Integration
Connect Hatz AI to Daytona
When New File fires in Hatz AI, your agent runs Add sandbox in Daytona. Describe the whole flow and it is built, tested on every scenario and kept running.
What the catalog holds today. Ask for anything missing and your agent reads the API documentation and adds it.
Build solutions, not workarounds.
What do you want Hatz AI and Daytona to do together?
Ask the assistant
Connect your AI client
Give your AI client this address.
https://mcp.apiant.aiOne connection does both: ask your client to act in an app once, or have it build an automation that keeps running. Any client that takes a remote MCP server. Nothing to install. Create your free account, then sign in once in your browser.
Set it up in your client
Claude Code
Run this in the directory you want to work in.
claude mcp add --transport http -s project apiant-ai https://mcp.apiant.aiStart Claude Code there, approve the server, and sign in in the browser page it opens.
Claude Code guide (opens in a new tab)Claude, web and desktop
Open Customize, then Connectors, then Add custom connector, and paste the address. On Team and Enterprise an owner adds it first.
Setup guide (opens in a new tab)Cursor
Add the address to your MCP configuration as a server URL. Cursor signs you in in your browser.
Setup guide (opens in a new tab)Zed
Open Settings, then AI, then MCP Servers, then Add Server, then Add Remote Server.
Setup guide (opens in a new tab)Codex and the ChatGPT desktop app
Open Settings, then MCP servers, then Add server, and choose Streamable HTTP. From the terminal, Codex takes the address with its own add command and then signs you in.
Setup guide (opens in a new tab)Grok
Open grok.com/connectors, choose New Connector, then Custom, and paste the address. Grok signs you in in your browser.
Setup guide (opens in a new tab)Any other MCP client
Paste the address where the client asks for a remote MCP server URL, and name the server apiant-ai where it lets you. APIANT's skills reach the client over the same connection.
Setup guide (opens in a new tab)Example flows
What Hatz AI can start in Daytona
When New File in Hatz AI
then Add sandbox in Daytona
When New File in Hatz AI
then Add snapshot in Daytona
Starting points drawn from the triggers and actions in the catalog today. Describe the flow you need, at any depth, and your agent builds it and tests every scenario before it ships.
Everything your agent can do with Hatz AI and Daytona
Triggers and actions 1 trigger · 29 actions
Trigger
New FileTriggers when a new file is uploaded to your Hatz AI account.
Action
Create Chat CompletionSends a prompt to a Hatz AI model and returns the model's reply.
Action
Get AgentReturns one Hatz AI agent, with its instructions, tools and model.
Action
Get AppReturns one Hatz AI app, with its prompt and the inputs it expects.
Action
Get File StatusReturns whether an uploaded Hatz AI file has finished processing.
Action
Get My UsageReturns how many Hatz AI credits you have used in a period.
Action
Get WorkflowReturns one Hatz AI workflow, with its steps and the inputs it expects.
Action
Get Workflow Job StatusReturns the status of a Hatz AI workflow run and the output of each step.
Action
List AgentsReturns the Hatz AI agents available to you, with their names, instructions and models.
Action
List AppsReturns the apps and workflows in your Hatz AI workspace, optionally filtered by name or type.
Action
List FilesReturns the files uploaded to your Hatz AI account, with their names and sizes.
Action
List ModelsReturns the AI models available in your Hatz AI workspace, with their names, developers and token limits.
Action
Run App QueryRuns a Hatz AI app with the inputs you give it and returns the app's answer.
Action
Run WorkflowStarts a Hatz AI workflow with the inputs you give it and returns the job ID to check its progress.
Action
Add sandboxCreates a new Daytona sandbox from a snapshot or build definition, with optional resources, labels, environment variables and network settings.
Action
Add snapshotCreates a new snapshot from a container image or Dockerfile, which sandboxes can then be started from.
Action
Add volumeCreates a new storage volume in your Daytona organization that sandboxes can mount.
