vocalinux
專案速覽:適用於 Linux 的免費、開源、100% 離線語音聽寫。透過 Whisper.cpp、Whisper 和 VOSK 引擎、GPU 加速、可在 X11 + Wayland 上運行,在任何地方說話和打字!
HYSEN LABS 專案目錄
以精準分類、人工校驗資料與實用脈絡整理值得關注的開源專案。
專案速覽:適用於 Linux 的免費、開源、100% 離線語音聽寫。透過 Whisper.cpp、Whisper 和 VOSK 引擎、GPU 加速、可在 X11 + Wayland 上運行,在任何地方說話和打字!
Editable scientific figures in PowerPoint and draw.io via Codex/MCP with Designer-Drawer-Reviewer-Corrector quality gates.
小李的大模型应用开发学习路线,涵盖 RAG、Agent、面试八股与论文速读。
面向中文开发者的 Claude Code Skills / Agents / Plugins 精选与原创技能库|按场景分类|复制即装|持续更新
有情绪的 AI 桌面伴侣 | 隐私优先 · 语音唤醒 · 协助办公 · MCP 无限扩展 | An AI desktop companion with emotions — privacy-first, voice wake, office assistance, and MCP extensibility
Real time communication for agents. Wake on message, channels, DMs and actions. Useful for orchestrating agents.
SumatraPDF fork: Chinese EPUB/MOBI, smart PDF dark mode, OCR, TTS, offline dictionary.
A unified library for building, evaluating, and storing speculative decoding algorithms for LLM inference in vLLM
此專案圍繞「luckyPipewrench/pipelock」建置,面向真實業務場景,提供可重複使用、可持續維運的開源實作。
OpenJudge: A Unified Framework for Holistic Evaluation and Quality Rewards
The fastest JavaScript BPE Tokenizer Encoder Decoder for OpenAI's GPT models (gpt-5, gpt-o*, gpt-4o, etc.). Port of OpenAI's tiktoken with additional features.
[Pytorch] Generative retrieval model using semantic IDs from "Recommender Systems with Generative Retrieval"
Official Project Page for Recurrent Looped Transformer (RLT)
A toolkit for applying LLMs to sensitive, non-public data in offline or restricted environments
MCP Gateway is a reverse proxy and management layer for MCP servers, enabling scalable, session-aware stateful routing and lifecycle management of MCP servers in Kubernetes environments.
A Dynamic Environment to Evaluate Attacks and Defenses for LLM Agents.
🦀 A friendly terminal UI for rsync, written in Rust. Reusable profiles, an honest dry-run diff, and live progress, even over SSH.
The most advanced, fully offline client-side AI suite on Android today.
Open-source, local-first video editor where creators and AI agents edit the same real timeline.
The independent security agent for AI-written software. Finds issues, investigates whether they are real, and shows you the evidence. Deterministic core, no API key needed, JSON and SARIF output.