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.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.
Explore the docs
Quick Start
Get up and running with CLaaS in minutes using Local, Tinker, or Modal backends.
Training Backends
Compare Local GPU, Tinker SDK, and Modal cloud backends for SDPO training.
Evaluation
Run automated feedback loops to measure preference compliance and detect collapse.
Dashboards
Built-in web dashboards for training metrics and eval results served by the CLaaS API.
Quick links
| Runtime | Python >= 3.11, uv |
| Repository | github.com/kfallah/CLaaS |
| License | MIT |