AI governance · static analysis · compliance · CI gate

Lint your AI features for governance guardrails.

Point aiglare at any JS/TS repo. It finds every place an LLM output reaches a user or triggers a side-effect — payment, booking, email, DB write — then flags which have no confidence handling, no fallback, no validation, and no human-in-the-loop. Map findings to SOC 2, EU AI Act, NIST AI RMF, and OWASP LLM Top 10 with one flag.

Run an audit View on GitHub

$ npx @nugehs/aiglare ./src --ci

aiglare ./src --compliance all --format lint

scanned 38 files · 3 AI surfaces · 1 blocking

routes/checkout.ts side-effectful

error human-in-loop required soc2/CC9.1

error output validation missing eu-ai-act/Art.9

error excessive agency owasp/LLM08

api/summarize.ts user-facing

warn fallback path missing nist/MANAGE-1.3

jobs/autotag.ts internal

✓ all guardrails present — no violations

3 errors 1 warning · 1 file

Most AI incidents aren't model failures.
They're governance failures — the output flowed straight to a user or an irreversible action with nothing in between.

aiglare makes those paths visible, and lets you block the dangerous ones in CI before they ship.

How it works

Scan, classify, score, gate

A static pass over your code — no runtime, no keys, no data leaving the repo. Run it locally or wire it into CI.

Scan

Finds every AI/LLM call site with a provider-agnostic registry — no config, no annotations. Raw fetch/axios to inference hosts count too.

Classify by sink

Traces where each output goes: returned to a user, feeding a side-effect, or internal-only. The sink decides how much the risk matters.

Score guardrails

Checks five governance dimensions per surface and rolls them into a red / amber / green severity you can read at a glance.

Gate in CI

--ci fails the build only on red side-effectful surfaces — the irreversible-action case — so you adopt it without warning fatigue.

Sinks

Where the output goes decides the risk

Every AI surface is classified by sink. A model writing a log line is not the same as a model issuing a refund.

user-facing

Returned from a route or controller, or rendered in a component. The model is talking directly to a person.

side-effectful

Feeds a payment, booking, email, database/file write, or shell. The model can trigger something irreversible.

internal

Logged or cached only. Lowest blast radius — flagged for awareness, never blocks your build.

Guardrails

Five dimensions, scored per surface

Each surface is checked on five governance signals. Full coverage is green; a side-effect with none is red.

01

Confidence handling

Does the code read and act on a confidence / probability signal before trusting the output?
02

Fallback path

Is there an uncertain-or-failed branch — a default, a retry, a safe no-op — when the model is unsure?
03

Output validation

Is the output schema-checked, parsed, or constrained before it's used downstream?
04

Human-in-the-loop

For side-effects: does a person confirm before the irreversible action fires?
05

Error isolation

Is the call wrapped so a model failure can't take down the surrounding request?

A severity you can adopt

The CI gate fails only on red side-effectful surfaces — the "AI auto-triggers an irreversible action with no confirmation" case. Safe to turn on today without drowning a team in warnings.

red · review now amber · partial green · covered

$ npx @nugehs/aiglare ./src --ci

scanning…  3 surfaces, 1 blocking
✗ red  routes/checkout.ts:42  side-effectful
────────────────────────────────────
exit 1 · build blocked

Provider-agnostic

It already knows your stack

Detection is driven by a provider registry — SDKs and raw inference calls alike. Adding a provider is a one-line PR.

OpenAI

Anthropic

Google

Cohere

Mistral

Replicate

Vercel AI SDK

LangChain

LangGraph

Ollama

AWS Bedrock

Cloudflare Workers AI

Hugging Face

fetch / axios

Compliance reports

One scan, four frameworks

Pass --compliance all and every surface gets annotated with the specific controls it violates. Pick your output format to match your workflow — ESLint lint, Markdown evidence doc, or an auditor-ready HTML report.

SOC 2

CC7.2 · CC7.4 · CC9.1 · A1.2 · PI1.2 · PI1.3

Trust Services Criteria — change management, monitoring, and processing integrity for AI outputs.

EU AI Act

Art. 9 · Art. 13 · Art. 14 · Art. 17

Risk management, transparency, human oversight, and quality management for high-risk AI systems.

NIST AI RMF

GOVERN-1.2 · MAP-2.3 · MEASURE-2.5/2.6 · MANAGE-1.3/2.2

Govern, Map, Measure, Manage — the four RMF functions, mapped to concrete guardrail gaps.

OWASP LLM Top 10

LLM02 · LLM04 · LLM08 · LLM09

Insecure output handling, model DoS, excessive agency, and overreliance — mapped per surface.

Output formats

terminal
Default coloured report, now with a per-framework violation summary footer.
lint
ESLint-style output. Rule IDs like soc2/CC9.1. Works in CI, editors, and code review.
markdown
Evidence doc with per-framework control tables — hand it to an auditor or attach to a ticket.
html
Branded HTML report with sticky nav, collapsible sections, and guardrail matrix table.

Multi-repo

Pass multiple paths to combine several repos into a single report. Files are prefixed with their repo root for clear attribution.

aiglare ./api ./web --compliance all --format html

compliance examples

# ESLint-style lint — works in CI
$ aiglare --compliance soc2,eu-ai-act --format lint

# Markdown evidence doc for auditors
$ aiglare --compliance all --format markdown > AUDIT.md

# Branded HTML report
$ aiglare --compliance all --format html > report.html

# Lint gate — fail CI on compliance errors
$ aiglare --compliance all --format lint --ci

MCP server

Let your agents run the audit

aiglare ships a built-in Model Context Protocol server — no SDK dependency. Three tools, wired straight into your agent host.

ai_surface_audit

Full audit of a repo → the same structured report as --json. Accepts an optional compliance array; each surface includes violations[] when set.

ai_surface_gate

CI-gate verdict: passed + count of blocking red side-effectful surfaces.

list_providers

The provider registry the scanner detects.

claude_desktop_config.json

{
  "mcpServers": {
    "aiglare": {
      "command": "npx",
      "args": ["-y", "@nugehs/aiglare", "mcp"]
    }
  }
}

⚡ Optional: repoctx acceleration

If a repoctx index is present, aiglare uses it to sharpen sink classification with real kind/domain data. Same tool, two fidelity levels — standalone for everyone, richer for repoctx users.

Honest limitations

It's a linter, not a verifier.

This is static, advisory analysis. It produces false positives (a guardrail two call-hops away can be missed) and false negatives (a confidence variable that doesn't actually gate anything reads as present). Treat the output as surfaces to review, not violations. The repoctx adapter exists precisely to close the call-graph gap.

See your AI surfaces in one command

No install, no config, no keys. Run it on any JS/TS repo right now.

$ npx @nugehs/aiglare # audit current repo

$ npx @nugehs/aiglare ./src --ci # fail the build on red

$ npx @nugehs/aiglare --compliance all --format html # HTML evidence report

$ npx @nugehs/aiglare --compliance soc2,nist --format lint --ci # compliance linter in CI

Star on GitHub View on npm