What We Study
Research Areas
Agent Architecture
Hermes skills, memory systems, observability, delegation patterns, and multi-agent orchestration. We build and document in the open.
Read architecture deep dives →Evaluation & Benchmarks
Model testing, eval harnesses, and benchmark results. We run the tests and publish the numbers — including when they surprise us.
See benchmark results →Governed Autonomy
Praxis — our governed autonomous colleague experiment. An AI agent operating with real consequences under human oversight. Early preview, honest about rough edges.
Learn about Praxis →Open Tools
Hermes skills, plugins, the media replay manifest, Mnemosyne, SMF Swarm, HyperFrames. Tools we build for ourselves, shipped for others to use.
Browse on GitHub →Deep Dive
Explore the Clearinghouse
The AI Clearinghouse
Our practitioner-facing research site. 900+ articles: agent directories, LLM profiles, service reviews, skill docs, benchmarks, guides, deployment recipes, and AI news analysis.
Visit the Clearinghouse →
White Papers
In-depth research papers on agent architecture, evaluation methodology, and governed autonomy.
Read white papers →
Lab Experiments
Hands-on experiments and benchmarks — GPU performance, inference optimization, local AI clusters, and model comparisons.
Browse lab experiments →