Stars
dsh-go — DeepSeek Harness 装进口袋:手机本机运行,也能遥控你的电脑。
利用泄露的emudhra ca+mitmproxy,实现中间人解密流量,便于APP调试等场景; use leaked emudhra ca certs with mitmproxy to catch traffic for app debugging.
Run many AI agents at once on your Mac, up to 3x faster.
Cryptanalysis of the ICCS NGCC round-1 public-key candidates: verification source
A 3D fruit fly living on your macOS desktop, driven by a live spiking simulation of the real FlyWire connectome
Pure mainline-based OpenWrt for the Xiaomi Mi Router AX3000T (RD03v2, IPQ5018): AN8855 2.5G switch, both WiFi bands, permanent NAND install.
unlock ssh/telent for xiaomi/redmi ax3600/ax3000/ax6000/ax9000/ax1800/ax5/ax6
嘉立创EDA专业版AI SKILL,为AI编程工具提供完整的EasyEDA Pro API接口和WebSocket桥接能力。EasyEDA Pro AI SKILL provides a complete EasyEDA Pro API interface and WebSocket bridging capability for AI programming tools.
一键DD/重装脚本 (One-click reinstall OS on VPS)
Train RL policies for the Pollen Microduck 🦆 on an ordinary Mac, no CUDA GPU, and watch them learn live in the browser.
RL training environments for Microduck (mjlab)
LLM inference server with continuous batching & SSD caching for Apple Silicon — managed from the macOS menu bar
MLX-VLM is a package for inference and fine-tuning of Vision Language Models (VLMs) on your Mac using MLX.
The fastest way to run Qwen 3.8 Flash Next, Qwen 3.8 27B and Ternary Bonsai 2 27B on a Mac: 125 tok/s in OpenCode on an M5 Max, and a 27B model on 16 GB Macs. Native MTP speculative decoding on App…
DeepSeek Harness: Everything is a Plugin.
Convert Word, PowerPoint, Excel, OpenDocument, RTF, EPUB, CSV, and PDF to clean Markdown. Built in Rust, with Node.js and Python bindings.
OpenMinis — The AI Agent app across platforms. Fully free and open source.
Rebuild the object in a reference image as a code-only, procedural, quality-gated, animation-ready Three.js model. Token-efficient image-to-3D.
OpenShell is the safe, private runtime for autonomous AI agents.
Qwen3-ASR is an open-source series of ASR models developed by the Qwen team at Alibaba Cloud, supporting stable multilingual speech/music/song recognition, language detection and timestamp prediction.
Open-source speech recognition toolkit for training, inference, streaming ASR, VAD, punctuation, speaker diarization pipelines, and OpenAI-compatible/MCP serving.
A free, open source, and extensible speech-to-text application that works completely offline.
Fastest and only macOS Dictation app with on-device STT and custom trained AI enhancement model. Windows, iOS testflight! Android, Linux waitlist open! A local Wispr Flow alternative. Follow https:…
The open-source AI voice studio. Clone, dictate, create.
旅行行程规划技能:规划 → 小红书调研 → 交互式地图页面 | Agent Skill for trip planning with 小红书 research and interactive map generation