Evaluate AI Tooling Posture. Prove It Deterministically.

Wrkr evaluates your AI dev tool configurations across your GitHub repo/org against policy. Posture-scored, compliance-ready.

Scan, rank, regress, verify, and export evidence with stable `--json` outputs and fail-closed safety defaults.

Start Here Org Scan Flow

# Initialize with deterministic defaults
wrkr init --non-interactive --path ./scenarios/wrkr/scan-mixed-org/repos --json

# Run scan and posture outputs
wrkr scan --path ./scenarios/wrkr/scan-mixed-org/repos --profile standard --json
wrkr report --top 5 --json
wrkr score --json

# Generate and verify compliance evidence
wrkr evidence --frameworks eu-ai-act,soc2 --output ./.tmp/evidence --json
wrkr verify --chain --json

# Gate on drift
wrkr regress init --baseline ./.wrkr/last-scan.json --output ./.tmp/wrkr-regress-baseline.json --json
wrkr regress run --baseline ./.tmp/wrkr-regress-baseline.json --json

Org and Repo Discovery

Discover AI tooling declarations across repo/org/path sources with deterministic output contracts.

Headless Risk Ranking

Surface high-impact CI/autonomous execution risks with ranked, explainable findings.

Compliance Evidence

Generate framework-mapped evidence bundles and verify proof chain integrity.

Deterministic Regressions

Create baseline posture gates and fail CI with stable drift reasons.

Open Manifest Contract

Use `wrkr-manifest.yaml` as a portable policy and lifecycle posture contract.

Agent-Readable Context

LLM-oriented docs resources, AI sitemap, and crawler policy for reliable assistant grounding.

Why Teams Use Wrkr

	Without Wrkr	With Wrkr
AI tool inventory	manual surveys, stale answers	deterministic repo/org inventory
Headless risk visibility	ad-hoc grep and assumptions	ranked findings with posture context
Compliance evidence	manual artifact assembly	command-generated evidence bundle
Regression gating	no baseline contract	stable drift reasons and exit code 5

Frequently Asked Questions

What is Wrkr in one sentence?

Wrkr evaluates your AI dev tool configurations across your GitHub repo/org against policy. Posture-scored, compliance-ready.

Does Wrkr require a hosted control plane?

No. Wrkr is deterministic and file-based by default, with local scan state and local evidence generation.

What makes Wrkr outputs audit-friendly?

Wrkr emits deterministic JSON contracts, stable exit codes, and proof-chain verifiable evidence paths.

Can Wrkr enforce runtime side effects?

Wrkr is a discovery and posture layer. Runtime side-effect enforcement belongs to control-plane runtimes like Gait.

How do I fail CI on posture drift?

Use `wrkr regress init` to create a baseline and `wrkr regress run` in CI. Exit code `5` indicates drift.

How do I generate compliance evidence?

Run `wrkr evidence --frameworks ... --json` and validate integrity with `wrkr verify --chain --json`.

Use command-first docs that agents can quote and operators can verify.

Start with intent guides, then validate with deterministic CLI outputs.

Open Documentation

For assistant and crawler discovery resources, use LLM Context.