Action
Archive sandboxArchives a stopped sandbox, moving its filesystem to cheaper storage until it is started again.
Action
Delete sandboxDeletes a Daytona sandbox by its ID or name and returns the sandbox record as it is being destroyed.
Action
Delete snapshotDeletes a snapshot from your Daytona organization.
Action
Delete volumeDeletes a Daytona volume. The volume must not be in use by any sandbox.
Action
Get sandboxReturns the details of a sandbox, including its state, resources, labels and settings.
Action
Get snapshotReturns a snapshot's details, including its state, image, resources and regions, looked up by ID or name.
Action
Get volumeReturns the details of a volume, including its name, state and timestamps.
Action
List sandboxesReturns the sandboxes in your Daytona organization, optionally filtered by name, ID, labels, state, snapshot, region, class, resources, public status and dates, and sorted.
Action
List snapshotsReturns the snapshots in your Daytona organization, optionally filtered by name or by the sandbox they were created from.
Action
List volumesReturns all volumes in your Daytona organization, optionally including deleted ones.
Action
Start sandboxStarts a stopped or archived sandbox, or resumes a paused one, and returns the sandbox.
Action
Stop sandboxStops a running sandbox, optionally forcing it to shut down immediately. Returns the sandbox record.
Action
Update sandbox labelsReplaces all labels on a Daytona sandbox with the key-value pairs you supply.
No trigger or action matches that. Ask your agent to add it: it reads the API documentation and builds what you describe.
Each app on its own
Reviews
What our customers say
More from Hatz AI
Hatz AI to HubSpotHubSpot is your all-in-one stop for all of your marketing software needs.
Hatz AI to SalesforceSalesforce is a leading enterprise customer relationship management (CRM) platform.
Hatz AI to SlackSlack is a messaging platform for teams. Post messages, manage channels, users, reminders, and react to...
Hatz AI to MailchimpMailchimp marketing automation and email platform.
Hatz AI to StripeStripe is a payment processing platform for online businesses.
Hatz AI to ShopifyShopify is a commerce platform for online stores and retail point-of-sale.
More into Daytona
HubSpot to DaytonaHubSpot is your all-in-one stop for all of your marketing software needs.
Salesforce to DaytonaSalesforce is a leading enterprise customer relationship management (CRM) platform.
Slack to DaytonaSlack is a messaging platform for teams. Post messages, manage channels, users, reminders, and react to...
Google Sheets to DaytonaGoogle Sheets is Google's online spreadsheet app for creating, editing and sharing spreadsheets.
Gmail to DaytonaGmail is Google’s email service, featuring spam protection, search functions, and seamless integration with...
Google Calendar to DaytonaGoogle Calendar is a time management tool providing scheduling features, event reminders, and integration...
Questions
Hatz AI and Daytona, answered
What can start an automation from Hatz AI?
Any of Hatz AI's 1 trigger in the catalog, including New File. Describe the moment in plain language and your agent picks the right one.
What can your agent do in Daytona when something happens in Hatz AI?
Any of Daytona's 16 actions, including Update sandbox labels, Add sandbox, Add snapshot and Add volume. Your agent maps the data both ways and tests every scenario before it ships.
Can it also run from Daytona to Hatz AI?
Daytona has no triggers in the catalog today, so automations start in Hatz AI. If you need the other direction, ask: your agent reads Daytona's API documentation and adds it.
Do I have to build a connector for Hatz AI or Daytona?
No. Both are in the catalog with their triggers and actions. You describe the automation; your agent builds it, tests every scenario and keeps it running.
Can my AI client use Hatz AI and Daytona without building an automation?
Yes. With your AI client connected to APIANT, ask it to do something in either app once and it runs that action on the spot. Ask for an automation and your agent builds it, tests every scenario and keeps it running. One connection covers both.
What happens when something fails?
Your agent works that out for you. It plans the failure paths along with the happy path, then tests every scenario before it ships.
Is there a free plan?
Yes. Every plan includes the agent, including free, and building from your own AI client spends no assistant credits.