Minimalistic Android client app for Audiobookshelf
Repositories
mvanhorn repositories
A fast, helpful, and open-source document parser
Light, flexible and extensible ASGI framework | Built to scale
LLM inference in C/C++
Unified management and routing for llama.cpp, MLX and vLLM models with web dashboard.
Light LDAP implementation
A lightweight, configurable, and real-time simulator designed to mimic the behavior of vLLM without the need for GPUs or running actual heavy models.
llm-d Router: The intelligent entry point for inference requests
Hundreds of models & providers. One command to find what runs on your hardware.
Computing-focused community centered around link aggregation and discussion
Rust library for local search optimization
Bidirectional, stateful control of Logic Pro from AI assistants. 8 dispatcher tools + 7 resources across 5 native macOS channels.
🧑🚀 Authentication and authorization infrastructure for SaaS and AI apps, built on OIDC and OAuth 2.1 with multi-tenancy, SSO, and RBAC.
Robust and reusable Executor for joblib
Millions and millions of volumes orchestrated
The tool-calling loop for LLM agents; iterator-first, protocol-hooked, one dependency.
Lossless Claw — LCM (Lossless Context Management) plugin for OpenClaw
Reference implementation of the Filecoin protocol, written in Go
Lucebox: LLM inference server built for speed for specific consumer hardware.
The back end for the Lunes vocabulary trainer. Front end: https://github.com/digitalfabrik/lunes-app.