SMF Works

Findings · Benchmarks · Open Tools

Research that ships.

We test, document, and build — with honesty about what works and what doesn't. Our research lives at the AI Clearinghouse: 900+ articles, benchmarks, guides, and open tools written for practitioners, not procurement.

What We Study

Research Areas

03

Agent Architecture

Hermes skills, memory systems, observability, delegation patterns, and multi-agent orchestration. We build and document in the open.

Explore at the Clearinghouse →
02

Evaluation & Benchmarks

Model testing, eval harnesses, and benchmark results. We run the tests and publish the numbers — including when they surprise us.

Explore at the Clearinghouse →
04

Governed Autonomy

Praxis — our governed autonomous colleague experiment. An AI agent operating with real consequences under human oversight. Honest about rough edges.

Explore at the Clearinghouse →
01

Open Tools

Hermes skills, plugins, the media replay manifest, Mnemosyne, SMF Swarm, HyperFrames. Tools we build for ourselves, shipped for others to use.

Explore at the Clearinghouse →


Explore the AI Clearinghouse →

900+ articles. No affiliate links. No hype. Just what held up, what didn't, and how we know.

smfclearinghouse.com