Governed AI delivery

Ship with agents. Keep humans in control.

One workflow policy for Claude Code, Codex, OpenCode and Antigravity, with human approvals that can be checked against GitHub reviews and comments. A dependency-free toolkit with explicit scope, approval, review, QA, and publish gates.

  • Python 3.11+, no runtime dependencies
  • Tested on Windows, Ubuntu, macOS
  • MIT
agentkit
$ agentkit validate
Validation complete: 0 error(s), 0 warning(s).

$ agentkit artifact transition docs/agent/specs/20261109162915-add-search.md approved
ERROR: Approval requires --approved-by and --evidence; agents cannot self-approve.

$ echo '{"tool_name":"Bash","tool_input":{"command":"git push --force origin main"}}' | python hooks/guard_git.py
BLOCKED: force push is forbidden
0runtime dependencies
6separated roles
9CI environments
MITopen source

The missing control plane

Fast agents need
a deliberate system.

Prompts can explain good behavior. They cannot prove approval, prevent a force push, or preserve a review trail. Governed Agent SDLC turns those expectations into portable policy, structured artifacts, deterministic validation, and safety hooks.

Project policy keeps scope, credentials, merge, and release under human authority. Generated role guidance and hooks constrain supported tool actions; platform permissions remain part of the security boundary.

One accountable path

From intent to pull request

Each handoff produces readable evidence. Every gate is explicit.

  1. 01

    Specify

    Separate facts, assumptions, scope, and risk.

  2. 02

    Plan

    Build an ordered task graph from approved intent.

  3. 03

    Implement

    Work from an active task with an explicit write boundary.

  4. 04

    Review

    Assess independently; never repair while reviewing.

  5. 05

    Verify

    Run the declared QA matrix and record evidence.

  6. 06

    Publish

    Open a PR only after a final human decision.

Policy that travels

One kernel. Multiple tools and stacks.

◇

Tool-neutral core

Roles, transitions, approvals, and security policy stay independent of any vendor. Adapters carry them to Claude Code, Codex, OpenCode, and Antigravity.

⌁

Structured evidence

Readable Markdown and TOML frontmatter make lifecycle state machine-checkable. Approvals can be verified on GitHub: only a review or comment by a human collaborator counts. agentkit review runs an OpenCodeReview or host CLI review, judges its findings against the manifest's policies, and keeps every attempt and human decision as append-only evidence.

⊘

Deterministic guards

Supported hooks deny known credential access, force pushes, protected-branch refspecs, recursive deletes outside the workspace, role writes outside their grant, and spawning a role from an artifact that has not passed its gate.

⌘

Portable CLI

Initialize, generate, validate, diagnose, migrate the manifest, and transition artifacts with Python 3.11+. After a package upgrade, agentkit upgrade refreshes the generated guards and adapter files and keeps hand edits. In CI, the reusable validation workflow runs the toolkit revision your workflow pins.

▦

Stack profiles

Start with generic, Python, Node.js, Java, .NET, Nuxt, Flutter, Go, Rust, Kotlin, and PHP defaults without changing governance.

✓

Cross-platform QA

Continuously checked across Windows, Ubuntu, macOS, and three Python versions.

Trust boundaries by design

Authority stays visible.

The workflow kernel owns meaning. Profiles add stack knowledge. Adapters translate policy. Hooks enforce selected high-value boundaries without replacing platform permissions.

Read the architecture
01Project manifest + artifactsscope · state · evidence
02Tool-neutral coreroles · policy · gates
03Profiles + adaptersstack · vendor translation
04CLI + deterministic hooksvalidate · enforce · report

Three commands to begin

Bring governance into your repository.

Install the published package, then initialize an existing project. Nothing project-owned is overwritten.

terminal
$ python -m pip install governed-agent-sdlc
$ agentkit init ./my-project --name my-project
$ agentkit doctor ./my-project

Human authority. Agent velocity.

Make every handoff accountable.