A compact AI ecosystem for local models, cloud APIs, serious chat workflows and custom model infrastructure — built for control without platform bloat.
The planned one-click local AI stack: llama.cpp, model management, LM Studio/Ollama-style runtime workflows, LocalLightChat preconfigured and infrastructure defaults that do not require cloud dependency.
Fast, bloat-free chat UI for local models and cloud APIs. Long context, editable documents/artifacts, file input, web/image tools, full parameter control and portable/self-hosted deployment.
Open LocalLightChat →Dedicated model work for companies: custom AI models, domain adaptation, deployment strategy and private model infrastructure. The public product name is intentionally not final yet.