yisiliu
Follow
Highlights
Stars
The beautiful docs framework with Next.js.
Make websites accessible for AI agents
This repository contains the official firmware for Meshtastic, an open-source, off-grid mesh communication system.
Overview of pipelines related to PDF document processing.
A high-quality tool for convert PDF to Markdown and JSON.一站式开源高质量数据提取工具，将PDF转换成Markdown和JSON格式。
The all-in-one Desktop & Docker AI application with built-in RAG, AI agents, No-code agent builder, MCP compatibility, and more.
Dify is an open-source LLM app development platform. Dify's intuitive interface combines AI workflow, RAG pipeline, agent capabilities, model management, observability features and more, letting yo…
Toolkit for linearizing PDFs for LLM datasets/training
A high-throughput and memory-efficient inference and serving engine for LLMs
[MLSys 2024 Best Paper Award] AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration
Servo aims to empower developers with a lightweight, high-performance alternative for embedding web technologies in applications.
Xiaomi Home Integration for Home Assistant
A low-power E-Paper weather display powered by an ESP32 microcontroller. Utilizes the OpenWeatherMap API.
The fastest, most feature-complete zkVM for developers.
rapidsnark is a fast zkSNARK prover written in C++, that generates proofs for circuits created with circom and snarkjs.
ezkl is an engine for doing inference for deep learning models and other computational graphs in a zk-snark (ZKML). Use it from Python, Javascript, or the command line.
A library to do regex verification in circom, adapted from the original zk-email. It additionally generates lookup tables for halo2-regex and soon Noir.
A starting point to setup some lsp related features in neovim.
Netflix-level subtitle cutting, translation, alignment, and even dubbing - one-click fully automated AI video subtitle team | Netflix级字幕切割、翻译、对齐、甚至加上配音，一键全自动视频搬运AI字幕组
Free and open-source map hosting solution with custom styles for websites and apps, using OpenStreetMap data
Create beautiful diagrams just by typing notation in plain text.
1 min voice data can also be used to train a good TTS model! (few shot voice cloning)
We write your reusable computer vision tools. 💜