Open Source
We build production AI systems for regulated environments — and we open-source the operating layer underneath them. These are the tools we use ourselves, released for anyone building disciplined, auditable AI. Free to read, run, and fork.
Make any AI coding assistant verify its work before it says "done."
A plain-markdown operating doctrine you drop into any project: a constitution of hard rules, a six-phase algorithm for non-trivial work, and a verification doctrine that refuses unverified claims. The discipline lives in the files — so it works identically across Claude Code, Cursor, Codex, Gemini CLI, Aider, and Copilot.
Tamper-evident, examiner-ready records of what your AI agents actually did.
An open reference implementation for AI-agent audit trails. Every action an agent takes is captured, hash-chained so any later edit is detectable, and anchored to public time — producing a self-contained report an auditor can verify without trusting you or us. Air-gappable, dependency-free, and mapped to the frameworks regulators actually cite.
Grade a risk assessment the way the rubric says — deterministically, every time.
The evidence engine for security and AI governance. It grades a risk assessment as a deterministic function of the findings: it cannot skip the grade, it cannot invent a threshold, and it will not mark a control proven because the prose sounded confident. Every grade carries its basis — the row walk, not just the letter — and the default evidence state is UNVERIFIED. Zero dependencies, no network, and eight bundled control catalogs — CIS Controls v8.1, ISO/IEC 27001 and 42001, NIST AI RMF, CSF 2.0 and SP 800-53, the SOC 2 Trust Services Criteria, and CCPA/CPRA — so a cited control id that doesn't exist fails validation instead of passing as real.
Building something that needs the governed, enterprise edition? Talk to the team →