Back to vendors
W

Windmill

Also known as: Windmill Labs, windmill.dev, Windmill AI

Visit site
Entry priceCommunity Edition free · Cloud Team $10 per seat a month · self-hosted Enterprise from $120 a monthFull pricing detail

Open source workflow engine and developer platform: scripts in 20+ languages become flows, apps and endpoints, with AI agent steps and evals, approval steps, broad triggers and full self-hosting.

Windmill is an open source, self-hostable workflow engine and developer platform. Scripts in more than 20 languages become flows (multi-step graphs with branches, loops, retries, error handlers and approval steps), internal apps and API endpoints, and they run on a Rust job engine across worker groups. Flows start from cron schedules, webhooks and HTTP routes, email, WebSocket, Postgres change capture, Kafka, NATS, Amazon SQS, MQTT, AMQP, Google Cloud Pub/Sub and Azure triggers. Any step can suspend until approvers resume it through generated URLs or an approval page with forms.

For AI work, AI agent steps run inside flows with a provider and model the customer picks (OpenAI, Anthropic, Google, Mistral, DeepSeek, Groq, OpenRouter and others), Windmill scripts as tools, nested agents, and conversation memory. Reusable agents carry evals: datasets of cases scored by AI judges or scripts, with every run kept for comparison. An MCP server exposes a workspace's scripts and flows to Claude, Cursor and other clients, and AI sessions let a chat assistant build scripts, flows and apps as drafts. The Hub offers ready-made projects and integration scripts for hundreds of services.

The Community Edition is free to self host; Windmill Cloud's Team plan is $10 per seat a month; the Enterprise Edition, from $120 a month self-hosted, adds audit logs, SAML and SCIM, OpenTelemetry tracing and a SOC 2 Type II report.

Vendor details

Canonical URL

https://www.windmill.dev

Category

Agent infrastructure

Company status

independent

Use cases & customers

Target customers

engineering and platform teamsdata and DevOps teamsenterprises self hosting automation

Deployment options

self-hostedopen sourcemanaged clouddocker

In practice

A Python script needs to be a scheduled job, an internal tool with a UI and a webhook API all at once. Windmill generates the interface and the endpoint from the script's parameters rather than requiring three implementations.

An AI workflow must stop for human sign off before it acts. Approval gates are built into the orchestration layer rather than being something you implement in the application.

Compliance rules out a managed automation service. The platform self hosts on your own infrastructure with role based access control, secret management and audit logs, though check which of those sit behind the paid tier.

Agentic Index coverage score

12.0 / 14 capabilities · 86%

Integrations & Tool Calling Full

Agents built in Windmill act in outside systems with stored credentials. The Hub catalogs integration scripts across hundreds of services (Slack, Jira, Gmail, Google Sheets, Postgres, Airtable, OpenAI, Anthropic and more), resource types store the credentials those scripts act with, and any Windmill script can be attached as a tool to an AI agent step, so the agent takes authenticated action in outside systems. AI sessions can also connect external MCP servers as clients.

Sourcehub.windmill.devread 2026-09-23

Workflow Orchestration Full

Windmill is a workflow engine: flows compose scripts in 20-plus languages into multi-step graphs with branches, loops, early stops, retries, error handlers and suspend steps, and AI agent steps run inside those flows with tools, including nested agents configured as tools of another agent.

Sourcewindmill.dev/docs/flows/flow_editorread 2026-09-23

Knowledge Grounding & RAG Not documented

No retrieval structure Windmill maintains over the customer's corpus is documented. Its persistent storage (data tables, DuckLake, object storage, states and resources) holds data the customer's own scripts read and write, which is storage rather than grounding, and any retrieval a customer builds runs through tools or providers they call from a script.

Sourcewindmill.dev/docs/core_concepts/persistent_storage/states_resources_shared_directoryread 2026-09-23

Human Oversight & Guardrails Full

Any flow step can be set to suspend, a durable approval wait built into Windmill, holding the flow until the required number of approval events arrive through generated resume and cancel URLs or the approval page, with forms for the approver to fill in and a timeout.

Sourcewindmill.dev/docs/flows/flow_approvalread 2026-09-23

Security, Identity & Governance Full

The plans page states Windmill is SOC 2 Type II compliant, with the report downloadable from the customer portal, and a trust center at trust.windmill.dev, scoped to the Enterprise Edition. On Enterprise, SAML and SCIM authenticate and provision users through the customer's identity provider; SSO is available on every edition (capped at 10 users on the free edition), and developer and operator roles separate who can edit from who can only run. Audit logs record every operation with side effects.

