October 2, 2026
modelright.dev is a live registry of AI model specs and pricing — ten providers' worth of context windows, token prices, and availability, queryable and comparable. Nobody wrote it. A LiveGraph bootstrap run created the repository, provisioned Cloudflare and Railway, delegated the nameservers, deployed the skeleton, and installed an improvement loop that then built the product through ten queued work items, each one a reviewed, CI-gated, human-approved pull request.
This post is the honest version of that story — including the parts that broke, because the parts that broke are where the product actually lives.

The App Bootstrap template is a run-once graph: Scaffold → Provisioner → approval gate → Deploy Verify. Scaffold creates the GitHub repo and pushes a Next.js+Postgres skeleton in a single commit — the agents have no filesystem, everything goes through GitHub's API. Provisioner creates the Cloudflare zone, captures the assigned nameservers, delegates them at the registrar's API, stands up the Railway project with app and Postgres services, writes the DNS records, and mints every secret the skeleton declares. A human gate sits before the verify hop — the last checkpoint before the run declares anything live.
Then the part that matters: the bootstrap installs a self-improvement loop on the new repo. Every ten minutes a tick reads QUEUE.md, the engineer picks the top item onto a branch, CI runs, a reviewer reads the actual diff, and a publisher sits behind a human approval gate before anything merges. The product plan was a paragraph. The queue items — the landing page, the compare page, the availability tracking — were written, implemented, reviewed, and merged by the loop.

Three honest failures, each now a feature:
Every hop of that run was visible, interruptible, and steerable while it happened — and the failures above surfaced as markers and parked approvals, not silent state. When the queue file corrupted, we didn't restart a pipeline; we watched the conflict-fix round run, approved the reparented PR, and hardened the machinery the same week. That loop is still running: modelright.dev continues to improve itself on a 10-minute tick, and every merge still parks at a human gate. (The live canvas demo shows the same steer-a-running-graph mechanics on a scripted model — no keys, no spend.)

The same template is what a new user gets: pick App Bootstrap, fill six fields, press “Start the build,” and watch a domain become a self-improving product — with a build-status page tracking every marker the run emits.
Five days later the loop is still ticking, and the queue went from ten items to forty-two done across 52 merged PRs. What modelright.dev gained on autopilot plus a few human-steered rounds: real OpenRouter sync every hour (with removed-model handling), Artificial Analysis benchmarks and speed metrics, a four-way compare page with an interactive picker and SEO-friendly pair URLs, task picks (coding, long-context, vision, cheap-bulk), a changes feed with price-history charts, a public JSON API, an MCP server with six read tools, the full agent-discovery surface (llms.txt, agents.txt, OpenAPI, A2A card), cookieless visitor/bot/MCP analytics, and a token-gated admin dashboard.


The interesting failure mode this week: a CI webhook consumed as STILL_BUILDING never re-armed the reviewer, so a green branch silently parked until a human noticed. When the publish lane stalls, a person lands the PR — which is the approval-gate design working as intended, not a bug in it.
And the headline: the repo is now public under MIT. QUEUE.md, PLAN.md, and the per-item delivery log in docs/loop-reports/ are committed alongside the code — the loop's work product is the sample.