Open source tools from the lab
Deterministic infrastructure for AI agents. Every product runs local first, ships with source, and is MIT licensed.
GRIM
Security audit for AI agents. GRIM finds code, dependency, exposure, secrets, and active compromise gaps across any stack, with drift detection and an SBOM.
Harmony
Repo rules enforcement for AI agents. Harmony checks diffs against the repository rule set and blocks violations before they land.
Logbook
Project memory across sessions for AI agents. A queryable decision log that survives between sessions.
Reference
Reference integrity for AI agents. Scans a repository for every reference and verifies each one resolves.
Release Gate
Release intelligence for AI agents. Analyze changes, detect breaking updates, and recommend the next semantic version.
Targetly
Deployment truth verification for AI agents. Targetly answers whether the live site is what you just built.
Token Gate
Token and context budget for AI agents. Track spend, estimate the cost of a read, and catch the burn before it happens.
Heides Lens
The screen for HEIDES. A desktop viewer and query tool over the HEIDES code nervous system.
HEIDES
The code nervous system. HEIDES gives any LLM instant, deterministic understanding of a codebase, so agents stop reading files and start knowing them.