Tag
Persist AI agent context across sessions and tool switches
Fine-tune any LLM on a 4 GB GPU, one YAML config
Open source RAG framework for any dataset or LLM
Self-hosted speech recognition API built on OpenAI Whisper
Real-time audio translation for Windows, powered by LLMs
14MB on-device LLM for tool calling on edge devices
LLM proxy with API translation and multi-backend routing
Open-source RAG engine with document parsing and agent orchestration
Model-definition framework for state-of-the-art ML
Local inference engine for DeepSeek V4 Flash/PRO and GLM 5.2
Agentic AI framework for the JVM
Open-source AI coding agent you can leave running locally.
