Repository Index

Low-latency local speech-to-speech voice assistant with Ming-3.0-audio-tiny on AMD and Nvidia GPUs. Easy setup on Windows and Linux

• amd
• local-llm
• radeon
• realtime

:hospital: Medical Text Mining and Information Extraction with spaCy

• natural-language-processing
• medical-natural-language-processing
• machine-learning
• metamap

Fast, exact inference for StartLux-Decision models on NVIDIA GPUs: the released GGUF files on int8 and 4-bit tensor cores, behind the /v1/systemone API, with up to 5.3× lower latency than vLLM in FP8 and bit-identical answers.

• calibration
• cuda
• cuda-graphs
• decision-making

An application for controlling 2D plotters, cutters, engravers, and CNC machines.

A learning environment for Python suited for beginners and children, inspired by Logo.

• python
• education
• learning-python
• turtle

RELATE is an Environment for Learning And TEaching

• web
• web-application
• course-management
• python

Image quality is an open source software library for Image Quality Assessment (IQA).

• artificial-intelligence
• machine-learning
• image-quality-assessment
• computer-vision

Android Studio / Eclipse ADT template for material-design-icons resources

A 4B grounding foundation model for physical intelligence. Unifies detection, referring, pointing, OCR, GUI, and layout grounding, achieving SOTA overall across 34 benchmarks and improving robot generalization and data efficiency in controlled evaluations.

• embodied-ai
• gui-grounding
• object-detection
• ocr

Reconquer the canvas: beautiful Tikz figures without clunky Tikz code

• tikz
• tikz-figures
• latex
• scientific-visualization

Code and Pretrained Models for Interspeech 2023 Paper "Whisper-AT: Noise-Robust Automatic Speech Recognizers are Also Strong Audio Event Taggers"

• audio
• audio-classification
• audio-processing
• audio-tagging

A curated collection of REA and AI-assisted reverse engineering cases, projects, and ideas. Updated every four hours.

• ai
• awesome-list
• rea
• reverse-engineering

EveryInfra MCP server & agent plugin: scraper API for TikTok, Instagram, Amazon, YouTube, Xiaohongshu & Douyin. 573 data APIs across 106 platforms, from $0.56/1K calls. For Claude Code, Cursor, Codex.

• ai-agents
• claude-code
• cursor
• mcp

[IROS 2020] se(3)-TrackNet: Data-driven 6D Pose Tracking by Calibrating Image Residuals in Synthetic Domains

• robotics
• tracking
• computer-vision
• pose-estimation

Iterative Linear Quadratic Regulator with auto-differentiatiable dynamics models

• trajectory-optimization
• differential-dynamic-programming
• theano
• dynamics-models

Browser automation engine benchmark - Test bypass rates, performance & stealth against Cloudflare, DataDome, reCAPTCHA, Kasada, Imperva, Akamai, PerimeterX and other bot detection systems. Find the best browser for scraping.

• anti-detect
• antidetect-browser
• automation
• browser

Raw talking-head take in, finished reel out. Open-source AI video editor for Claude Code.

• agent-skills
• captions
• claude-code
• hyperframes

A highly customizable DIY irrigation/sprinkler controller based on Raspberry Pi

• irrigation
• drip-irrigation
• hydroponics
• sprinkler-controller

TranslatedAn AI avatar for real-time voice/text conversations with idols from "The iDOLM@STER Shiny Colors": original Japanese voice + Chinese subtitles, recalling the original story, memory shared across characters; supports Google/GitHub login and bring-your-own key, one-command deployment with Docker Compose (inspired by LAPLACE Eidolon)

• ai-companion
• character-ai
• fastapi
• idolmaster

Skill for rigorous academic paper writing, revision, and submission. Field-agnostic with per-paper journal overrides.

A python package for calculating the PESQ.

Kotti is a high-level, Pythonic web application framework based on Pyramid and SQLAlchemy. It includes an extensible Content Management System called the Kotti CMS.

Turkish voice design with VoxCPM2 on a 4 GB GPU: describe a voice, pick a variant, read text in 30 languages. Patched audio.cpp, local UI in 30 languages, 14 ready-made voices.

• cuda
• ggml
• low-vram
• speech-synthesis

Experimental Nikon Z8 C 3.11 firmware patch builder: 3:2 open-gate N-RAW, desqueeze, ProRes/H.265 quality controls, N-Log/S-Log3/Log3G10, RAW pre-capture, and in-camera pixel-shift merging.

• firmware
• firmware-patching
• h265
• n-raw