We build AI products too. Orinyx is one of ours.
Not tools built to fill a market. Tools built because we needed them and they didn't exist.
Both started as internal work. Orinyx came out of trying to answer a question hospitals kept asking about clinical AI and finding no independent way to answer it. Stellar Agents came out of running a one person practice on a fleet of agents and needing every one of them to stop one step before anything went out.
Featured Product
Orinyx (beta)
Orinyx is an independent verification platform for clinical AI. Hospitals use it to test AI products before deployment, then keep verifying them once they are live.
Every AI assertion is checked against authoritative sources rather than against another model's judgment, so each verdict is deterministic and arrives with a citation showing what was checked and which source applies. That independence is structural. Orinyx has no clinical AI product of its own, because a system that grades its own output is not performing a check.
Phase 1 runs in a sandbox on synthetic data, with no PHI, no EHR connection, and no security review needed to begin. Phase 2 runs the same verification continuously at runtime, upstream of the clinician, with a full audit trail.
Available nowAgent kit
Stellar Agents
Ten agents, one human gate, and the vault they live in.
Stellar Agents are the agents charmthirteen uses to run a one person practice. They plan the week, triage the inbox, draft the writing, check it, keep the record, and audit the lot, and every one of them stops one step before anything goes out.
Free for Artificially Designed subscribers · Claude Code, Codex, Gemini CLI, OpenClaw, Hermes
Available nowMore tools are in development, each one built from real advisory and systems work rather than from a roadmap. When something is useful enough to hand to someone else, it shows up here.