> ## Documentation Index
> Fetch the complete documentation index at: https://to11.ai/docs/llms.txt
> Use this file to discover all available pages before exploring further.

# Quickstart

> Sign in, create a project, render a chat prompt with an API key, install the project's skills with the CLI, and see your Claude Code sessions.

In this tutorial you sign in to to11 and create a project, render a chat prompt from code with an API key, link a repository to the project with the to11 CLI, and see one of your Claude Code sessions in the dashboard.

You need:

* a terminal on macOS or Linux, and [Homebrew](https://brew.sh) on macOS;
* Node.js or Python 3.10 or later, for the SDK step;
* a git repository on your machine and Claude Code, for the CLI and sessions steps.

## 1. Sign in and create your project

Open [app.to11.ai](https://app.to11.ai) and sign in with GitHub, Google, or Microsoft.

The first time you sign in, onboarding asks for your name and then creates three things: an **organization** for your company, a **workspace** inside it, and a **project** inside the workspace. Name the project after the git repository you will use in step 5, for example `web` for a repository in a folder called `web`. [Core concepts](https://to11.ai/docs/get-started/concepts.md) explains how the three levels fit together.

When onboarding finishes, the dashboard opens on your project's **Sessions** page. It is empty for now; you fill it in step 5.

> [!NOTE]
>
> If a teammate invited you, sign in with the email address the invitation went to. You join their organization instead of creating one, and can choose one of its projects, or ask them to create one for you. See [Team](https://to11.ai/docs/platform/team.md).

## 2. Create a chat prompt

In the sidebar, under **Build**, open **Chat Prompts** and choose **New prompt**.

1. Set **Display name** to `Welcome message`. The **Slug** fills in as `welcome-message`.
2. In the content step, write this system message:

   ```text theme={null}
   You are a friendly assistant. Greet {{ name }} in one sentence.
   ```

   Typing `{{` starts a variable reference. `name` is a variable your code fills in.
3. Save the prompt.

Saving creates the prompt and its first version, and the prompt's `latest` label points at that version. Your code renders `latest`.

## 3. Create an API key

Your code authenticates to to11 with an API key.

1. Open **Settings** at the bottom of the sidebar, then **API keys** under **Organization**.
2. Choose **Create API key**.
3. Name the key `quickstart`. Under **Where does this key live?**, choose **Project**, then your workspace and project.
4. On **Permissions**, keep the **Read** preset. It lets the key read prompts and skills, which is all rendering needs. Keep the default expiry.
5. Review the key and create it.
6. Copy the secret. It is shown only once.

The **API keys** page header has a copy button after the word **project**: it copies your project's ID, which starts with `proj_`. Set both values in your terminal:

```bash theme={null}
export TO11_API_KEY="<the secret you copied>"
export TO11_PROJECT_ID="<your project id>"
```

## 4. Render the prompt from code

Install the SDK and render the prompt you created:

```bash TypeScript theme={null}
npm install @to11ai/sdk
cat > render.mjs <<'EOF'
import { createClient } from "@to11ai/sdk";

// Reads TO11_API_KEY and TO11_PROJECT_ID from the environment.
const to11 = createClient({ format: "openai" });

const prompt = await to11.prompts.render("welcome-message", {
  variables: { name: "Ada" },
});
console.log(prompt.messages);
EOF
node render.mjs
```

```bash Python theme={null}
pip install to11ai-sdk
cat > render.py <<'EOF'
from to11ai_sdk import create_client

# Reads TO11_API_KEY and TO11_PROJECT_ID from the environment.
to11 = create_client(format="openai")

prompt = to11.prompts.render("welcome-message", variables={"name": "Ada"})
print(prompt["messages"])
EOF
python render.py
```

The output is one system message with `Ada` in place of `{{ name }}`. Node prints it like this, and Python prints the same list with its own quoting:

```text theme={null}
[ { role: 'system', content: 'You are a friendly assistant. Greet Ada in one sentence.' } ]
```

`format: "openai"` shapes the messages for the OpenAI client, so you can pass them to `openai.chat.completions.create()` with your own OpenAI key. Edit the prompt in the dashboard and publish a new version, run the script again, and the output changes with no change to your code.

