Open source by Hlinor

Tools that make AI work provable.

Explore the open-source components behind selected Hlinor review workflows: agent policy checks, repository discovery, scope-drift review and spreadsheet validation. Each project states what is available today and where its evidence ends.

Inspect the code, reproducible examples and limitations before relying on a tool. A source repository is one part of the evidence behind a review.

The toolchain

Each tool works on its own. Together they cover the full path from declared intent to accepted evidence.

01

Agent Registry

YAML policies, signed bundles and supported runtime checks for agent actions and resources. LangChain and CrewAI wrappers are available. Budget declarations require separate enforcement. On PyPI.

Learn more

02

Agent Control Plane

Read-only scanner that inventories agents, models, tools and MCP servers in a codebase, then flags deterministic risk findings with file/line evidence. SARIF output for CI gates.

Learn more

03

ScopeGuard

Flags potential scope drift between agreed work and communication exports. The browser pilot stores one project locally on this device; a human reviews each finding.

Learn more

04

SheetSentry

Checks .xlsx files that cross a company boundary: numbers stored as text, duplicate keys, totals that miss rows, columns that moved between versions. Cell-level evidence and SARIF output.

Learn more

Why open source?

An audit you cannot inspect is an opinion. Our detection rules, policy formats and scanners are public, so your engineers can verify exactly how findings are produced - before trusting the report.

What this gives you

  • No black box: the method is on GitHub, reviewable line by line.
  • No lock-in: YAML policies and SARIF reports work with your existing tooling.
  • Self-service first: run the tools yourself, call us when you want independent review.
From tools to proof

Want an independent review on top of the tools?

We run fixed-scope governance reviews of AI agents and workflows: policy inventory, runtime permission checks, audit-log gaps and a client-ready report in 72 hours.

Agent Governance Review