flowwork turns your daily work into auditable, repeatable programs that drive Claude Code — combining deterministic orchestration with the generative power of agents in one durable unit.
Free tier: 3 active workflows · 10 runs/day · no credit card
Short, focused demos of real workflows driving Claude Code.
A quick tour: author a workflow in Claude Code, deploy it with flowctl, and watch a run execute end to end.
The flexibility of a coding agent with the guarantees of a versioned, strongly-typed workflow.
External calls execute inside the workflow. You pay the token cost once, at authoring time — not on every agent run.
MCP import docs →Keep working in your Claude Code session while getting the predictability of versioned, strongly-typed workflows.
Skills and built-in tools are callable from a workflow. Drive Claude Code over local files, docs, devops, source code, and browsers — on your laptop or in an ephemeral sandbox you spin up, run, and tear down for cents.
Workflows are repeatable, shareable units with a full audit trail. Run the same thing twice and get the same shape of result.
Retries, exponential backoff, and greedy fallback out of the box — or author your own graceful degradation.
Develop custom applications and agents on top of flowwork. Integrate your own app as an MCP server or CLI tool — the engine is the durable substrate; you bring the product.
MCP import docs →Because the code is prewritten, there is no sandboxing to bolt on, no AI-firewall trying to out-guess a probabilistic model, and no class of prompt-injection that turns into an arbitrary external call. Those defenses are inherently insufficient against the nondeterminism of LLMs.
Every external call is abstracted into a connector with explicit checking, retries and backoff, and a fallback you control. The model decides what to do within bounds you authored — it never decides how to reach the outside world.
Describe the workflow in words and use the 'flowwork' skill to generate a typed, versioned definition — connectors and all.
Trigger workflows from Claude, monitor execution, and handle human-in-the-loop steps as they come up.
Execute it repeatably. Every run is auditable, resumable, and shareable as one unit.
Start free. Own it with a one-time Pro license. Scale on Cloud.
For trying it out
Early-adopter price — locks in for life; rises as features land.
For teams and heavy, multi-machine workloads
| Capability | Free | Pro | Team / Cloud |
|---|---|---|---|
| Active workflows | 3 | Unlimited | Unlimited |
| Runs per day | 10 | Unlimited | Unlimited |
| Authoring skill | Basic | Pro | Pro |
| MCP import — any stdio / remote server, unlimited tools per workflow | — | ✓ | ✓ |
| Workflow Garden — search & import community workflows Soon | Search | ✓ | ✓ |
| Machines per license (run on laptops, servers & ephemeral sandboxes) | 1 | 5 | Unlimited |
| Workspaces — shared state & memory across machines Soon | — | — | ✓ |
| Inference server — hosted Soon | — | — | ✓ |
Items marked Soon are on the roadmap and ship to the relevant tier as they land. Team / Cloud pricing announced at launch.
The free tier allows up to 3 active workflows and 10 runs per day — enough to build something real. Upgrade to remove the limits.
Because the code is prewritten. There's nothing to sandbox at runtime and no AI-firewall guessing at a probabilistic model's intent. External calls are abstracted into vetted connectors with explicit checking.
You can — until you need retries, backoff, leases, versioning, fan-out, long timers, replay, and operator tooling. Then you've rebuilt a workflow engine. We wrote about this.
Yes. The engine runs locally against your own Postgres. The trial license checks in periodically but tolerates being offline within a grace window.
Browse the community workflow collection, watch a demo, then start your free trial.