## 5. Link a repository and see a session

The to11 CLI installs your project's skills into the directories your coding agent reads, and uploads your Claude Code sessions to the project. Install it:

```bash macOS theme={null}
brew install to11ai/tap/to11
```

```bash Ubuntu & Debian theme={null}
sudo apt-get update
sudo apt-get install -y curl gnupg
curl -fsSL https://apt.fury.io/to11/gpg.key | sudo gpg --dearmor -o /usr/share/keyrings/to11-keyring.gpg
sudo chmod go+r /usr/share/keyrings/to11-keyring.gpg
echo "deb [signed-by=/usr/share/keyrings/to11-keyring.gpg] https://apt.fury.io/to11/ * *" | sudo tee /etc/apt/sources.list.d/to11.list
sudo apt update
sudo apt install to11
```

```bash Fedora & RHEL theme={null}
sudo rpm --import https://yum.fury.io/to11/gpg.key
sudo rpm --import https://raw.githubusercontent.com/to11ai/to11-cli/main/rpm-signing-key.asc
sudo tee /etc/yum.repos.d/to11.repo <<EOF
[to11]
name=to11 Repository
baseurl=https://yum.fury.io/to11/
enabled=1
gpgcheck=1
repo_gpgcheck=1
gpgkey=https://yum.fury.io/to11/gpg.key
EOF

sudo dnf install to11
```

```bash theme={null}
to11 version
```

This tutorial needs version `0.36.0` or later.

Go to your git repository and run `to11`:

```bash theme={null}
cd ~/src/your-repository
to11
```

`to11` links the repository to a project, asking one question at a time:

1. At `Press Enter to continue in your browser, or Ctrl-C to cancel.`, press Enter and sign in in the browser.
2. Because you named the project after the repository, it asks `Found project <workspace>/<project>. Receive its skills here?`. Press Enter for yes. If it asks `Which project?` instead, choose the project you created in step 1.
3. Press Enter to accept the skills and the coding agents it installs them for.
4. Answer `y` to `Install the to11 plugin for Claude Code?`. The plugin keeps your skills current while Claude Code is open.
5. At `Sync this repository's Claude Code sessions to to11 automatically?`, press Enter to keep it off. You sync by hand below.

It writes `.to11/skills.yaml`, which your team can commit, and `.to11/sessions.yaml`, which names your project as the place your sessions go and stays out of git.

Now start Claude Code in the repository, ask it one question, and exit:

```bash theme={null}
claude
```

Then send the session to your project:

```bash theme={null}
to11 session sync
```

```text theme={null}
Synced 1 session to <workspace>/<project> (1 new).
https://app.to11.ai/p/proj_…/sessions
```

Open the link. The **Sessions** page lists the session you just ran, with its title, owner, duration, and estimated cost. Click it to read the session as a thread of your prompt, Claude's responses, and its tool calls.

## What you did

You created a project, rendered a chat prompt from code with a project-scoped API key, linked a repository to the project with the CLI, and uploaded a Claude Code session to it.

## Next steps

> [card] [Skills quickstart](https://to11.ai/docs/skills/quickstart.md)
>
> Write a skill and store it, so everyone who follows the project receives it.

> [card] [Rendering prompts](https://to11.ai/docs/platform/prompts/rendering.md)
>
> Variables, tools, model settings, and sending the result to a model.

> [card] [Syncing sessions](https://to11.ai/docs/sessions/syncing-sessions.md)
>
> Send sessions automatically after each response.

> [card] [API keys](https://to11.ai/docs/platform/api-keys.md)
>
> Scopes, rotation, and revocation.


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.