Show HN: Human0 – A template to run an autonomous, self-improving code loop

moshest1 pts0 comments

GitHub - human0-ai/template: Fork-and-go template for running an autonomous company with human0 — domain-owning AI agents that assess, decide, build, and ship. · GitHub

/" data-turbo-transient="true" />

Skip to content

Search or jump to...

Search code, repositories, users, issues, pull requests...

-->

Search

Clear

Search syntax tips

Provide feedback

--><br>We read every piece of feedback, and take your input very seriously.

Include my email address so I can be contacted

Cancel

Submit feedback

Saved searches

Use saved searches to filter your results more quickly

-->

Name

Query

To see all available qualifiers, see our documentation.

Cancel

Create saved search

Sign in

/;ref_cta:Sign up;ref_loc:header logged out"}"<br>Sign up

Appearance settings

Resetting focus

You signed in with another tab or window. Reload to refresh your session.<br>You signed out in another tab or window. Reload to refresh your session.<br>You switched accounts on another tab or window. Reload to refresh your session.

Dismiss alert

{{ message }}

Uh oh!

There was an error while loading. Please reload this page.

human0-ai

template

Public template

Notifications<br>You must be signed in to change notification settings

Fork

Star

main

BranchesTags

Go to file

CodeOpen more actions menu

Folders and files<br>NameNameLast commit message<br>Last commit date<br>Latest commit

History<br>7 Commits<br>7 Commits

.github/workflows

.github/workflows

docs

docs

AGENTS.md

AGENTS.md

CLAUDE.md

CLAUDE.md

LICENSE

LICENSE

README.md

README.md

View all files

Repository files navigation

human0

Describe a change. Claude Code ships it. You barely touch it.

human0.ai ·<br>the reviewer action

Fork this template and your repo runs on a self-driving loop.

You say what you want — in plain language, from your laptop or your phone. Claude<br>Code does the rest. It researches the code. It makes the change. It writes the<br>docs. It opens a pull request.

Then an AI reviewer checks the work. If something's off, the agent fixes it and<br>tries again. It loops on its own until the review passes. Then it merges.

You step in twice: to say what you want, and to say "go."

What you get out of the box:

AGENTS.md / CLAUDE.md — your rules, read by every agent on every run.<br>Write them once.

An AI reviewer — checks every PR, comments inline, gives one verdict:<br>APPROVE or REQUEST_CHANGES .

An autonomous workflow — open a draft PR, watch the preview, say "go." The<br>agent clears the review and the PR merges itself.

Built for Claude Code, including Claude Code on the web. The reviewer and rules<br>work with Codex or any agent too. It's the same setup that runs<br>human0 itself — every commit reviewed and merged by AI.

Why we build this way: Why AI Agents Should Be Defined as<br>Code.

Two ways to use it

1. Drop the reviewer into an existing repo

If you just want the AI reviewer on your current project, you don't need to fork<br>anything. Add a credential and one workflow file — full steps in the<br>code-review action README.

2. Start a new repo from this template

Use this repo as a template (the green Use this template button), then:

Add a credential. In Settings → Secrets and variables → Actions , add<br>one of:

ANTHROPIC_API_KEY — an Anthropic API key, or

CLAUDE_CODE_OAUTH_TOKEN — a Claude.ai OAuth token (claude setup-token).

Edit AGENTS.md to describe your project — its structure and rules.

Review docs/ai-review.md — this is your reviewer's instructions. Tailor<br>it to your project before you start relying on it.

Open a pull request. The reviewer runs on the next push.

To let an approval merge on its own, enable auto-merge and require the AI<br>review in your branch protection settings.

Repository settings

For the reviewer to approve PRs (which is what lets an approval auto-merge),<br>GitHub must allow Actions to approve pull requests:

Settings → Actions → General → Workflow permissions → enable<br>"Allow GitHub Actions to create and approve pull requests."

In an organization this is often locked at the org level — set it under<br>Organization → Settings → Actions → General instead. You don't need the<br>"Read and write" default token permission; the workflow already requests the<br>write scopes it needs.

What's in here

Path<br>What it's for

AGENTS.md<br>Guidelines agents read every run. CLAUDE.md is a symlink to it.

docs/ai-review.md<br>The reviewer's prompt — edit it to change how the reviewer behaves.

.github/workflows/ai-review.yml<br>Runs the reviewer on every PR.

.github/workflows/task-gate.yml<br>Holds an agent's PR until its linked task is independently approved.

The task gate

The reviewer checks the diff; the task gate<br>checks the work was signed off by someone who didn't do it. It's a CI check that<br>stays red until an agent's PR links a Human0 task that's been independently<br>approved, so self-approved work can't merge. It only gates the Human0 app's<br>PRs — human PRs pass through.

There's nothing to configure — no secret, no env. Just mark task-gate a<br>required status check so a red gate...

reviewer claude human0 template code github

Related Articles