A home for the
tools your
agents build.
Like Vercel, but inside your company.
Any agent builds it. Your whole team uses it.
Admins stay in control.
The problem: Anyone can build a tool with AI now, but it has nowhere to live and run.
The solution: Harbor gives AI-built tools a home, with everything they need to run. Every teammate and every agent can use them, securely, in your own cloud.
An app is one folder.Your agent writes it. Harbor runs it.
Ask Claude for a discount approval app. It’s live today.Claude writes the folder. Harbor tests it, then runs it at its own address behind your company’s sign-in.
Built in Claude. Used from ChatGPT.Any agent can call the desk’s actions through Harbor’s MCP server, so Jared’s 30% still goes to finance, whichever agent he asks.
The app’s own agent researches every request first.Each new discount request starts it. It reads the customer’s Salesforce history and usage before finance sees the request.
Finance approves in Slack. The app updates Salesforce.A workflow waited for Monica in finance to say yes, then wrote the new price to Salesforce.
A deal closes at the wrong price. The app catches it.Bachmanity closed at 35%, not the approved 30%. The moment Salesforce says so, a trigger checks the price and flags it to finance.
Change the rule once. Every agent follows it.The tests run on the new release before anyone uses it, and every approval so far stays.
Anything can be an app.Tools any agent can call for your order system, a company brain every agent searches and adds to, partner payouts on the 1st of the month, a router for every email that reaches sales, or checks on every file a supplier sends, each made from one request to an agent.
deal-desk
README.mdWhat it does, for people and agents
app.tsIts name, owner and connections
uiThe screens your team opens
actionsWhat people, agents and apps can call
dataTables, shared or personal
triggersWhat starts it: an event, a time, a webhook
workflowsMulti-step jobs that pick up where they stopped
agentsIts own AI, with the tools and limits you set
skillsInstructions that teach any agent to use the app
testsChecked before every release
For admins: today every agent connects to every system on its own.
Harbor sits in between. Connect each system once.
Every app your agents build lives there too, with your skills.
What one agent builds runs in harbor, for the whole team.
Share what’s in harbor with your team.
Each person’s agent reaches only what’s shared with them.
All of it in one place, in your own cloud, behind your sign-in.
Connect your apps once, not once per agent.
Agents can work in sites with no API, without your password.
Write a process once. Every agent follows it.
Today every person connects their own Claude, ChatGPT and Cursor to Salesforce, Gmail and Slack. With Harbor, an admin connects each one once, and every agent connects to Harbor at one address. People still see only what they could see before, and every call is logged.
Supplier portals and old internal sites need a browser. Harbor signs the agent in, and the agent never sees the password.
Pricing rules, brand voice, refund policy: write them once as skills, and every agent follows them, instead of each person pasting them into chats.
Not an artifact. Not a Site.
They can look alike. They’re built different.
Claude artifacts and ChatGPT Sites are
Pages inside Claude or ChatGPT.
People open them and use them.
For people on that AI plan, or the public.
Run on Anthropic’s or OpenAI’s servers.
Harbor apps are
Software of their own, outside any AI app.
People, agents and other systems all use them. Their actions are tools any agent can call.
For everyone at your company, whatever AI they use, or none.
Run in your own cloud, next to your internal systems.
Checked against Anthropic’s and OpenAI’s documentation on 17 October 2026. Sites is in public beta.
Questions
Something else? Ask us.
What is a Harbor app?
Software your agent builds for your team: an approval tool, a shared tracker, a report that runs every morning. Your agent writes the code. Harbor runs it in your cloud, behind your company login, for the people and agents you share it with.
What is the Harbor gateway?
The one place your agents reach everything at work. You connect your tools to Harbor once: Salesforce, Gmail, Slack, an internal API. Your skills, your apps and resources like a signed-in browser live there too. Then you connect each agent to Harbor’s one MCP address, and it can use all of it, with each person’s own access. An app’s actions show up as tools any agent can call.
Does everyone need a Claude or ChatGPT seat?
No. Anyone in your company directory can open an app shared with them. Agents are only needed to build and change apps, and to use them from chat.
Which agents work with it?
Any agent that speaks MCP: Claude, ChatGPT, Copilot, Cursor, Codex and others. An app built in one can be used from all of them.
How is a Harbor app different from a Claude artifact or a ChatGPT Site?
An artifact or Site is a page inside one AI product. A Harbor app is software of its own: a page, a database your team shares, tools any agent calls, or jobs that run on a schedule or when something happens, for everyone at your company.
How do people sign in?
With your company login: Entra, Okta or Google. Admins see every app and who uses it, and app code never sees a credential.
Where does the data live?
In Postgres, in your own cloud or on your own machine, next to your internal systems.
What happens when an agent changes an app?
Harbor installs, type-checks, builds and runs the app’s tests. A release that fails never goes live, and the app’s data stays.
Is Harbor open source?
Yes. It’s in private preview now. Join the waitlist and we’ll invite your company.
Runs in your cloud, behind your login.
Harbor is open source. You install it in your own cloud account, or on one computer just for you, so your apps and their data stay with you. Everyone signs in with the login your company already uses: Entra, Okta or Google. Admins see every app and who uses it. Apps never see a password or API key, and every action is logged.