GitHub - awlevin/typesafe-computer-use: Computer use for about $0.0002 a step: OCR the screen, classify the next action with TypeSafe, click
typesafe-computer-use drives a Mac toward a goal you type in plain English, for about a fiftieth of a cent per step. It never sends a screenshot to a big model. Instead it reads the screen deterministically, asks a small classifier which action comes next,
GitHub - fhshaik/typesafe-mario: A TypeSafe/Jev agent that plays Super Mario Bros. from structured emulator state.
TypeSafe Mario An experimental controller that lets TypeSafe's Jev model directly choose NES controller inputs for the original Super Mario Bros. The model does not receive screenshots. The harness translates emulator telemetry and RAM into compact,
soundshuman/SKILL.md at main · aashaexo/soundshuman
name humanize description Remove signs of AI-generated writing from prose, and keep it out of a repo. Use when drafting, editing, or reviewing text to make it sound natural and human, or when auditing a whole docs folder for AI slop. Detects 41 patterns
AI Hedge Fund:AI 驱动的对冲基金团队概念验证(virattt/ai-hedge-fund)
AI Hedge Fund 是一个用于探索“用 AI 做交易决策”的概念验证项目,作者 virattt,采用 MIT 许可证。项目定位为教育与研究用途,明确声明不进行真实交易、不提供投资建议。当前项目正在重构为持久化、常驻运行的 AI 对冲基金(fund 作为一等实体,可回测、可纸面交易、可选择性实盘),投资者 Agent 被重新设计为可插拔、可回测的 alpha 模型。安装方式为 pipx/uv/pip 安装 aihf,运行 aihf 启动交互式终端应用,或通过 mandate 文件加 --tickers 做非交互式单周期运行与历史回测。
GitHub - unslothai/unsloth: Local UI to run and train LLMs and diffusion models. Supports GGUF, MLX, Qwen3.8, DeepSeek-V4, MiniMax-H3, Gemma
Unsloth is the first desktop app to run and train models. Features • Quickstart • Notebooks • Documentation ⚡ Get started Download the native Unsloth Desktop app for your operating system: Platform Link Windows Download macOS Download Linux x64 / Ubuntu (deb)