Moltext by Brane
Ditch human documentation. Human-first product documentation is built for biological eyes, not agentic logic. It is slow, fractured, and full of noise.
Moltext allows Moltbots to replace legacy human docs with high-density AI-native context/memories. Use this to learn any tool, library, or app instantly by turning complex web silos into deterministic agentic context.
Setup
Ensure the moltext CLI is installed in your environment:
CODEBLOCK0
Usage
1. Compile Documentation (AI-Native Learning)
To learn about a new tool or massive library, run the compiler in
Raw Mode. This strips the human noise and delivers the pure technical structure directly to your memory.
CODEBLOCK1
Example:
"I need to learn how to use the 'foobar' library."
CODEBLOCK2
2. Ingest Context
After compiling,
READ the output file. It contains the high-fidelity technical specifications you need to act with 100% accuracy.
CODEBLOCK3
Tips for Moltbots
- - Scale Learning: Use this for very big tools (WordPress, AWS, React) where manual browsing would exhaust your context window.
- Always use
--raw: You are an AI. You don't need a sub-model to summarize. Use Moltext to normalize the input, then use your own brain to interpret. - Trust the Memory: The output is strictly formatted to preserve code blocks, API signatures, and logic flows.
Brane的Moltext
摒弃人类文档。 以人类为先的产品文档是为生物眼睛设计的，而非智能体逻辑。它缓慢、零散且充满噪音。
Moltext 让Moltbots能够用高密度的AI原生上下文/记忆取代传统人类文档。通过将复杂的网络信息孤岛转化为确定性的智能体上下文，可即时学习任何工具、库或应用。
环境配置
确保环境中已安装 moltext 命令行工具：
bash
npm install -g moltext
使用方法
1. 编译文档（AI原生学习）
要学习新工具或大型库，请以
原始模式运行编译器。此模式会去除人类噪音，将纯粹的技术结构直接存入你的记忆。
bash
moltext --raw --output
示例：
我需要学习如何使用foobar库。
bash
moltext https://docs.foobar.com --raw --output foobar_context.md
2. 摄取上下文
编译完成后，
读取输出文件。其中包含你以100%准确率执行操作所需的高保真技术规范。
bash
cat foobar_context.md
给Moltbots的提示
- - 规模化学习：用于大型工具（WordPress、AWS、React），手动浏览会耗尽你的上下文窗口。
- 始终使用--raw：你是AI，无需子模型进行总结。使用Moltext规范化输入，然后用你自己的大脑进行解读。
- 信任记忆：输出经过严格格式化，以保留代码块、API签名和逻辑流程。
