BH

brichar01/hive.nvim

开发工具

本页由 AI 翻译,技术细节请以原文为准。 查看原文

1 stars 质量 59 趋势 22MIT

代理微提示和协作框架,既保持代理输出距离,又方便建议整合。

概览

代码上下文、模板提示和编码代理,在 Neovim 内部 Hive 实现了几个核心理念:- 将建议从代码中分离出来,减少集成开发环境中的视觉杂乱,同时提供高效的工具,以便接受即使是部分建议。- 控制一个面向任务的小型代理模型阵列,并访问它们的模式,因此得名蜂巢,每个昆虫执行单一且专门的工作,与其他昆虫并行。- 通过允许用户微调发送给模型的上下文,提高控制和生成精度,同时使用足够的生成上下文,使模型有充分机会生成用户想要的特定输出(强调自动源代码的形状,用户输入的方向)。- 通过提供开发者工具和知识,高效利用本地资源,产出优质的大型语言模型输出,只有在任务足够大或通用时才考虑云端解决方案。

概述(AI 翻译)

🐝  蜂巢.nvim  🐝

代码上下文、模板提示和编码代理,在 Neovim 内部


💡 使命宣言

Hive 实现了几个核心理念:

  • 将建议与代码分离,减少集成开发环境中的视觉杂乱,同时提供高效的工具来接受建议,即使是部分建议。
  • 控制一组任务导向的小型代理模型并获取它们的模式,因此得名蜂巢,每只昆虫执行单一且专门的工作,与其他昆虫并行。
  • 通过允许用户微调发送给模型的上下文,同时使用足够的生成上下文,使模型有良好机会产生用户想要的特定输出(强调自动源代码的形状,用户输入的方向)。
  • 通过为开发者提供工具和知识,高效利用本地资源,产出优质的LLM输出,只有当任务规模或通用时才考虑云解决方案。

这些核心理念的目标是让用户比纯粹的氛围编码更能控制代码风格。

本页由 AI 翻译,技术细节请以原文为准。

README

以下为原文 README 节选,完整内容请查看原文。

Code context, templated prompts and a coding agent, inside Neovim


💡 Mission statement

Hive implements a few core ideas:

  • Separate suggestions from the code to reduce visual clutter in the IDE, but provide efficient tools for accepting suggestions, even partial suggestions.
  • Control a task-oriented array of smaller agentic models and access patterns to them, hence the hive name, each insect does a single, specialised job, in parallel to others.
  • Improve control and generation accuracy by allowing the user to fine tune the context sent to the models, while using enough generated context to give the model a good chance to produce the specific output the user wants (emphasising shape from automatically sourced code, direction from user input).
  • Use local resources efficiently by giving the developer the tools and knowledge to produce good llm outputs, deferring to cloud solutions only when the task is appropriately large or general.

The aim of these core ideas is to provide a user with more control over code style than pure vibe coding. Allowing the user to inject their real world context into the code shape itself, providing effective abstractions instead of the common brute force and re-implementation methods typified by generated code.

🗺️ Status

Hive has three layers, each with its own command.

Command Layer Modules State
:Hive Agent: a Neovim frontend for pi-coding-agent hive.agent, hive.fs (planned) Planned, see PLAN.md
:HiveBare Direct: templated prompts sent straight to an endpoint hive.direct.* Fill-in-the-middle works
:HiveContext Context: select, gather and copy code hive.context.*, hive.workbench Works

Agent (planned)

Neovim starts a Node service that wraps @earendil-works/pi-coding-agent. The service owns the agent loop. Neovim is the filesystem: the agent’s read, write and edit tools use buffers and never touch disk. An edit to an open file changes the buffer and leaves the file on disk as it was. A write to a new file opens a listed, modified, unsaved buffer. bash, grep, find and ls still read the filesystem.

在 GitHub 查看完整 README

推荐工具

换一个关键词,或者移除筛选条件。

安装

npx skillfish add brichar01/hive.nvim
新手?先看 mcpskill.org 教程 →