorDB graph internals to platform-by-platform integration guides.

Financial Agents Need Memory, Not Just Market Data

Why persistent memory matters more for trading bots than chat assistants, and how Bankr can add it with one command.

AutoMem Now Runs Natively in OpenClaw

No bridges, no middleware. AutoMem memory recall works directly inside OpenClaw agents via a single skill file.

You Don't Need to Spend Most of Your Day Thinking About Memory to Have a Memory-Powered AI Assistant

A beginner-friendly guide to running AutoMem locally — completely free, no coding experience required

What's Coming in v0.10.0: See Your Memory Graph

3D visualization, 11 relationship types, hand gesture controls, and real-time monitoring. Your memories are about to get visual.

Remote MCP: The SSE Sidecar Grows Up

Streamable HTTP replaces SSE as the primary transport. Same features, better reliability, zero breaking changes.

SSE Sidecar: AutoMem Now Works With ChatGPT, Claude Web, and ElevenLabs

How we enabled real-time memory streaming for AI platforms that don't natively support MCP

Understanding RAG: Why AI Needs Context

A practical guide to Retrieval Augmented Generation and why it matters for AI assistants

Introducing AutoMem: Universal Memory for AI

Why we built AutoMem and why your AI's memory should belong to you

Why We Chose Graph-Based Memory Over Pure Vector Search

A deep dive into AutoMem's FalkorDB + Qdrant architecture and why relationships matter

Self-Hosting AutoMem: Docker, VPS, and Beyond

A practical guide to running AutoMem on your own infrastructure