Quick start

Get a Casama server running, sign in, and give your first bot a task. With Docker already installed, this takes about 15 minutes, most of it building images.

1. Start a server

You need a machine with Docker. For a trial on your own computer:

git clone https://github.com/stackwares/casama && cd casama
./install.sh --local

For a server other people reach over the internet, point a domain at the machine first, then:

./install.sh --domain casama.example.com

The installer checks Docker, generates every secret, builds and starts the stack, and waits until it's healthy. It prints the address when it's done. See Self-hosting for requirements, every option and production advice.

Prefer not to use a terminal?

The desktop app can run a server on the computer it's installed on: on the sign-in screen, choose More options → Run Casama on this computer.

2. Install a client

• Apps: iOS, Android, macOS, Windows, Linux and the web.
• CLI: brew install stackwares/tap/casama, or download a binary from the releases page. See CLI.

3. Sign in to your server

In the app:

1. Tap Sign in or create account.
2. Tap More options, then the Server button, and enter your server's address (for example https://casama.example.com, or the address --local printed).
3. Tap Continue with email → Use a password instead → New here? Create an account, and enter an email and password.

The first account on a server becomes its owner.

Email links, Google and Apple

Signing in with an emailed link needs the server to send email, and Google and Apple sign-in need them set up on the server. A new server has neither, so start with a password. See Configuration.

With the CLI:

casama config --api-url https://casama.example.com
casama signup --email you@example.com

4. Meet your first bot

The first time you sign in, the app opens a welcome chat. It creates a workspace and a personal bot for you, then asks what you'd like help with first. Along the way it asks for a model:

• Continue with ChatGPT to use a ChatGPT plan you already pay for,
• Add a model key for OpenRouter, OpenAI, Anthropic, Google, xAI or another provider, or
• Use a local model, for example one served by Ollama.

Answer the questions (or skip them) and the bot suggests a first task. Prefer to set things up yourself? Choose Set up manually.

With the CLI:

casama org create "My team" && casama org use my-team
casama credential add --provider openrouter      # prompts for the key
casama bot create Ada --credential <id>
casama chat Ada "Research the top three open-source vector databases and write a comparison to report.md"

No API key?

Run a model locally with Ollama and add it as an OpenAI-compatible endpoint, using an address the server can reach (on a self-hosted server, the Ollama machine's network address rather than localhost, allowed with OUTBOUND_ALLOW_CIDRS; see Configuration): casama credential add --provider openai_compatible --base-url http://192.168.1.20:11434/v1.

5. Give it real work

Try a task that needs its computer:

Find the five most-starred Rust web frameworks on GitHub, compare their latest releases, and save a table to frameworks.md.

Open the bot's computer to watch it work. When it wants to do something risky, an approval appears in the chat and as a notification.

Next steps

• Connect your tools: Apps and connections
• Put it on a schedule: Routines and triggers
• Decide what it may do on its own: Autonomy and approvals
• Invite your team: Workspaces and teams
• Use it from your coding tool: Connect AI apps