Codync
免费开源的 1:1 Grok Bot 与 Muse 替代方案。可在 iPhone、Mac 或 Linux 桌面上将 Claude 代码、Codex、Cursor 以及 40 多个编码代理作为持久机器人使用。支持群组聊天、线程、应用。
AI 翻译
尚未检测到更新。GitHub 发布版本后会显示在这里。
个人 GitHub 账号下公开仓库的所有者可以登录并验证所有权,自行管理介绍,无需管理员批准。
登录并生成验证文件,在 30 分钟内将其提交到此仓库的默认分支。其他分支或分叉仓库中的文件无效。然后在下方检查文件,即可无需管理员批准直接管理项目。请保留文件以维持管理权限。
如需登录,将前往登录页面。登录后请回到此处,再次点击所选的验证按钮。
在项目文件夹中运行 /nomorevibe verify,即可验证所有权并自行管理介绍。
一分钟完成验证Python SDK and CLI for Amália, Portugal's open pt-PT LLM from the AMALIA-LLM initiative
翻译准备中
取自仓库 README
正在加载完整 README。
查看完整 README ↗Modern Python SDK, CLI, and Boilerplate for Amália — Portugal's National LLM
Status: In Active Development (v2.0 Alpha)
License: MIT
Website: https://fitzyracing1.github.io/Amalia2.0
PyPI (planned): pip install amalia2
Original SDK: alfmatos/amalia
Amalia 2.0 is the next-generation developer experience for Amália, the fully open-source Portuguese (pt-PT) large language model from the AMALIA-LLM initiative.
While the original SDK provided a solid foundation, Amalia 2.0 delivers a batteries-included, visually-documented, ecosystem-aware boilerplate that makes it dramatically easier and more enjoyable to build production-grade applications with Amália.
Key pillars:
This project draws inspiration from the pioneering work of the AMALIA-LLM organization and the original community SDK, while pushing the boundaries of what a national LLM platform can offer developers.
amalia2 new my-app instantly scaffolds a full project (RAG, chatbot, evaluation harness, mobile companion, etc.)# Install (once published)
pip install amalia2
# Or from source
git clone https://github.com/fitzyracing1/Amalia2.0
cd Amalia2.0
pip install -e ".[cli,chat]"
# Create a new project from template
amalia2 new my-portuguese-app --template rag-chatbot
# Interactive chat
amalia2 chat --model amalia-9b
# Run an agent example
amalia2 run examples/agent_researcher.py
See the full Getting Started guide on the website.
Amalia2.0/
├── src/amalia2/ # Core package
│ ├── client/ # Async + sync clients
│ ├── cli/ # Typer CLI
│ ├── agents/ # Agent framework & tools
│ ├── skills/ # Reusable skills (pt-PT optimized)
│ └── templates/ # Project scaffolding
├── examples/ # Ready-to-run examples
├── templates/ # Cookiecutter / copier templates for new projects
├── docs/ # Beautiful GitHub Pages website
├── skills/ # Community + official skills
└── pyproject.toml
| Phase | Focus | Status |
|---|---|---|
| 01 | Core async client + beautiful CLI | In Progress |
| 02 | Agent framework + skill system | Planned |
| 03 | Project templates & scaffolding | Planned |
| 04 | Deep ecosystem integrations (3XB, Pie Face, etc.) | Planned |
| 05 | Production examples + benchmarks | Future |
| 06 | PyPI release + community growth | Future |
Full interactive roadmap and technical architecture available on the project website.
Amalia 2.0 is designed to be a first-class citizen in ambitious Portuguese and European AI stacks:
We believe national LLMs like Amália deserve world-class tooling.
We welcome contributions from Portuguese speakers, LLM enthusiasts, agent builders, and anyone passionate about sovereign AI tooling.
Please read CONTRIBUTING.md. Visual contributions (diagrams, UI mocks for the chat client, example screenshots) are especially valued.
MIT License.
Built with deep respect for the AMALIA-LLM organization, the original community SDK by @alfmatos, and everyone advancing open Portuguese language technology.
Special thanks to the Grok & xAI ecosystem for accelerating ambitious builder workflows.
Amalia 2.0 • Modern tooling for Portugal's LLM • fitzyracing1 • 2026
Part of the Earthenware Computer ecosystem — Tagging for everyone and everything.
This project is free, and its license stays as is. Support it through GitHub Sponsors: