Docs.rs

Local image generation backend for Blazen using diffusion-rs (pure Rust Stable Diffusion)

Core engine for a self-hosted advisory AI PR reviewer: fetches a pull request diff, reviews it with a Claude model via OpenRouter, and posts line-anchored inline comments plus a summary. Works with GitHub and Bitbucket.

Embedding backend facade for Blazen: picks fastembed (ORT) or tract (pure Rust) per target

Local embedding backend for Blazen using HuggingFace candle

Multi-backend text-to-speech crate for Blazen (any-tts local engines + OpenAI-compatible HTTP)

Inkhaven — TUI literary work editor for Typst books

Pure-Rust ONNX inference backend for Blazen embeddings (tract-onnx)

Multi-backend speech-to-text engine crate for Blazen (whisper.cpp, candle)

Music + sound-effect generation backends for Blazen (MusicGen, AudioGen, Stable Audio)

Neural audio-codec backends for Blazen — encode PCM to discrete codebook tokens and back for generative audio models

Shared model download and cache layer for Blazen local-inference backends

Multi-backend 3D-pipeline crate for Blazen (texturizer, rigger, refiner, animator capability traits)

Multi-backend voice-conversion crate for Blazen (RVC and related speaker-transform engines)

Public/private individual key encryption for repo secrets with biometrics support and explicit approval of who can decrypt. In other words — the missing good UX for SOPS

Some user-friendly yet personalized tools