Describe the change.
Dev ships it.
Hanzo Dev is a coding agent. It reads your repository, makes the change, runs the tests and shows you the diff — in your terminal, on the web, in the cloud and in Slack.
Read the docs →One agent
Wherever the work is.
The same agent, the same models and the same account in every place it runs.
Terminal
devIn any repository. It reads the code, makes the change and runs commands in a sandbox. Bare hanzo opens the same session.Web
hanzo.ai/devDescribe an app. Dev writes it, runs it and deploys it, with the database, the sign-in and the storage already there.Cloud
dev cloud execHand a task to Hanzo’s cloud and close the laptop. dev cloud diff shows what it did; dev cloud apply puts it in your checkout.Slack
An org admin connects the workspace in Dev’s settings, and the team talks to it from their channels.Install
One line, three ways.
Linux, macOS and Windows. Dev updates itself the way it was installed.
curl -fsSL https://hanzo.sh | shnpm install -g @hanzo/devbrew install hanzoai/tap/hanzo-devdev login # pick an account: Hanzo is the default
dev login --hanzo # straight to your Hanzo account
dev login --with-api-key # or paste a Hanzo API key, hiddenModels
Enso by default. Any model by name.
Dev starts on enso-auto through api.hanzo.ai, so every call is metered on your Hanzo account. Every model Hanzo serves is a flag or a /model away.
dev # enso-auto, through api.hanzo.ai
dev --model enso-ultra # name any model Hanzo serves
/model zen5-coder # or switch inside a sessionController
Kai decides. Dev does.
Kai is Dev’s own controller, not an adviser. At each step it returns an operation Dev can run, or says plainly that it abstains. The cheapest step that holds is the one taken.
Proof
Built to be checked.
Nothing counts as done because a model said so.
Verified, not predicted
A step is settled by what the verifier records — the exit status, the tests, the diff — never by what anything expected.Bound to the revision
Preconditions are checked just before an action runs, and an edit voids every decision made against the files as they were.A ledger you can replay
Every decision, fallback, run and verification is a line with a stable id and its reason, credentials redacted, so its time and cost can be read back.Sandbox
Inside the fence you set.
Commands run in a sandbox and are approved inside it. Ask before every action, or lift the fence for one run. A repository’s own tool servers stay off until you say you trust it.
hanzo dev --ask # ask before each action
hanzo dev --no-sandbox # run unconfined, for this run only
hanzo dev --project-mcp # also load this repository's .mcp.jsonGen
Dev is our agent. Gen runs any agent.
Hanzo Gen is the harness: Claude Code, Codex, Cursor and the rest, on Hanzo’s tools and models and linked to your account. Dev is the agent it opens when none is named.
Open source
Read every line.
Dev is Apache-2.0 on GitHub. Build it, change it, send a pull request — hanzoai/dev.
Questions
Asked plainly.
What does it cost?
Which systems does it run on?
How does it update?
Can I bring a key instead of signing in?
How is Dev different from Gen?
Read
The agent, its controller, its source.
Where to start, what Dev thinks with, and the code.