momo-code

What it is

███╗ ███╗ ██████╗ ███╗ ███╗ ██████╗ ██████╗ ██████╗ ██████╗ ███████╗ ████╗ ████║██╔═══██╗████╗ ████║██╔═══██╗ ██╔════╝██╔═══██╗██╔══██╗██╔════╝ ██╔████╔██║██║ ██║██╔████╔██║██║ ██║ ██║ ██║ ██║██║ ██║█████╗ ██║╚██╔╝██║██║ ██║██║╚██╔╝██║██║ ██║ ██║ ██║ ██║██║ ██║██╔══╝ ██║ ╚═╝ ██║╚██████╔╝██║ ╚═╝ ██║╚██████╔╝…

The homepage listed on the repository, momozi.cc, puts it like this: 莫琰 MoMoZi 的粉紫小世界 · Agent 技术产品、AI 算法转产品、Skills 与多智能体开源作品 · momo子讲AI

What the README says it does

• 25+ LLM Providers — Deepseek, Zhipu (GLM), Moonshot (Kimi), Claude, GPT-4, Gemini, Doubao, OpenRouter, Groq, Mistral, and more. The \chat command uses OpenAI-compatible protocol only
• Custom Provider — Plug in any OpenAI-compatible API with MOMOCUSTOM env vars
• Model Tiers — Zero-config selection: ultra / standard / lite
• Interactive REPL — v2.0 native TTY interface with CoT panel, decision chips, keyboard shortcuts
• Pi Framework Integration — v2.0 extension-mode agent runtime with 6 momo-specific extensions

From the project’s README.

Getting started

From the README:

node -v   # should print v22.x or later
npm -v
git --version
curl --version

Where the decision sits

momo-code runs its own weights or its own runtime rather than calling a hosted API, so its decisions do not depend on a vendor being up or on a key being funded. The trade is that the model is now yours to keep current.

Models it references: laya-mlx.

How active it is

Created 2026-06-16, last pushed 2026-10-27, 1,112 stars and 107 forks when we read it on 2026-11-02. Everything in this category is weeks old at most, so a stale push date means something different here than it would on a mature project. Check the repository before you depend on it.