Added on Nov 17,2026

StateWeave is a testing platform for AI agents that runs your agent inside sandboxes filled with stateful clones of the apps it works in. Each clone, or twin, has the same API, events, MCP server and web UI as the real service.
Available twins include Slack, Salesforce, Gmail, Zendesk, Shopify, Google Sheets, Google Calendar, Google Drive, WhatsApp, Teams, Stripe, HubSpot, Notion, Outlook, GitHub, Intercom, Linear, Jira, Confluence and Snowflake. If your agent uses an app that is not listed, the team will build its twin for you.
You give your agent a task, such as replying to a customer, refunding an order and closing a ticket, and StateWeave records every API call the agent makes. Checks are read back from the apps' APIs to grade whether the task was completed.
Key features include graded runs with each call recorded, fault injection such as outages and 401 errors, AI-generated data that fills every app with a consistent scenario, and a fresh copy for every run so tests can be repeated.
Setup uses a Python SDK and a command-line tool: you create an API key in the dashboard, sign in from your terminal and connect agents built with tools such as Claude Code, Codex or Cursor.
Pricing: the Free plan costs nothing and includes 5 sandbox hours a month with all apps. Basic is USD 249 per month for 200 sandbox hours, then USD 0.50 an hour, with more sandboxes and AI-generated data. Custom plans add app clones built for you and help with data and tasks. Idle twins cost nothing.
It is suited to teams building AI agents that act in business apps and want to test every model, prompt and agent setup change before production.
By the PowerfulAI.tools Editorial Team · Updated 18 November 2026 · Researched with AI assistance and checked against the official StateWeave website · How we review tools
Free plan costs $0 a month with 5 sandbox hours; Basic costs $249 a month with 200 sandbox hours, then $0.50 an hour. Custom plans are quoted on request.
Pricing checked against the official StateWeave website in November 2026. Prices can change, so confirm before you buy.
AI engineering teams who want to test agents against realistic copies of business apps before each model or prompt change reaches production.
A minute counts when your agent, or you, calls one of a sandbox's apps through its API, MCP server or web page, and it counts once per sandbox however many apps were called. Twins nobody calls go to sleep and cost nothing.
Yes. You can request an app, and the team builds its twin with the same API, events and web UI, then checks it against the real app in a test account. Custom plans include app clones built for you.
Popular alternatives to StateWeave include Pollinations, NemoClaw and Agnes AI. Compare their pricing and what each is best for below.
| Tool | Pricing | Best for |
|---|---|---|
| Pollinations | Freemium | Developers and hobby builders who want a single API for adding AI images, audio and text to their websites, bots and app... |
| NemoClaw | Free | Developers and platform teams who want to run always-on AI agents on NVIDIA hardware under policy-based security control... |
| Agnes AI | Freemium | Developers building AI-powered apps who want access to several models through one API. |
| OrcaRouter | Freemium | Developers and teams who want to balance AI quality and cost across many models. |
| DiagramGPT | Free | Developers and students who need to sketch system designs and workflows quickly by describing them in words. |
Leave a review for the community
No Review Found
Already a member? The same buttons sign you in.
We'll email you a 6-digit code. No password needed. By continuing you agree to our Privacy Policy.
We sent a 6-digit code to . It expires in 10 minutes.
No email? Check your spam folder, or ·