Rigour

Your AI agent just tried to commit an AWS secret. Rigour blocked it in <100ms.

Agent Transaction Firewall (v6): treat the agent as an untrusted proposer. Rigour decides—deterministically—what it may write, run, call, and ship. No AI judge on the allow/deny path.

Try it now (zero config)

npx rigour-scan

Works on any repo. No init, no config, no setup. Instant results in your terminal:

  HARDCODED SECRET DETECTED
  AWS_SECRET_ACCESS_KEY found in src/config.ts:23

  + 22 more violations across 847 files (2.1s)

  Score        ████░░░░░░░░░░░░░░░░  34/100
  AI Health    ███░░░░░░░░░░░░░░░░░░  28/100

  Gates:  ✅ file-size  ❌ security  ❌ ast  ✅ deps

  Brain: learned 12 patterns · trend: improving ↑

Add to your AI IDE (30 seconds)

{ "mcpServers": { "rigour": { "command": "npx", "args": ["-y", "@rigour-labs/mcp@latest"] } } }

Then install hooks so writes are checked in real time:

npx @rigour-labs/cli hooks init --tool cursor   # or claude, cline, windsurf
# or via MCP: rigour_hooks_init

Does the firewall run automatically?

Short answer: quality gates + DLP + mediated rigour_run paths run when MCP/hooks are installed. It does not yet sit in front of every third-party MCP tool (GitHub/Slack/etc.)—that gateway is designed but not the default proxy.

Agent proposes action
        ↓
Hooks / MCP mediation (when on the path)
        ↓
Deterministic deny/allow + rule id
        ↓
Studio evidence  ·  CI attestation (admit)

Agent Transaction Firewall

npx @rigour-labs/cli firewall status
npx @rigour-labs/cli firewall adversarial   # deterministic corpus — unexpected allows fail CI
npx @rigour-labs/cli firewall transact --agent <id> --scope 'packages/foo/**'
npx @rigour-l

... [View full README on GitHub](https://github.com/rigour-labs/rigour#readme)