J-tau: A Japanese tau-bench for Benchmarking Tool-Agent-User Interaction in Real-World Domains

An all-in-one, pure C++ inference engine for audio models, powered by ggml. Supports TTS, STT, VAD, voice conversion, music generation, and more, with highly optimized performance. No Python depend…

End-to-end realtime stack for connecting humans and AI

GGUF implementation in C as a library and a tools CLI program

a community oriented 1:1, vLLM-alike (Continuous batching, paged KV) engine in C++ with additional features

NeMo-Speech.cpp is a lightweight C++ inference runtime for Speech models

Parakeet implementation in C++ with ggml

Open Source framework for voice agents, multimodal apps, and realtime AI. Maintained by Daily and the community.

An AI accelerator implementation with Xilinx FPGA

J-Moshi: A Japanese Full-duplex Spoken Dialogue System

Transactional Verilog design and Verilator Testbench for a RISC-V TensorCore Vector co-processor for reproducible linear algebra

TensorCore Vector Processor for Deep Learning - Google Summer of Code Project

A Python DSL to write Nvidia PTX for Hopper and Blackwell in JAX and PyTorch

Real-time, local speech-to-text with streaming ASR, speaker diarization, translation, and OpenAI/Deepgram-compatible APIs.

Kernel-level benchmark infrastructure for torch.compile / TorchInductor

User facing skill definitions for PyTorch users

A realtime voice runtime that keeps Agents talking, working, and present. Real-time Voice Runtime for AI Agents

Live USB device tree in your terminal. Rust TUI, no root, no libusb. Full activity metrics on Linux; device tree on macOS/Windows.

An AI agent development platform with all-in-one visual tools, simplifying agent creation, debugging, and deployment like never before. Coze your way to AI Agent creation.

MoonEP: A Perfectly Balanced Expert Parallelism Library via Dynamic Redundant Experts

Bento, the office suite that fits in a file

OpenROAD's unified application implementing an RTL-to-GDS Flow. Documentation at https://openroad.readthedocs.io/en/latest/

Event Driven Orchestration & Scheduling Platform for Mission Critical Applications

An open-source wake word library for creating voice-enabled applications.

ggml speech-to-text inference for 16+ model families

Driver stack (including user space libraries, kernel module and firmware) for the Arm® Ethos™-N NPU

User-friendly AI Interface (Supports Ollama, OpenAI API, ...)