Build and automate with the models you choose

Codewhale gives you agents that can build software, work with your files, and turn repetitive tasks into reusable workflows. Tell them what you want to accomplish and choose the hosted or local models that suit the job, with the freedom to switch providers as you go.

Get Codewhale Explore the product

Codewhale v0.9.12 terminal, build 171acee689aa: a new session with the whale mark, message composer, Full Access and Operate mode, two scheduled tasks, 21 MCP servers connecting, and GLM-5.3 at max effort. — Terminal previewv0.9.12 development build
cwLatest release v0.9.12Unreleased v0.9.13MIT

What you can do with Codewhale

Start with a project, a question, or a task you want to automate, then work with one agent or give parts of a larger job to several.

Build something

Describe what you want to make and work with agents that can read your code, edit files, run commands, and check the result.

Automate everyday work

Create scripts and workflows for tasks you repeat, so you can run them again from the terminal whenever you need them.

Work with different models

Use hosted or local models for your agents, with different models and roles handling the parts of a job they are suited to.

02 / Your models

A choice of models for every task

Connect directly to a hosted provider, use a gateway to access several, or run a model locally, then choose which model each session uses as you work.

Explore models and providers

Hosted: Your own API key, saved with codewhale auth set --provider <id>
Gateway: One endpoint for many models, provider still chosen by you
Local: vLLM, SGLang, Ollama on localhost — usually no key
Plan · Work · Operate: Ask · Auto-Review · Full Access

03 / Getting started with Codewhale

Getting started with Codewhale

Install the published release, connect a model, then try one task in your project folder. A team of agents is optional; start with one and add more when the work can be split.

01
Install Codewhale
The command below installs the latest published release on macOS or Linux. Use the install guide for Windows, package managers, or building the unreleased source candidate.
```
curl -fsSL https://codewhale.net/install.sh | sh
```
Full install guide →
02
Connect your model
Model replies need a connection to a hosted or local model. Use your own provider key, as in the DeepSeek example below, or follow the provider guide for other services and local models. Offline setup does not require a key.
```
codewhale auth set --provider deepseek
```
Choose a provider →
03
Give it a task
Open Codewhale in your project folder. Try /mode plan and ask it to explain the project, then use /mode work when you want edits and commands. Shift+Tab changes the approval setting; /provider and /model change the model connection.
```
codewhale
```
Modes and permissions →
04
Add a Fleet when you need one
When a task would benefit from several models and roles, run /fleet setup inside Codewhale to put a team together. You can see the saved Fleet from your shell with codewhale fleet status.
```
/fleet setup
codewhale fleet status
```
Fleet and Workflow docs →

Read the getting-started guide Look up a term

04 / Get Codewhale

Where you can use Codewhale

You can use Codewhale in your terminal today while we build the web app, desktop app, and cloud computers.

Terminal: ReleasedGitHub release binaries for Linux, macOS, and Windows; npm and Cargo are alternatives. Android on Termux is a preview.
Web app: Development previewAccount access and browser pairing in the development preview.
Desktop: Development buildThe macOS app is in development; a public download is coming later.
Cloud computers: In developmentHosted computers for running your tasks.

You can use the terminal without a Codewhale account, and any hosted model usage is billed by your provider.

Create an account

Ways to work with Codewhale

TUIRun codewhale to work interactively in your terminal

codewhale execRun a task from a script or CI job

Local web clientRun codewhale web to open a browser client for the same local Runtime

Plugins and MCPAdd tools to the Runtime; review and enable plugins before use

FleetSeveral agents on one job

Explore integrations

Install Codewhale on macOS or Linux

curl -fsSL https://codewhale.net/install.sh | sh

GitHub Releases · BinariesnpmCargoDockerNixWindowsAndroid / TermuxChina mirrors

Read the install guide

Help make Codewhale better

Whether you have found a bug, have an idea for a feature, or want to send your first pull request, we would like to hear from you and work together on what comes next.