开源好物 26/04

1. AI Agent

1.1 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-codex

1.2 Superpowers

Superpowers 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/superpowers

1.3 gstack

gstack: 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/gstack

1.4 RoboClaw

RoboClaw 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/RoboClaw

2. AI Learn

2.1 MiniMind

MiniMind: 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/minimind

3. AI Model

3.1 SAM 3

SAM 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/sam3

3.2 TimesFM

TimesFM (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/timesfm

3.3 Rex-Omni

Rex-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-Omni

4. AI Tool

4.1 CC Switch

CC 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