开源好物 26/04

1. AI Agent1.1 oh-my-codex (OMX)OMX is a workflow layer for OpenAI Codex CLI.OMX 是一个基于 OpenAI Codex 构建的 AI 工作流编排工具。https://github.com/Yeachan-Heo/oh-my-codex1.2 SuperpowersSuperpowers is a complete software development methodology for your coding agents.Superpowers 是一套完整的软件开发方法论让你的编程智能体能够有效地协助开发。https://github.com/obra/superpowers1.3 gstackgstack: turns Claude Code into a virtual engineering team.gstack: 将 Claude Code 变成一个虚拟工程团队让一个人就可以用它来创造与交付软件。https://github.com/garrytan/gstack1.4 RoboClawRoboClaw is an open-source embodied intelligence assistant.RoboClaw 是一个开源的具身智能助手。https://github.com/MINT-SJTU/RoboClaw2. AI Learn2.1 MiniMindMiniMind: Train a 64M ChatBot from zero. 2 hours. ¥3. One 3090. That’s it.MiniMind: 完全从 0 开始仅用 3 块钱成本与 2 小时训练时间即可训练出规模约为 64M 的超小语言模型。https://github.com/jingyaogong/minimind3. AI Model3.1 SAM 3SAM 3 is a unified foundation model for promptable segmentation in images and videos.SAM 3 是一个用于图像和视频中可提示分割的统一基础模型。https://github.com/facebookresearch/sam33.2 TimesFMTimesFM (Time Series Foundation Model) is a pretrained time-series foundation model for time-series forecasting.TimesFM时间序列基础模型是一个用于时间序列预测的预训练时间序列基础模型。https://github.com/google-research/timesfm3.3 Rex-OmniRex-Omni is a 3B-parameter multimodal model that unifies visual perception tasks, including object detection, OCR, pointing, keypointing, and visual prompting into a single next point prediction framework.Rex-Omni 是一个 3B 参数多模态模型它将视觉感知任务包括物体检测、OCR、指向、关键点定位和视觉提示统一到一个单一的下一点预测框架中。https://github.com/IDEA-Research/Rex-Omni4. AI Tool4.1 CC SwitchCC Switch: The All-in-One Manager for Claude Code, Codex, Gemini CLI, OpenCode OpenClaw.CC Switch: Claude Code, Codex, Gemini CLI, OpenCode 和 OpenClaw 的全方位管理工具。https://github.com/farion1231/cc-switch