Sourcewindmill.dev/docs/advanced/saml_and_scimread 2026-09-23

Observability & Auditability Full

Runs are recorded step by step, with an audit record kept apart from them. The Runs page lists past and future jobs with each job's logs, inputs, results and per-step detail for flows, and AI agent steps report their tool calls and token usage. Audit logs capture every operation with side effects and the user responsible, with a configurable retention period on self-hosted instances, and an OpenTelemetry guide exports traces, metrics and logs to the customer's own observability stack.

Sourcewindmill.dev/docs/core_concepts/audit_logsread 2026-09-23

Memory & State Persistence Partial

The AI agent step keeps conversation memory the agent reads as context across runs: in auto mode Windmill keeps up to a set number of the most recent messages, in manual mode the caller supplies the history in OpenAI message format, and the docs cover using memory with webhook-triggered runs. No published lifetime or purge path and no first-party surface to review or edit what the agent remembers are documented. States and resources persist small JSON between job executions, which is storage the code reads.

Sourcewindmill.dev/docs/core_concepts/ai_agentsread 2026-09-23

Deployment & Data Residency Full

Windmill is open source and self-hosts in the customer's own infrastructure, with documented Docker, Kubernetes (Helm), AWS EKS and ECS and Azure setups, alongside Windmill Cloud and dedicated cloud instances for Enterprise.

Sourcewindmill.dev/docs/advanced/self_hostread 2026-09-23

Prebuilt Agents, Templates & Packs Full

The Hub publishes a browsable catalog of assets a buyer adopts into a Windmill workspace. It includes ready-made projects that each do a job: a support engine that drafts replies into Gmail, a recruiting app with AI CV screening, a Sentry engine that investigates recurring errors and opens a pull request with the fix, a helpdesk and an uptime monitor. It also holds integration scripts and flows for hundreds of services, pickable from inside the editors, and a Private Hub serves an organization's own approved set.

Sourcehub.windmill.devread 2026-09-23

Triggers & Channel Coverage Full

Work starts on its own from cron schedules, webhooks and HTTP routes, email triggers, WebSocket and Postgres change capture, and from Kafka, NATS, Amazon SQS, MQTT, AMQP, Google Cloud Pub/Sub and Azure triggers, plus native triggers, each starting a script or flow when the event arrives.

Sourcewindmill.dev/docs/triggersread 2026-09-23

Model Flexibility & Routing Full

The customer chooses the model behind each Windmill AI agent step. Providers include OpenAI, Azure OpenAI, Azure AI Foundry, Anthropic, Mistral, DeepSeek, Google (Gemini), Groq, OpenRouter, Together AI and custom endpoints, with the credentials stored as reusable resources. The model is picked per step, with a reasoning-effort setting for models that support it, and nested agents configure their own provider and model.

Sourcewindmill.dev/docs/core_concepts/ai_agentsread 2026-09-23

APIs, SDKs & MCP Extensibility Full

Outside callers reach Windmill through a documented REST API with a published OpenAPI specification, the wmill CLI with sync to Git, TypeScript and Python clients, webhook and HTTP route endpoints generated for any script or flow, and an MCP server that exposes a workspace's scripts and flows as tools plus API operations on jobs and other objects.

Sourcewindmill.dev/docs/core_concepts/mcpread 2026-09-23

Testing, Debugging & Optimization Full

Customers get an evaluation harness for their agents. AI agent evals attach a dataset of cases (question and expected answer) to a reusable agent, run the agent against every case, score the answers with AI judges or scripts, and keep every run so the next one is compared against it. The docs frame it as answering whether the agent got better after each change.

Sourcewindmill.dev/docs/core_concepts/ai_agent_evalsread 2026-09-23

Browser & Computer Use Partial

Windmill hosts the environment browser automation runs in: a worker group installs Chromium on start and takes jobs tagged chromium, and the docs give Playwright and Puppeteer examples for testing and scraping, which a script can expose as a tool to an AI agent step. The browser control comes from those libraries in the customer's own script, and no Windmill API for screenshots, clicks or typing is documented.

