docs: clarify usage data collection scope and GDPR basis (#453)

* docs: add Supporting Other CLIs section with Claude Code, Codex and OpenCode

Adds a new documentation section covering how to use the Alias API
with third-party scaffoldings (Claude Code via proxy, Codex CLI, and
OpenCode). Includes privacy/security warning banners and support
disclaimers on each page.

* docs: update Claude Code setup to use env vars instead of proxy

* docs: clarify usage data collection scope and GDPR basis

Expand the Usage Data Collection section to explicitly mention model
training and evaluation as purposes of data collection, separate the
GDPR legal basis into its own paragraph for readability, and refine
the closing note about CAI_TELEMETRY.
This commit is contained in:
UnaiAlias 2026-06-01 16:31:58 +02:00 committed by GitHub
parent 87cc46f46f
commit 2963eb2d22
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
2 changed files with 64 additions and 51 deletions

View File

@ -967,14 +967,18 @@ Currently, the extensions are not publicly available as the engineering endeavou
### :information_source: Usage Data Collection
CAI is provided free of charge for researchers. To improve CAIs detection accuracy and publish open security research, instead of payment for research use cases, we ask you to contribute to the CAI community by allowing usage data collection. This data helps us identify areas for improvement, understand how the framework is being used, and prioritize new features. Legal basis of data collection is under Art. 6 (1)(f) GDPR — CAIs legitimate interest in maintaining and improving security tooling, with Art. 89 safeguards for research. The collected data includes:
CAI is provided free of charge for researchers. To improve CAIs detection accuracy, advance open security research, and develop and train future models, we ask you to contribute to the CAI community by allowing usage data collection. This data helps us identify areas for improvement, understand how the framework is being used, prioritize new features, and support model training and evaluation efforts.
The legal basis for data collection is under Art. 6 (1)(f) GDPR — CAIs legitimate interest in maintaining, improving, and advancing security tooling and research — with Art. 89 safeguards applied for research purposes.
The collected data includes:
- Basic system information (OS type, Python version)
- Username and IP information
- Tool usage patterns and performance metrics
- Model interactions and token usage statistics
We take your privacy seriously and only collect what's needed to make CAI better. For further info, reach out to researchaliasrobotics.com. You can disable some of the data collection features via the `CAI_TELEMETRY` environment variable but we encourage you to keep it enabled and contribute back to research:
We take your privacy seriously and only collect what is necessary to improve CAI, support research, and train and evaluate models responsibly. For further information, contact researchaliasrobotics.com. You can disable some data collection features via the `CAI_TELEMETRY` environment variable, although we encourage you to keep it enabled to contribute to ongoing research and model development:
```bash
CAI_TELEMETRY=False cai

View File

@ -4,28 +4,36 @@
Third-party scaffoldings may be serving your data outside your environment.
For **privacy** and **cybersecurity refusal optimization**, use **CAI** to obtain the best performance.
Claude Code is Anthropic's official CLI for agentic coding. Because it speaks the **Anthropic API format** natively, it cannot talk directly to the Alias API (which is OpenAI-compatible). A small proxy is required to translate between the two.
!!! warning "Support Disclaimer"
Alias Robotics **does not provide support** for developments or integrations related to Claude Code. This page documents API compatibility only. Alias simply allows usage of the Alias API through your preferred scaffolding.
---
## How It Works
## Step 1: Install Claude Code
```
Claude Code → Anthropic API format
claude-code-proxy (localhost:8082)
OpenAI-compatible format → Alias API
### Prerequisites
- **Node.js 18** or newer
- For **macOS**, use [nvm](https://github.com/nvm-sh/nvm) to install Node.js — installing the package directly may cause permission issues
- For **Windows**, additionally install [Git for Windows](https://gitforwindows.org/)
```bash
# Install Claude Code
npm install -g @anthropic-ai/claude-code
# Navigate to your project
cd your-awesome-project
# Launch
claude
```
The proxy ([github.com/1rgs/claude-code-proxy](https://github.com/1rgs/claude-code-proxy)) intercepts Anthropic-format requests from Claude Code and forwards them to any OpenAI-compatible backend — in this case, the Alias API.
!!! note
If macOS users encounter permission issues during installation, use `nvm` to install Node.js.
---
## Setup
## Step 2: Configure the Alias API
### 1. Get your Alias API Key
@ -34,58 +42,59 @@ An `ALIAS_API_KEY` (format: `sk-...`) can be obtained from either of the followi
- **[CAI PRO](https://aliasrobotics.com/cybersecurityai.php)** — full cybersecurity AI platform with access to `alias1` and other models.
- **[Alias LLMs](https://aliasrobotics.com/aliasLLMs.php)** — acquire `alias2-mini` and other Alias language models directly.
### 2. Clone and configure the proxy
### 2. Configure Environment Variables
```bash
git clone https://github.com/1rgs/claude-code-proxy.git
cd claude-code-proxy
Set up environment variables using one of the following methods for macOS/Linux or Windows.
!!! note
Some commands show no output when setting environment variables — that's normal as long as no errors appear. A new terminal window may be required for the changes to take effect.
#### macOS & Linux
Edit the Claude Code configuration file `~/.claude/settings.json`. Add or modify the `env` fields `ANTHROPIC_BASE_URL` and `ANTHROPIC_AUTH_TOKEN`.
Replace `your_alias_api_key` with the API Key you obtained in the previous step.
```json
{
"env": {
"ANTHROPIC_AUTH_TOKEN": "your_alias_api_key",
"ANTHROPIC_BASE_URL": "https://api.aliasrobotics.com:666/",
"API_TIMEOUT_MS": "3000000"
}
}
```
Create a `.env` file:
#### Windows Cmd
```bash
# Point to the Alias API
OPENAI_API_KEY="sk-your-alias-api-key-here"
OPENAI_BASE_URL="https://api.aliasrobotics.com:666/"
Run the following commands in Cmd. Replace `your_alias_api_key` with the API Key you obtained in the previous step.
# Map Claude model names to Alias models
BIG_MODEL="alias1"
SMALL_MODEL="alias1"
PREFERRED_PROVIDER="openai"
```cmd
setx ANTHROPIC_AUTH_TOKEN your_alias_api_key
setx ANTHROPIC_BASE_URL https://api.aliasrobotics.com:666/
```
### 3. Run the proxy
#### Windows PowerShell
Install `uv` if needed, then start the server:
Run the following commands in PowerShell. Replace `your_alias_api_key` with the API Key you obtained in the previous step.
```bash
uv run uvicorn server:app --host 0.0.0.0 --port 8082 --reload
```
Or with Docker:
```bash
docker run -d --env-file .env -p 8082:8082 ghcr.io/1rgs/claude-code-proxy:latest
```
### 4. Launch Claude Code via the proxy
```bash
ANTHROPIC_BASE_URL=http://localhost:8082 claude
```
To avoid setting this every time, export it in your shell profile:
```bash
echo 'export ANTHROPIC_BASE_URL=http://localhost:8082' >> ~/.zshrc
```powershell
[System.Environment]::SetEnvironmentVariable('ANTHROPIC_AUTH_TOKEN', 'your_alias_api_key', 'User')
[System.Environment]::SetEnvironmentVariable('ANTHROPIC_BASE_URL', 'https://api.aliasrobotics.com:666/', 'User')
```
---
## Verification
## Step 3: Start with Claude Code
Inside Claude Code, run a quick prompt and confirm the response is served via `alias1`. Token usage and billing will appear in your Alias account.
Once the configuration is complete, start using Claude Code in your terminal:
```bash
cd your-project-directory
claude
```
Token usage and billing will appear in your Alias account.
---