Skip to content
Voidex
Sign inStart free
Controlled beta

Infrastructure for AI that acts.

Connect agents to tools. Control what they can do. Verify what actually happened. Voidex gives AI agents a controlled way to act across applications — and gives your team evidence of the outcome.

Start in the sandboxRead the API

Free developer plan with simulated connectors. No card required.

in flightheld for approvalverified → receiptfailed check· Illustration, not live data
How it works

Every action takes the same controlled path

Whether a request comes from an agent over MCP, a workflow, or your code, it is validated, evaluated, executed in a worker and checked against the real system before anyone calls it done. Scroll to follow one action.

  1. 1. Action

    An agent, workflow or API call proposes a typed action. Input is validated against the tool’s JSON Schema before anything else happens.

  2. 2. Policy
  3. 3. Approval
  4. 4. Execute
  5. 5. Verify
  6. 6. Receipt
Step 1 of 6 · Actionillustrative
POST /api/v1/runs
{ "tool": "acme_ledger.create_invoice",
  "connectedAccountId": "acct_…",
  "input": { "customer": "Globex", … } }
Integrations

Voidex Connect →

Typed tools with input schemas, risk classes and reversibility. A generic HTTPS connector with explicit allowlists, signed webhooks, a REST API, a TypeScript SDK and an MCP endpoint — all calling the same execution path.

Control & evidence

Voidex Verify →

Deny-by-default policy, approvals bound to the exact payload, isolated execution, independent postcondition checks, and hash-chained receipts that say what did — and did not — happen.

Evaluation

Voidex Bench →

Versioned suites with deterministic fixtures and fault injection. Measure task success, verification status, policy compliance, retries and latency — from real recorded runs only.

Business console

Voidex Workforce →

Configure specialist workers from templates, check their readiness, run them, and review their exceptions — on the same Connect and Verify foundation.

Evidence, not assertions

A receipt for every attempted action

  • Independent checks. After a write, Voidex reads the target system again and compares fields, counts, totals or status transitions.
  • Honest outcomes. Checks are passed, failed, inconclusive or not run. Only passed deterministic or human-attested checks make an action “verified”.
  • Lost responses handled. If a non-idempotent call times out, Voidex does not blindly retry — it verifies the real state and asks for review.
  • Tamper-evident. Receipts are hash-chained per workspace. The chain shows records weren’t edited later; it doesn’t by itself prove the claims are true — the checks do that.
Illustrative example shape of a receipt (abridged)
Integrations

Horizontal by design, honest about status

Generic REST / HTTPS

Available

Any JSON API you control, behind host allowlists and SSRF protection.

Signed outbound webhooks

Available

HMAC-SHA256 with timestamps; retries with backoff.

MCP endpoint

Available

Your registered tools exposed to MCP clients — still policy-checked.

Acme Test CRM & Ledger

Simulated

Local simulators with fault injection for development and Bench.

SaaS connectors (CRM, support, dev tools, ERP)

Planned

Salesforce, HubSpot, Zendesk, GitHub, Jira, ERPNext, Odoo and others are on the roadmap.

Model providers

Planned

Provider adapters are interface-ready; only a deterministic demo provider ships today.

Security principles we build to

Deny by default

No matching rule means no action. High-impact actions always need two approvers.

Least privilege

Server-enforced roles, scoped API keys, tenant isolation on every query.

Secrets stay secret

Credentials are encrypted, write-only, never sent to the browser or a model.

No arbitrary code

Workers run registered connector operations only — no shell, no user code.

What’s implemented vs planned

Try the full loop in minutes

Connect the simulated CRM, run an action, approve a sensitive one, and read the receipt.

Create a free workspaceTalk to us