Team Hull
*Hull* is one control plane that unifies version control, CI/CD, deployments, observability, and incident response — and operates it autonomously with a crew of Claude Opus 4.8 agents.** It's GitHub + Vercel + PagerDuty
Core trick
Production log errors trigger an agent that works in an isolated git worktree to fix the root cause, add a regression test, and open a PR.
Description
*Hull* is one control plane that unifies version control, CI/CD, deployments,
observability, and incident response — and operates it autonomously with a crew
of Claude Opus 4.8 agents.** It's GitHub + Vercel + PagerDuty + Datadog fused
into a single product and run by agents instead of by you.
You import a repo once. Hull detects its runtime, stands up **staging + prod**
with real public URLs (Docker Compose or a managed-process runtime, host-based
routing + Caddy on-demand TLS), and watches it. You ship features by handing a
ticket to an agent, which works in an isolated **git worktree**, opens a **pull
request** in Hull's own diff UI, and runs **CI** — then spins a **preview
environment** so you can test the change before merge.
The autonomous loop: when production throws an error, Hull detects it from the
live logs, opens a **PagerDuty-style incident**, spawns a Claude agent in a fresh
worktree that reproduces the bug, fixes the root cause, **adds a regression
test**, opens a PR, runs CI green, and — after a human approves the merge
(HITL by default; `HELM_AUTO_MERGE=1` closes the loop fully) — redeploys and
resolves the incident. The human reads the timeline after it's handled.
Built solo at Claude Build Day, SF, June 13 2026. Django 5.1 + HTMX (minimal JS),
SQLite, Temporal Cloud for durable orchestration (with a threaded fallback),
multi-tenant and auth'd, deployed live on a single EC2 box.
README excerpt
# ⎈ Hull — the AI-native control plane for software teams > One control plane for your entire stack — version control, CI/CD, deployments, > observability, and incident response — **operated by a crew of Claude Opus 4.8 > agents.** GitHub + Vercel + PagerDuty + Datadog, mashed together and run > autonomously. Built at **Claude Build Day**, San Francisco — June 13, 2026. Small, elite engineering teams shouldn't need a platform org to run a production-grade stack. Hull lets one engineer **import a legacy repo, stand up staging + prod, ship features through agents, and have production incidents fixed autonomously** — all from a single pane of glass. ## The autonomous loop 🎯 A production app throws an error → Hull detects it from the live logs → opens a PagerDuty-style **incident** → spawns a **Claude agent in an isolated git worktree** → the agent reproduces it, fixes the root cause, **adds a regression test** → opens a **pull request** in Hull's own PR/diff UI → **CI runs** → green → a human **reviews & merges** → Hull redeploys → incident **resolved**. Everything up to the merge is autonomous; the merge is a human-in-the-loop gate by default (you review the agent's fix before it ships). Flip `HELM_AUTO_MERGE=1` and the loop closes itself — no human in the loop at all. ## What it does | Capability | Plays the role of | How | |---|---|---| | Import any repo, detect runtime | — | clone + framework detection | | Staging & prod deployments w/ public URLs | Vercel | managed