LSP server leveraging LLMs for code completion (and more?)
The most RAM efficient harness
All-in-one LLM CLI tool featuring Shell Assistant, Chat-REPL, RAG, AI Tools & Agents, with access to OpenAI, Claude, Gemini, Ollama, Groq, and more.
A blazing fast inference solution for text embeddings models
Instant, controllable, local pre-trained AI models in Rust