The constitutional hook engine for AI coding agents.
A local, deterministic MCP server that intercepts agent actions before they execute and enforces your rules — not as documentation the model can ignore, but as a decision it can't route around.
npm install -g @sunaiva/gate
Enforcement that runs on your machine.
The Gate intercepts AI agent actions before they execute and enforces constitutional rules. 100 rules ship with the package: 31 enforced locally (23 strict-constitutional + 8 recommended-default) and 69 premium rules served via backend on the paid tier.
Fail-open by design. If the gate encounters any internal error during evaluation, it degrades to pass-through. Your agent never stalls waiting on us.
The free tier needs no signup, no API key, no onboarding step.
31 local rules evaluate entirely on-device. Works offline.
Every decision is appended to a JSONL log at ~/.sunaiva/audit/audit.jsonl.
From tool call to verdict in under a millisecond.
Free & local: the 31 rules run entirely on your machine. Nothing leaves.
Free for personal and evaluation use under BUSL-1.1. The 31 local rules evaluate on-device and your audit log is plain JSONL on disk. A representative sample of the constitutional categories — not exhaustive.
Deploys, publishes and financial commands require an explicit token before they're allowed to run.
No writes outside the designated workspace. No destructive git operations.
Gold asset paths are enforced read-only — the agent cannot overwrite protected material.
No shell=True. No empty-index commits. Hygiene the model tends to skip.
On paid: premium rule evaluation sends the action to our server (the detection patterns are proprietary); only content-free verdict metadata — tool, decision, rule ID, timestamp — is retained in your dashboard. The action content itself is not stored.
Step up when one machine isn't the whole team.
Beta launch pricing shown below — ends ~Aug 8, 2026; standard pricing applies to everyone after. Standard list price in grey. Annual prepay is 2 months free across paid tiers (10× monthly).
| Tier | Price | What you get | |
|---|---|---|---|
| Free | $0 · forever | 31 local constitutional rules · no signup · no API key · JSONL audit log on disk · evaluate offline | Install → |
| Starter | $19/mo · seatreg $29 Beta price — ends ~Aug 8, 2026 |
+ 69 premium server-side rules · API token via email · 1 agent | Upgrade → |
| Pro | $49/mo · seatreg $79 Beta price — ends ~Aug 8, 2026 |
+ BYOK — Gemini · Anthropic · OpenRouter (any model) · or any OpenAI-compatible key · 5 agents · webhook · CSV export · multi-seat | Upgrade → |
| Power | $149/mo · seatreg $199 Beta price — ends ~Aug 8, 2026 |
Custom rule authoring · cross-session severity escalation · managed LLM compute · extended audit retention | Upgrade → |
| Enterprise | Contact sales | Custom rules · air-gap deployment · SSO / SAML · dedicated SLA · hardware attestation option (Patent 04) | Book intro |
~/.sunaiva/audit/audit.jsonl) and the CLI.
See every verdict. Tune every rule.
Browse the audit log, toggle rules and manage your plan from the hosted dashboard — no terminal required.
Where the Gate sits in the portfolio.
The Gate is built on the same architecture the Sunaiva Triple-Gate Validation MCP (Patent 01 Claim 1 commercial embodiment) uses. The Gate enforces agent actions — Claim 22 of USPTO 64/006,491, autonomous AI agent action validation.
The full conjunctive AND-logic Triple-Gate over AI outputs (Claims 1 + 3 + 5) ships in the Validation MCP, now in early access. See the patent portfolio →
Install the Gate. Try the architecture.
Free for personal and evaluation use. No account, no API key.
npm install -g @sunaiva/gate