Skip to main content
Smithers orchestrates AI coding agents at scale with composable, model- and harness-agnostic workflows. Most workflow systems fail quietly, losing work to a crash and forcing a manual restart. Smithers’s render loop avoids that: each frame asks what’s finished and what can start, validates task outputs against Zod schemas, and persists them to SQLite immediately. Crashes, restarts, and approvals become first-class, and the runtime resumes from the last persisted state without re-running completed work.
You are in the Technical API: reference material written for AI agents and workflow authors, not for humans. You never need to read it; your agent does. If you’re a human, start at the Product API: What Smithers Is explains the product in plain language, and Platform Capabilities shows what to say to your agent to get each capability.
Default authoring path: MDX prompts. Edit a plain Markdown file in .smithers/prompts/; the seeded TypeScript skeleton picks it up automatically, no build step or TypeScript needed. See MDX Workflow Authoring. Advanced authoring: TypeScript SDK. For branching, schemas, parallel fan-out, or loops, write the workflow as a JSX tree that Smithers renders and drives execution from:
Use Smithers when:
  • order matters across multiple AI or compute steps
  • you need crash recovery
  • humans must approve or answer questions mid-run
  • different tasks need different models, tools, or policies
  • operators need the Gateway API to launch, stream, and approve runs programmatically
Don’t use it for a single prompt → single response: use your model provider’s SDK directly.