A high-throughput and memory-efficient inference and serving engine
Drag & drop UI to build your customized LLM flow
Data Lake for Deep Learning. Build, manage, and query datasets
Chat with LLM like Vicuna totally in your browser with WebGPU
Self-hosted, community-driven, local OpenAI compatible API
⚡ Building applications with LLMs through composability ⚡
Zep: A long-term memory store for LLM / Chatbot applications
Build, deploy, and manage LLM-powered agents
State-of-the-art Parameter-Efficient Fine-Tuning
Vector database plugin for Postgres, written in Rust
Low-code framework for building custom LLMs, neural networks
Tensor search for humans