Latency-aware LLM router that dynamically cascades between edge and cloud models via logprob inspection.
Latency-aware LLM router that dynamically cascades between edge and cloud models via logprob inspection.
Local web UI for exploring token-level log probabilities from OpenAI-compatible chat models.
a small word frequency library
Predicting gender based on name.
wrapper for textsynth.com
Probabilistic programming library powered by TensorFlow.js
A wrapper around floats to handle log probabilities
Detect normalization errors, entropy bias, and truncation artifacts in LLM logprob data
React to elements in a JSON stream
A real-time LLM stream interceptor for token-level interaction research
AVI/video → SRT subtitle generator using whisper.cpp via whisper-rs
Shared primitives, traits, and utilities for the Cyanea bioinformatics ecosystem
Tools for OpenAI API
Rust client library for the Grok AI API (xAI)
OpenAI provider implementation for the LLM Kit
A Rust library to mock OpenAI's API for testing purposes.
Official Rust SDK for Rainy API by Enosis Labs v0.6.14 - OpenAI/GPT-5 parity, native streaming events, and legacy static model cleanup
Blazingly fast proxy server that bridges Ollama and LM Studio