About this project
Rig is a Rust library for building scalable, modular, and ergonomic LLM-powered applications. It provides a unified interface for over 20 model providers and 10+ vector store integrations, supporting LLM completion, embedding, transcription, audio generation, and image generation workflows. Key features include agentic workflows with multi-turn streaming, a classic agent runtime, full GenAI Semantic Convention compatibility, and minimal boilerplate integration. The library is split into `rig-core` for provider-neutral contracts and `rig-agent` for orchestration, with the root `rig` facade re-exporting both. It supports browser-WASM for the portable core and classic runtime. Integrations include AWS Bedrock, Google Vertex AI, LanceDB, Qdrant, MongoDB, and more, each behind a feature flag. Rig also offers recording and replay capabilities via `rig::cassette` for testing and debugging. Used by companies like St Jude, Coral Protocol, and Nethermind.
Comments
0 Rating appears after 10 ratings
Sign in to join the discussion.