Documentation Protocol v1.0

Integrate pre-execution governance: API contract, receipts, offline verification, and CI enforcement. Start with npx trigguard demo; live authorization uses TRIGGUARD_API_KEY and authorize() on the gateway.

Authorization before execution

Every irreversible action passes through TrigGuard. Offline Policy Authoring never performs runtime authorization. Only authorize() can authorize execution. Only the gateway can enforce policy. Risk is assessed, and a receipt is produced before anything executes.

Current state

AI decides
AI executes

Risk: no authorization layer

With TrigGuard

AI decides
TrigGuard authorizes
Permit Deny Escalate Silence
AI executes
  • Gateway evaluates before side effects
  • Risk assessed on every surface
  • Receipt independently verifiable
  • Verification Live
  • Gateway Live
  • CLI npm trigguard · pip trigguard

Installation

Offline demo: npx trigguard demo with no API key / no ~/.trigguard login → Decision: PERMIT · Receipt: VERIFIED. If an API key is present, the demo uses the live gateway and may return DENY (fail-closed). Live authorization: set TRIGGUARD_API_KEY, then authorize() against the Execution Gateway. Root SDK: authorize, verify, receipt, explain, createAgent, createClient - see SDK.

npm install trigguard
npx trigguard demo
pip install trigguard
pip install authgraph
pip install trigguard-litellm
# MCP: npx @trigguard/mcp
# Live: TRIGGUARD_API_KEY + authorize()

How it works

Architecture and decision semantics live on dedicated pages - this hub links into them.

Quickstart

Machine path: npm install trigguard then npx trigguard demo. Live path: TRIGGUARD_API_KEY + authorize(). Full walkthrough: quickstart.

Protocol reference

Runtime integration

Trust & verification

Deterministic authorization boundary - every request yields PERMIT, DENY, ESCALATE, or SILENCE. Report vulnerabilities to [email protected].

FAQ

Protocol Verification vs Execution Gateway?
Offline verification is live: Ed25519 over receipt JSON using /.well-known/trigguard-keys.json. The Execution Gateway issues PERMIT / DENY / ESCALATE / SILENCE for irreversible actions via authorize() with TRIGGUARD_API_KEY - see TG-EXECUTION-AUTH-01.
API keys for verification?
No. Use published keys with the CLI or /verify.
Canonical quickstart?
/docs/quickstart - offline demo first (npx trigguard demo), then live authorize().
SILENCE vs DENY?
DENY is an explicit refusal. SILENCE withholds authorization without leaking policy signals.