Your owncoding agent

An AI coding agent for your own machine and browser, with subagents, dynamic workflows and Claude Code compatible hooks.

Create account Sign in

Desktop app and web workspace.
The agent runs on the machine that hosts it.

⌄ Account reviewCompleted

ReviewCompleted

Review account codeDone

Review account testsDone

SynthesisCompleted

Combine findingsDone

Example session: a workflow in the chat.

Work with
a whole crew

Delegate a piece of the task, or orchestrate the whole run. Keep the work in one conversation.

Workflow script fragment

phase("Review");
const findings = await parallel([
  () => agent("Review account code"),
  () => agent("Review account tests")
]);

phase("Synthesis");
await agent(`Combine: ${findings}`);

Subagents, coordinated

Start a fresh child agent or fork the current conversation. Run it in the foreground or background, with tools to message it, wait for it and stop it.

Dynamic workflows use a JavaScript orchestration script with agent(), parallel(), pipeline() and phase(). Claude Code dynamic-workflows meta blocks are supported. Runs appear live in the chat.

Plan before edits

In plan mode, the agent researches read-only. It then presents a plan for your approval before it edits anything.

The plan stays part of the conversation, so you can review the proposed work before it starts.

Hooks that fit

Use Claude Code compatible command hooks, configured in a hooks.json file.

SessionStart, UserPromptSubmit, PreToolUse, PostToolUse, Stop, SubagentStart and SubagentStop.

Keep work moving

Track todos. Bring skills in SKILL.md folders. Use /goal to keep the agent working until an objective is met.

Background jobs and schedules handle work beyond a turn. Git worktrees and agent teams are optional.

Two models.
One account.

Both models are available through your devvi.sh account, each with a 1M-token context window.

DeepSeek V4.1 Flash

Work with text and images.

1M-token context

DeepSeek V4 Pro

Stronger agentic coding, knowledge and difficult reasoning. Suited to complex or quality-critical tasks.

1M-token context

Credit, without
a clock

One devvi.sh account with prepaid credit: pay only for what you use, with no subscription, and keep whatever you do not spend.

Start with

in credit once you confirm your email

Usage-based. Each request is charged from your balance at devvi.sh rates for the model you use, and your usage page lists every charge.

$5 to $500. Add credit by card through Stripe whenever you need more.

Top up your credit

Your machine.
Clear boundaries.

Telemetry is off by default.

Model requests are routed only to zero-data-retention hosts.

The provider key stays on the devvi.sh server and is never sent to the app. A signed-in account needs no API key of its own.

The agent works on your own machine, in the desktop app or the browser workspace.

Get the app

The desktop app for macOS, on Apple silicon or Intel, and for Windows x64.

Download the app

Run with care

devvi.sh is experimental developer-preview software. The agent executes model-written commands on the machine that hosts it.

Use the least privileges needed, preferably in a disposable VM or container. Keep backups and review proposed commands before allowing them to run. Permission controls do not guarantee isolation or prevent damage.