Sourcewindmill.dev/docs/advanced/browser_automationread 2026-09-23

The Agentic Index coverage score grades every vendor Full, Partial or Not documented against the same 14 buyer facing capabilities, from public evidence only. Each capability links to how all vendors in the index score on it. How this evidence is graded

Recent platform changes

2026-10-01·Agent capabilityVerified

AI agents are now their own item in Windmill, listed beside scripts, flows and apps with dedicated pages for running and editing them, including drafts, deployment and version history.

Bears on: Agent capability

View source
2026-09-25·Pricing / packagingVerified

Windmill v1.818.0 counts enabled service accounts as operator seats in self hosted Enterprise deployments, billing each as half a seat regardless of its assigned role. Enabled service accounts also count toward the offline license seat cap, and creation is refused when the cap is reached. The related Cloud Team billing change is separate from this release.

Bears on: Pricing / packaging

View source
2026-08-28·Agent capabilityVerified

Windmill enabled Anthropic prompt caching specifically for the Vertex AI agent. This update allows agents utilizing Anthropic models via Google Cloud's Vertex AI to cache context and instructions.

Bears on: Agent capability

View source
View all 7 changes for Windmill →Tracked since Aug 2026 · Verified from public vendor sources

Pricing

Community Edition free · Cloud Team $10 per seat a month · self-hosted Enterprise from $120 a month

Cloud: per seat per month. Self-hosted Enterprise: developer seats, operator seats at half price, and compute units per worker (standard worker $50 a month); app guests beyond 100 a month count as seats

Free tierTrial available

What is public

The Community Edition (free to self host), Cloud Team at $10 per seat a month and self-hosted Enterprise from $120 a month with developer, operator and worker rates are public, as are the Pro and non-profit terms; cloud Enterprise is custom.

Billing mechanics

Two routes. The open source edition is free to self host on any infrastructure, where the only cost is compute and operations. Windmill Cloud starts with a free tier for small projects and scales through paid tiers adding team collaboration, priority support and higher execution limits, with enterprise terms negotiated.

Cost watchouts

Audit logs, SAML and SCIM, the SOC 2 report, OpenTelemetry tracing and longer job retention sit in the Enterprise Edition; the free edition keeps job run details for up to 30 days. Self-hosted Enterprise bills compute units per worker on top of seats.

Variable cost rationale

Self-hosted Enterprise adds a compute unit charge per worker, so scaling workers raises cost alongside seats; cloud Team is priced per seat.

Additional watchouts

Windmill's own pricing table puts audit logs, SAML and SCIM and the SOC 2 report in the Enterprise Edition only. Any team adopting the open source edition for a regulated or security sensitive workload should confirm secrets management, roles, audit logs and approver identity are actually available in the tier they intend to run.

Sales call required

Mixed (some tiers require a call)

Free / trial

Free open source Community Edition to self host; a month's trial of Enterprise

Lowest paid plan

Cloud Team $10 per seat a month

Commercial notes

Windmill claims a thirteen times throughput advantage over Apache Airflow as a self hostable engine, and positions itself against managed automation platforms on control. For teams that already run infrastructure, the self hosted route makes the platform cost effectively zero beyond compute and operations.

Key ambiguities

Self-hosted Enterprise cost depends on the worker configuration as well as seats, which the pricing page's calculator simulates; cloud Enterprise is custom.

Missing data

Cloud Enterprise pricing (custom on seats and compute units) and execution limits per tier.

Agentic Index verified 2026-09-23

Alternatives to Windmill

The closest documented capability profiles to Windmill among agent infrastructure platforms tracked by Agentic Index, ordered by similarity on the same 14 point evidence the rankings use. No vendor pays for placement.

  • Bernstein10.5 / 14A lighter documented profile than Windmill
  • LangSmith11.5 / 14Fuller documented coverage on Memory & State Persistence
  • OpenRouter10.5 / 14A lighter documented profile than Windmill
  • Agno13.0 / 14Adds documented Knowledge Grounding & RAG
  • Anchor Browser11.0 / 14Fuller documented coverage on Browser & Computer Use
  • Braintrust10.0 / 14A lighter documented profile than Windmill

Similarity is computed from each vendor's Agentic Index coverage score evidence, axis by axis, not from the totals. How this evidence is graded

Contact us

Found a vendor we missed? Have feedback on the index? We'd love to hear from you.