openevals
Readymade evaluators for your LLM apps
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。
Readymade evaluators for your LLM apps
此skills用于指导智能体在 Windows 上恢复 Codex Desktop 升级后失效的本地补丁和能力开关。(Computer Use,插件,破限,codex强制汉化,fast mode,手机远控,会话消失等问题)支持每次使用前自动将skills更新到最新版。/These skills are designed to guide the agent in restoring local patches and feature toggles that have been disabled or invalidated following a Codex Desktop upgrade on Windows. Supports auto-updating translations.
pinact 是一個 CLI,用於編輯 GitHub 工作流程和複合操作檔案以及操作和可重複使用工作流程的 pin 版本。 pinact也可以更新其版本並驗證版本註解。
具有 SQLite 持久性和內建儀表板的獨立 CliProxyAPI 使用情況追蹤器。
A personal context store for AI agents and assistants—reuse your existing coding agent CLI (Codex/Claude/OpenCode) with built‑in Skills/tools and a desktop GUI to capture, search, and reuse project knowledge across agents and repos.
Pre-submission AI review stress-test for research papers. A Claude Code skill: review, verdict, revise, verify.
Local first, desktop companion platform with animated pets, plugin SDK and coding-agent integrations.
Self-hosted gym & body-weight tracker — plan routines, log workouts (supersets, warm-ups, cardio), see which muscles are trained, fatigued or detrained, import from FitNotes/Strong/Hevy, passkey login. Your data, your server.
Scan the devices connected to your WIFI / LAN and alert you the connection of unknown devices. It also warns if a "always connected" device disconnects. In addition, it is possible to check web services for availability. For this purpose HTTP status codes and the response time of the service are evaluated.
The simplest way to serve AI/ML models in production
All the handwritten notes 📝 and source code files 🖥️ used in my YouTube Videos on Machine Learning & Simulation (https://www.youtube.com/channel/UCh0P7KwJhuQ4vrzc3IRuw4Q)
🥤 RAGLite is a Python toolkit for Retrieval-Augmented Generation (RAG) with DuckDB or PostgreSQL
A desktop app that lets you use your AI subscriptions (Claude, ChatGPT, Gemini, GitHub Copilot) with any coding tool. Wraps CLIProxyAPI with a clean UI for managing connections and tracking usage.
Beautiful native macOS video downloader. Download and trim in one app.
Ultra-minimalist macOS dictation.
Evaluate and improve models and agents using environments
PDEBench: An Extensive Benchmark for Scientific Machine Learning
A Terminal-style trading dashboard built entirely on free public market data. No API keys, no subscriptions.
📈 Open source, privacy-first web analytics — a cookie-less Google Analytics alternative with built-in error tracking and performance monitoring. Self-host it or use our cloud. Get started for free!
Elixir implementation of a LangChain style framework that lets Elixir projects integrate with and leverage LLMs.