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

# CLaaS Documentation

> Continual Learning as a Service. Real-time model personalization via self-distillation

**Continual Learning as a Service (CLaaS)** personalizes open-source language models in real time using SDPO (Self-Distillation from Preference Optimization). Every piece of user feedback triggers a single distillation step that updates the model's LoRA adapter, without forgetting what it already knows.

## Explore the docs

<CardGroup cols={2}>
  <Card title="Quick Start" icon="rocket" href="/quickstart">
    Get up and running with CLaaS in minutes using Local, Tinker, or Modal backends.
  </Card>

  <Card title="Training Backends" icon="server" href="/training/overview">
    Compare Local GPU, Tinker SDK, and Modal cloud backends for SDPO training.
  </Card>

  <Card title="Evaluation" icon="chart-line" href="/eval/overview">
    Run automated feedback loops to measure preference compliance and detect collapse.
  </Card>

  <Card title="Dashboards" icon="table-columns" href="/dashboards">
    Built-in web dashboards for training metrics and eval results served by the CLaaS API.
  </Card>
</CardGroup>

## Quick links

|                |                                                              |
| -------------- | ------------------------------------------------------------ |
| **Runtime**    | Python >= 3.11, [uv](https://docs.astral.sh/uv/)             |
| **Repository** | [github.com/kfallah/CLaaS](https://github.com/kfallah/CLaaS) |
| **License**    | MIT                                                          |