T3 Stack is a TypeScript workable choice for mlops. GreatCTO auto-detects both — adds the mlops archetype overlay, wires mlops-specific gates, and runs 34 specialist agents around your existing T3 Stack workflow.
GreatCTO reads your package.json and detects t3-stack + mlops archetype from signals: imports, file structure, env vars, README hints.
Attaches the mlops archetype overlay: archetype-specific reviewer + compliance gates. Override if your specifics differ; the defaults are sensible for T3 Stack-style projects.
qa-engineer runs tsc --strict / eslint / vitest --coverage; security-officer checks for prototype pollution + XSS sinks; performance-engineer reviews bundle size + cold-start times.
Bugs you've hit before in other T3 Stack projects (connection-pool exhaustion, ORM N+1 queries, retry storms) — the agent's Step 0 includes the prior detection order. MTTR drops 94 % on second occurrence (methodology).
$ cd my-t3-stack-app && npx great-cto init ✓ scanning manifests… found package.json ✓ stack: t3-stack (TypeScript) ✓ archetype: mlops ⚠ archetype + stack combo is unusual — review overlay manually ✓ 34 agents ready $ /start "add mlops feature" ▸ architect drafting ARCH-mlops.md… ▸ pm decomposing into beads tasks… ⚐ gate:plan — your approval needed
Approve → 3 senior-devs run in parallel worktrees → 5 reviewers fan out in parallel → gate:ship → deploy. One real run walked stage-by-stage: /proof.
T3 Stack (TypeScript) is not a typical fit for mlops. The archetype overlay still attaches, but you may want to override defaults more aggressively. Check the mlops archetype page for the typical stack list and decide if your case is the right tool / right archetype.
No black-box "AI does it all" loop. GreatCTO is a deterministic state machine — 8 stages, 22 nodes, 2 human gates. Every node maps to a real agent on GitHub. Inspect the state machine →
$ npx great-cto init
Free, MIT, runs locally. Works in Claude Code, Cursor, OpenAI Codex CLI, Aider, and Continue.