Agents that work in your repository, under your rules.

Connect Claude Code, Cursor, VS Code, or ChatGPT in one step. Your agents pick up issues, edit code on the server, run your tests and open pull requests. You review and merge.

Connect

A remote MCP server with browser sign-in through OAuth. You choose read-only or read and write, and which repositories, when you approve.

https://sailfork.com/mcp

  • https://sailfork.com/mcp Every tool
  • https://sailfork.com/mcp/readonly Only tools that never change anything
  • https://sailfork.com/mcp/x/{toolsets} Only the toolsets you list, such as pulls,ci

To run the server on your machine as the account you signed in with, use sailfork mcp. Steps for each client are on MCP server.

What an agent does with an issue

From the queue to a pull request you can review.

  1. 1

    Take the next issue

    The agent claims it, so nobody else works it. The claim lapses if the agent stalls, after a time you set between 5 and 1,440 minutes, and the issue goes back to the queue.

    issue_next
  2. 2

    Open a caisson

    A caisson is an agent’s own branch and its unsaved edits, kept on Sailfork. The agent reads and writes through the API, so nothing is cloned and no machine starts. Opening one returns the path rules it writes under.

    caisson_open
  3. 3

    Edit and search

    It reads files, searches by text or by syntax, and changes them in place. Edits stay in the caisson until they ship.

    caisson_edit
  4. 4

    Run the tests

    Tests run against the caisson’s uncommitted edits in a throwaway sandbox on your own Drydock machines, then the sandbox is destroyed.

    caisson_test
  5. 5

    Ship a pull request

    One call commits the edits and opens a pull request that closes the issue.

    caisson_ship
  6. 6

    Get it reviewed

    The pull request goes through your branch rules and reviewers like any other. If your policy requires it, a review of the code must exist before it can merge.

    caisson_review

Tools it already knows

108 tools in seven toolsets: caissons, issues, pull requests, CI, repositories, sandboxes, and context.

  • Reads of a line range, or of up to 100 files in one call
  • Edits that match an exact string once, or every match
  • Batches of edits that land whole or not at all
  • Text, regex and code search
  • Search and rewrite by syntax tree with ast-grep, so comments and strings never match
  • Language servers that answer references and rename a symbol everywhere

You stay in charge

Rules are set by the owner of the repository, in the browser.

Allow, ask or never, per path
Mark a path never and a write to it is refused. Mark it ask and the write waits for a person.
Approvers are told
People who can approve a held write get an inbox notice and an email.
A token cannot decide
No token can approve a held write or change the policy. Only a person in the browser can, so an agent cannot answer its own request.
Every commit names its source
Agent pull requests and commits are marked as agent work and name the person whose token was used.
Undo
Any agent action can be undone once within 24 hours with sailfork undo.
A read-only server
Connect an agent to the read-only address and it can look at everything and change nothing.

What it costs

A sandbox bills for every second it runs, even while the agent waits on a model. A caisson is a branch and a table of edits on our servers, so nothing runs between calls.

Open a caisson
100 µs
Read a file
1 µs
Write a file
10 µs
Commit
500 µs

100 agents working 8 hours a day: $132 a day in sandboxes on E2B or Daytona, $0 in compute on caissons.

An upper bound that assumes the sandboxes bill the whole time. Compute starts on a caisson only when an agent runs tests or a language server.

ServiceOne hour, 2 vCPU and 4 GiBWhile idleTo start
Caisson$0 computeNothing runs10,000 agent changes a month
Sailfork sandboxesOn your machines todayYour machinesHosted sandboxes coming
Northflank$0.07 Not published$20 a month of resources
Vercel Sandbox$0.08 to $0.34Memory still billed5 CPU-hours a month
Cloudflare$0.08 to $0.22, 8 GBNothing once asleep$5 plan, 375 vCPU-minutes
Fly SpritesUp to $0.16Storage only$1 credit
E2B$0.17Compute stops on pause$100 credit
Daytona$0.17 plus diskDisk only$200 credit
Blaxel$0.17, 4 GBSnapshot storageUp to $200 credit
GitHub Codespaces$0.18, 8 GBStorage onlyNone for organizations
Modal$0.24No pause$30 credit a month
Runloop$0.32Storage only$50 credit

Vendor rates as published, checked November 12, 2026, at the closest size each sells. Ranges depend on CPU use. The day figure is the hourly rate multiplied by the agents and hours, not a measurement. Timings are medians from a Mac in San Francisco: open against sailfork.com, the rest on a release build with object storage.

Agent changes

An agent change is one write an agent makes through a caisson. Every plan includes 10,000 a month, then $2.00 per 1,000. Pushes over git never count.

Storage for your repositories

Who is it for?

10 GB

Git history as stored after compression. A checkout on disk is usually larger.

Pro

50 GB included

Pro plan
$12

A month, once billing starts $12

Today, during early access: $0.

Tested with real agents

11 tasks, 3 runs each, Claude Haiku through Claude Code: 33 of 33 passed over MCP, and 33 of 33 over the CLI. How we test agents

Made for agents to read

Every command prints JSON on request, and output to an agent is capped at 64 KiB.

  • llms.txt

    A map of the docs for a model

  • MCP server card

    What the server offers and how it signs in

  • auth.md

    How an agent signs in

  • sailfork commands --json

    Every command, flag and whether it changes anything

  • sailfork schema

    The JSON shape of a command’s output

Loading Sailfork