speed-of-light

tokenspeed

Python

90

TokenSpeed is a speed-of-light LLM inference engine.

Noustiny

TypeScript

54

An agent native video creation pipeline that runs on top of Hermes Agent

riptide

Go

63

A polished terminal internet speed test and realtime bandwidth monitor written in Go. Riptide measures download, upload, and latency in a centered card UI with live progress, compact sparklines, smooth animation, and clean cross-platform output for Linux and Windows terminals.

apex-inference-chip

Python

68

An inference chip design that runs a real LLM (Qwen2.5-0.5B) on FPGA — one transformer decoder layer in RTL, every silicon value bit-exact against a golden model. 0.56 tok/s measured, a 140× climb, full evidence trail.

MTPLX

Python

90

3x faster speeds on MLX | Qwen 3.8 27B | Native MTP Speculative Decoding On Apple Silicon With No External Drafter.

outreachr

TypeScript

77

Local-first, open-source investor fundraising CRM for founders