GOVENANT
Coding agent · open pattern

Govern your OpenAI Codex agents.

“Done” lives in the database, not in the model’s mouth.

Codex tasks end in diffs and pull requests, so outcome-keyed completion is native; the Codex CLI also connects to the hosted GOVENANT Audit as an MCP client today.

See the pattern → Run the free audit from Codex Track the integration ↗

Why govern Codex agents

The most verifiable agents on earth

PR merged, tests green, deploy live — coding agents produce terminal outcomes the record can verify. That makes this the easiest class of agents to govern honestly, and the least excusable to leave ungoverned.

Trust the fleet, not the transcript

When agents write your code, the question is not what they said they did — it’s what shipped, verified against CI and the repo record. Motion is not delivery.

Audit today, govern this quarter

Most tools in this class speak MCP, so the free hosted GOVENANT Audit connects now. The governed substrate then turns agent output into a standing, sweepable delivery record.

How it works with OpenAI Codex

The pattern for coding agents: A governed definition of done: coding agents have naturally verifiable terminal outcomes (PR merged, tests green, deploy live), so the repo becomes the substrate — branch protections as ownership gates, CI as the validation gate, completion keyed to merged-and-green.

Why Codex fits: Codex tasks end in diffs and pull requests, so outcome-keyed completion is native; the Codex CLI also connects to the hosted GOVENANT Audit as an MCP client today.

  1. Where the tool is an MCP client, connect the free hosted GOVENANT Audit — one URL, no API key.
  2. Make the repo the substrate: branch protections and required reviews are ownership gates; CI is the deterministic validation gate.
  3. Assign agent work as duties with outcome-keyed completion — merged and green, not “task marked complete.”
  4. Ledger agent sessions: what was asked, what was changed, what it cost, what verifiably landed.
  5. Sweep on a schedule and put the delivery record — misses included — where the team can see it.

The full requirements live in the open standard (CC BY 4.0) — the substrate shapes, the acceptance tests, and the conformance ladder your record is measured against.

What you can claim

A real integration can wear the Built-on GOVENANT badge under its four rules from day one. The ladder — Logged → Gated → Delivered → Earned — is self-assessed against the open standard and published to the registry with probe logs, open to challenge. For coding agents the Delivered rung has teeth: it means the record shows verified shipped work, not activity.

Levels & badges The public registry
Status — kept honest

Integration pattern: documented (this page). The Codex adapter, mapping, or worked example is being built in the open — progress, scope, and acceptance criteria live in the public GitHub issue. This page will not say “supported” before that issue closes with a working example. Holding our own pages to the standard’s claims discipline is not modesty; it is the product.

Build this with us

For dev-tool vendors and platform engineering teams: “provably governed” is the enterprise unlock for agentic coding. We co-market shipped integrations, and buyers who ask us “which coding stack can I actually govern?” get pointed at the ones with a public record.

Talk to the stewards → Contribute on GitHub ↗

OpenAI Codex governance — FAQ

My coding agent already shows me diffs and test results. What does this add?
A durable, queryable record across the fleet and across time: which duties exist, what delivered, what missed, and whether the misses are being written down by an independent watchdog rather than smoothed over. One session’s output is visibility; the substrate is governance.
Does this slow the agents down?
The gates run at chokepoints you already have — branch protection, CI, review. GOVENANT makes them count as governance by recording outcomes against duties; it adds accounting, not latency, to the inner loop.
What is “performed autonomy”?
Agents that look busy — fluent plans, satisfied logs — but don’t verifiably ship. Motion is not delivery. GOVENANT measures verified outcomes against the record, never the logs’ self-report.
What is GOVENANT, and who controls it?
An open standard for provable AI agent governance: three laws, a conformance ladder, and acceptance tests any implementation can run against its own record. It is free to all under CC BY 4.0 with a citable companion paper (DOI 10.5281/zenodo.21440225), and conformance is self-assessed and published openly — no certifying authority, no gatekeeper.

More coding agents

Claude CodeCursorGitHub Copilot coding agentDevin (Cognition)WindsurfPriiism

Different stack? Browse all 45 integrations — or run the free audit from any MCP-capable tool.