Documentation platform for people and AI agents, with cited answers, self-updating docs and an MCP server
TrustList summary
Not yet independently verified. The launch date rests on the company's own Y Combinator launch post of 9 October 2026. Every detail comes from the company's own pages, so the claims about scale and the founders' research are its own and unchecked. Other products called Maritime exist in shipping software; this listing is the AI agent cloud company at maritime.sh. No independent report was found. We will update this when it can be confirmed, and remove this note.
Maritime is a managed cloud for running AI agents, each on its own persistent virtual machine. It was founded in 2026 in San Francisco and is part of the Fall 2026 Y Combinator batch. The company launched it on Launch YC with the line that it can run millions of agents.
What Maritime does
Each agent gets an isolated computer where it can run code, install software and use a browser. Files, memory, installed software and logins persist between tasks. Maritime handles hosting, scaling and putting agents to sleep and waking them, and it provides tools to inspect, debug and fix a single agent. The computer can be a Linux machine, a Windows desktop or a virtual Android phone.
There are two ways to use it. Agent code can run inside a Maritime machine, or the agent can stay on the customer's existing backend and use MCP, the Model Context Protocol, to control a Maritime computer.
Who it is for
The launch post addresses teams that build and sell AI employees, personal assistants and similar products where every customer has their own agent. The founders say the idea came from hosting hundreds of agents during research at MIT, where most of their time went on setting up and debugging environments. The scale claims, including millions of agents, are the company's own and we have not tested them.
Key facts
- Maker: Maritime, founded 2026, San Francisco, team of three at the time of the Y Combinator listing
- People: Maria Gorskikh (founder and CEO) and Aryaman Shrivastava (founder and CTO), both with MIT research backgrounds
- Pricing: from $1 per agent per month; three agents hosted free
- Environments: Linux, Windows desktop, virtual Android
- Website: maritime.sh (not reachable from our checking tools; details taken from the Y Combinator pages)
Categories & features
- Artificial Intelligence Software
- API
- United States
- California
- San Francisco
Trust Score
An earned signal from verification, reviews, awards, transparency and engagement - the vendor can't buy it.
Updated 10/10/2026
Request a demo or quote from Maritime
Reviews
Questions & answers
No questions yet. Be the first to ask about Maritime.
Maritime alternatives
Similar listings buyers compare against this one.
API that turns a URL into Markdown written by a vision model, with the page's hidden JSON and a citable snapshot. Priced at $1 per 1,000 fetches per its launch post and pricing section.
A framework for command-line tools that agents load only when needed, so connecting many services costs little context
Post-mortem debugger for Windows x86 and x64 crash dumps, exposing its findings to AI coding assistants over MCP
An AI coding agent for C, C++ and CUDA that works from the real build and call graph, takes bugs from Slack, Jira or the command line, and returns a pull request with build, test, sanitizer and performance results attached.
A Bolt.new agent that runs on open-source models and gives more usage in return for training data
Debugging tool that lets AI coding agents inspect live backend services without redeploying
MIT-licensed runtime of single-request serverless actors, each with its own SQLite database and WebSocket server, written in TypeScript on a Rust runtime; run on Terse Cloud or self-hosted. Billed by the second for CPU and memory requested.
More on TrustList
Everything here links back to the same verified catalogue. Pick your next stop.
- Write a reviewHelp other buyers decide
- CompaniesAgencies, consultancies and IT service providers, ranked by verified reviews.
- ArticlesGuides, comparisons and research from the editorial desk and the community.
- AwardsAnnual recognition decided by verified reviews and an independent jury.
- LaunchesNew products and releases, voted up by the community every day.
- AI ModelsBenchmark scores and community ratings for every major model.
- RequestsBuyers describe what they need; vendors respond directly.
- PeopleReviewers, authors and makers with public profiles.
- ComparePut up to four listings side by side before you shortlist.