Texo
A minimalist SOTA LaTeX OCR model with only 20M parameters, running in browser. Full training pipeline available for self-reproduction. | 超轻量SOTA LaTeX公式识别模型,仅20M参数量,可在浏览器中运行。训练全流程代码开源,以便自学复现。
HYSEN LABS DIRECTORY
Curated repositories with precise taxonomy, verified metadata and practical context.
A minimalist SOTA LaTeX OCR model with only 20M parameters, running in browser. Full training pipeline available for self-reproduction. | 超轻量SOTA LaTeX公式识别模型,仅20M参数量,可在浏览器中运行。训练全流程代码开源,以便自学复现。
MIDI / symbolic music tokenizers for Deep Learning models 🎶
Free and fully open-source L2 ADAS stack powered by End-to-End AI technology
Self-hosted lightweight PaaS solution to deploy and manage your applications on any VPS [Your own self-hosted Heroku, Vercel]
Optimized Whisper models for streaming and on-device use
Expose Gemini CLI endpoints as OpenAI API with Cloudflare Workers
Cortex local-first personal memory app
workshop materials to build intelligent solutions on Open AI
About This repository is a curated collection of the most exciting and influential CVPR 2025 papers. 🔥 [Paper + Code + Demo]
Blazing fast Vue.js Toolchain. Compiler, Linter, Type Checker, Formatter, LSP, Story System, Editor Extensions. This already passed 10k+ test suites, includes real world E2E.
A Claude Code plugin that makes Opus behave like Fable — completion, evidence, and verification enforced as procedure. Ships only what a Fable-vs-Opus comparison proved transferable.
OCTO Android Client — Open-source enterprise IM
MyAgents - 优雅、易用的 Agent 桌面端 ,一站式 Agent 工作台与任务中心
Running any GGUF SLMs/LLMs locally, on-device in Android
Late Interaction Models Training & Retrieval
Self-hosted torrent video streaming service compatible with Chromecast, AppleTV & Kodi deployable in the cloud
A local sandbox for your AI agents
Agent Plugins for AWS equip AI coding agents with the skills to help you architect, deploy, and operate on AWS.
Plugin for agents to interact with Chatcut
面向 AI Agent / Codex 的本地 CTF 逆向工程流程技能。加载后通过“真心为你”进入逆向模式,默认在本地沙盒、CTF、crackme、wargame 或训练靶场环境中工作,按“分析 → 报告 → 逆向 → 深度逆向 → 漏洞研判 → 用户选择下一步”的流程推进。