The Human.Exe Geometric Intelligence Layer (GiL) is shipping in stages. Account creation, BYOK, automation, memory retention, and audit trail are live. GiL includes a Basic governed-intelligence and memory foundation, with paid plans expanding managed memory and workspace capacity. Public content (blog, podcast, research) is open to everyone — it is not the subscription product. See the API reference for the full contract.
TypeScript SDK — install, client options, every method, error handling, and manual-signing fallback. The recommended integration path for the Geometric Intelligence Layer.
Human.Exe API
The Human-Link.
Turbocharge your AI workflow. Already have an AI API key? You're in the right place.
The Governance Layer for AI That Thinks — structural, provider-agnostic, session-aware.
Human.Exe provides a structural AI governance layer you deploy between your application and any AI provider. Your model. Our governance. Every decision traceable.
Most AI tools give you a response. Human.Exe governs a decision. The difference is architectural, not cosmetic.
What Human.Exe is
- Governance API — structural, provider-agnostic, session-aware
- The layer that makes AI decisions traceable, coherent, and auditable at the architecture level
- Sits between your app and your AI provider — every inference governed, not just logged
What Human.Exe is not
- Not a model. Not an AI assistant. Not a chatbot wrapper.
- Not a compliance tool that monitors outputs after the fact
- Not another OpenAI wrapper
This is not a wrapper. This is the first public implementation of structurally governed AI.
The Human.Exe API is a working proof of concept and a real product — the first public example of an AI governance layer that structurally controls how inference behaves, not just what it outputs. Every request is governed at the architecture level: coherency-scored, session-tracked, drift-detected, and fully auditable. This is fundamentally different from how AI is currently deployed anywhere.
The API is permanent infrastructure for those it serves — but it's not even the tip of the iceberg. What you see here is the surface layer of something significantly larger. The governance architecture underneath this product was designed for a class of intelligence that doesn't exist yet in public. It will.
Quickstart
Get your first governed inference in three steps. No waitlist, no approval queue.
Issue a Governance API key
Set your environment
export GIL_API_KEY=gil_live_<key-id>.<key-secret> export ANTHROPIC_API_KEY=sk-ant-... # your own provider key — BYOK
Install the SDK and call it
npm install @human-exe/gil-sdk
import { GiLClient } from '@human-exe/gil-sdk';
const gil = new GiLClient({ apiKey: process.env.GIL_API_KEY! });
const res = await gil.analyze({
provider: 'anthropic',
providerKey: process.env.ANTHROPIC_API_KEY!, // forwarded, never persisted
model: 'claude-opus-4-5',
input: { messages: [{ role: 'user', content: 'Hello.' }] },
governance: { attentionWave: 'tier1', coherencyCheck: true },
});
console.log(res.output); // provider-native response
console.log(res.governance.attentionWaveScore); // governance signalNever paste your GIL_API_KEY into a chat prompt, a file an AI agent reads, or any model context. It's a service credential, not part of the conversation.
Learn More
Authentication, endpoints, error codes, the full response object (audit trail, coherency scoring, governed routing), approved models, and efficiency practices are documented in full in the two references below — not duplicated here.
Pricing
Basic is the no-cost foundation. Pro and Pro+ unlock expanded memory allowance and extended dashboard tools — pick a plan when you create your account.
Start Building →AGI R&D
From the AGI R&D Division @Human.EXE
Deep-form content on structural AI governance. No fluff. Respects your intelligence.
The signal through the static.
10–20 minute episodes on the governance problem, the August 2026 EU AI Act deadline, cost economics, session coherence, and audit trail architecture.
Architecture-level dispatches.
The governance problem nobody is solving. The EU AI Act deadline that changes everything. The math behind 10–20× cheaper inference. Session coherence explained. The audit trail your AI isn't producing.