> ## Documentation Index
> Fetch the complete documentation index at: https://smithers.sh/llms.txt
> Use this file to discover all available pages before exploring further.

# Smithers vs. Claude Code Workflows

> Claude Code's Dynamic Workflows are excellent for one sitting. Smithers is the open, durable version: any model, any harness, survives a crash, and waits overnight for a human.

Claude Code ships [Dynamic Workflows](https://code.claude.com/docs/en/workflows): describe a task, Claude writes a JavaScript orchestration script, and a runtime fans it out across parallel subagents that attack the problem from independent angles and converge on an answer. If you have a Max or Team plan, you already have it, and for work that fits in one sitting it is genuinely good.

So when do you want Smithers instead? When the work has to outlive the sitting.

## The short version

Dynamic Workflows is a feature of one vendor's coding agent. Smithers is an MIT-licensed runtime that treats coding agents, humans, and plain code as steps in one durable workflow. The two overlap on "run many agents against a problem" and differ on everything around it.

|                     | Claude Code Workflows                | Smithers                                                                                               |
| ------------------- | ------------------------------------ | ------------------------------------------------------------------------------------------------------ |
| Where it runs       | Inside a Claude Code session         | Your laptop, CI, or a server; the process is disposable                                                |
| Models              | Claude subagents                     | Claude Code, Codex, Pi, Antigravity, any AI SDK model, mixed in one workflow                           |
| Crash mid-run       | Work is lost; start the script again | Resumes from the last persisted step                                                                   |
| Human approval      | Blocks while you are at the terminal | Durably suspends; answer tomorrow over CLI, web, or HTTP                                               |
| The workflow itself | A script generated per task          | A versioned file you review, diff, rerun, and eval                                                     |
| History             | Scoped to the session                | Every run, frame, and attempt is a SQLite row: `ps`, `inspect`, `timeline`, `rewind`, `fork`, `replay` |
| Scheduling          | You start it                         | Durable cron triggers, alerts, and a supervisor that revives stale runs                                |
| Source              | Closed research preview              | MIT, on [GitHub](https://github.com/smithersai/smithers)                                               |

## What that means in practice

**Durability is the line.** A Dynamic Workflow orchestrates subagents and returns an answer; the value lives in that session. A Smithers run persists every completed step the moment it finishes, so killing the process, closing the laptop, or deploying over it costs you nothing. Resume picks up at the right step, and `supervise` does it automatically when a heartbeat goes stale.

**Vendor scope is the other line.** An orchestration layer earns its keep by outliving the model choice. In Smithers a frontier model plans, a cheaper model fans out, and a different lab's model reviews, in one workflow, with fallback arrays (`agent={[claude, codex]}`) when a provider has a bad day or you hit a rate limit. Dynamic Workflows orchestrates Claude.

**Approvals change what you can automate.** A run that cannot stop and wait for a human is a run you have to babysit. `<Approval>` suspends a Smithers run as a database row that costs nothing while it waits, then resumes at the right step when someone answers. That is the difference between "agents I watch" and "agents I check on in the morning."

## They compose

This is not either/or. Smithers drives Claude Code as a first-class agent, on your existing subscription, and the [Claude Code plugin](/integrations/claude-code-plugin) mirrors Smithers runs into the session so your agent can watch and steer them. A sensible split: quick fan-outs in the session, anything long-running, approval-gated, or worth rerunning goes to Smithers.

The longer argument, with the crash-resume demo, is in [the open, durable version of agent workflows](/why/durable-open-orchestration).

## See also

* [Smithers vs. Temporal](/why/vs-temporal)
* [Smithers vs. LangGraph](/why/vs-langgraph)
* [Get started](/guide/get-started): one command, first run in 30 seconds