Integration
Connect Letta to TypeSafe
When New Agent fires in Letta, your agent runs Ask a Yes/No Question in TypeSafe. 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 Letta and TypeSafe 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 Letta can start in TypeSafe
When New Agent in Letta
then Ask a Yes/No Question in TypeSafe
When New Message in Letta
then Classify Into Options in TypeSafe
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 Letta and TypeSafe
Triggers and actions 3 triggers · 16 actions
Trigger
New AgentTriggers when a new agent is created in your Letta account.
Trigger
New MessageTriggers when a new message is added to the chosen Letta agent's conversation.
Trigger
New ProjectTriggers when a new project is created in your Letta account.
Action
Add agentCreates a new Letta agent with the model, memory blocks, tools and system prompt you choose.
Action
Add archival passageAdds a passage of text to an agent's archival memory, with optional tags and timestamp.
Action
Add memory blockCreates a new memory block that can be attached to Letta agents, with a label and its contents.
Action
Create Agent From a TemplateCreates one or more Letta agents from a saved agent template and returns the new agent IDs.
Action
Create IdentityCreates an identity (a user, organization or other entity) in Letta that agents and memory blocks can be attached to.
Action
Find archival passages by querySearches an agent's archival memory by semantic similarity and returns the matching passages.
Action
Get agentReturns a Letta agent's details, including its system prompt, model and optionally its memory blocks, tools and tags.
Action
Get IdentitiesReturns the identities in your Letta project, optionally filtered by name, identifier key or type.
Action
List agentsReturns the agents in your Letta account, optionally filtered by name, tags, project, template, identity or last stop reason.
Action
List memory blocksReturns the core memory blocks attached to a Letta agent.
Action
List toolsReturns the tools available to agents in your Letta organization, optionally filtered by name, type or ID.
Action
Update agentUpdates an existing Letta agent's name, system prompt, model, tools, memory blocks, tags and other settings. Only the fields you fill in are changed.
Action
Update memory blockUpdates a memory block's value, label, character limit, description, tags or other settings.
Action
Ask a Yes/No QuestionAsks a yes/no question about a piece of content and returns how likely the answer is yes, as a number from 0 to 1. Use it to check a condition that needs judgement rather than an exact match, such as whether a message sounds urgent or whether a review is a complaint.
Action
Classify Into OptionsSorts a piece of content into one of the options you define and tells you how certain the choice is. Use it to route a ticket to a team, tag an enquiry by intent, or pick a category, and branch on the confidence so unclear cases go to a person instead.
Action
Score Against LevelsRates a piece of content against levels you describe, from lowest to highest, and tells you how certain the rating is. Use it to grade severity, sentiment, lead quality or risk on a scale of your own wording rather than a yes/no answer.
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 Letta
Letta to SalesforceSalesforce is a leading enterprise customer relationship management (CRM) platform.
Letta to SlackSlack is a messaging platform for teams. Post messages, manage channels, users, reminders, and react to...
Letta to MailchimpMailchimp marketing automation and email platform.
Letta to StripeStripe is a payment processing platform for online businesses.
Letta to ShopifyShopify is a commerce platform for online stores and retail point-of-sale.
Letta to QuickBooks OnlineQuickBooks Online accounting — manage customers, invoices, bills, payments, vendors, expenses, and more via...
More into TypeSafe
HubSpot to TypeSafeHubSpot is your all-in-one stop for all of your marketing software needs.
Salesforce to TypeSafeSalesforce is a leading enterprise customer relationship management (CRM) platform.
Slack to TypeSafeSlack is a messaging platform for teams. Post messages, manage channels, users, reminders, and react to...
Google Sheets to TypeSafeGoogle Sheets is Google's online spreadsheet app for creating, editing and sharing spreadsheets.
Gmail to TypeSafeGmail is Google’s email service, featuring spam protection, search functions, and seamless integration with...
Google Drive to TypeSafeGoogle Drive is a cloud storage solution for uploading, sharing, and collaborating on files across devices...
Questions
Letta and TypeSafe, answered
What can start an automation from Letta?
Any of Letta's 3 triggers in the catalog, including New Agent, New Message and New Project. Describe the moment in plain language and your agent picks the right one.
What can your agent do in TypeSafe when something happens in Letta?
Any of TypeSafe's 3 actions, including Ask a Yes/No Question, Classify Into Options and Score Against Levels. Your agent maps the data both ways and tests every scenario before it ships.
Can it also run from TypeSafe to Letta?
TypeSafe has no triggers in the catalog today, so automations start in Letta. If you need the other direction, ask: your agent reads TypeSafe's API documentation and adds it.
Do I have to build a connector for Letta or TypeSafe?
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 Letta and TypeSafe 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.