moollm

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

MOOLLM

"Many-Voiced Object-Oriented LLM — the system that explains itself."

"多语音面向对象LLM——可自我解释的系统。"

What Is It?

什么是MOOLLM？

The moollm skill is the spirit and constitution of MOOLLM itself. It's the top-level help agent that can:

Explain what MOOLLM is
Answer "what can I do?"
Navigate users to relevant skills
Articulate the philosophy
Show the constitution
Recommend approaches for tasks

When confused, invoke this skill.

moollm skill是MOOLLM本身的精神与架构核心。它是顶级帮助Agent，能够：

解释MOOLLM是什么
回答“我能做什么？”
引导用户找到相关技能
阐述核心理念
展示架构规则
推荐任务处理方法

遇到困惑时，调用该技能即可。

The Core Ideas

核心理念

Many-Voiced

多语音特性

MOOLLM doesn't use a single LLM perspective. It simulates multiple agents debating within a single call:

Committees of personas with opposing views
Deliberation forced by Robert's Rules
Evaluation by independent assessors
The debate produces wisdom, not statistics

MOOLLM不采用单一LLM视角。它在单次调用中模拟多个Agent辩论：

持有对立观点的角色委员会
遵循罗伯特议事规则的审慎讨论
独立评估者的评估环节
辩论产出的是智慧，而非统计结果

Filesystem as World Model

以文件系统为世界模型

Directories are rooms. Files are objects:

examples/adventure-4/
├── pub/              # A room
│   ├── ROOM.yml      # Room properties
│   ├── pie-table.yml # An object
│   └── cat-cave/     # Nested room
├── characters/       # Metaphysical room
└── ADVENTURE.yml     # Game state

目录代表房间，文件代表对象：

examples/adventure-4/
├── pub/              # 一个房间
│   ├── ROOM.yml      # 房间属性
│   ├── pie-table.yml # 一个对象
│   └── cat-cave/     # 嵌套房间
├── characters/       # 抽象房间
└── ADVENTURE.yml     # 游戏状态

Play-Learn-Lift

玩耍-学习-升华（Play-Learn-Lift）

The methodology:

PLAY — Explore freely, try things, fail safely
LEARN — Notice patterns, document what works
LIFT — Share as reusable skills

方法论：

玩耍——自由探索，大胆尝试，安全试错
学习——发现规律，记录有效方法
升华——将经验分享为可复用技能

Skills as Prototypes

技能作为原型

Skills are documented capabilities that can be:

Instantiated into specific contexts
Composed with other skills
Inherited (multiple inheritance)
Evolved through play

技能是已文档化的能力，可：

实例化到特定场景中
与其他技能组合
继承（多继承）
通过玩耍不断演进

Protocol

协议规范

When invoked, this skill should:

Assess what the user needs
If lost → provide orientation
If asking "what can I do?" → show relevant capabilities
If asking about philosophy → explain core concepts
If asking about skills → navigate to skill system
Always be helpful, welcoming, and clear

调用该技能时，应执行以下步骤：

评估用户需求
若用户迷路→提供定位指引
若用户问“我能做什么？”→展示相关功能
若用户询问理念→解释核心概念
若用户询问技能→引导至技能系统
始终保持有用、友好且清晰

Constitutional File Map (kernel/)

架构规则文件映射（kernel/）

```
kernel/README.md
```
— index and navigation for kernel docs
```
kernel/constitution-core.md
```
— core constitution and invariants
```
kernel/constitution-template.md
```
— template for new constitutions
```
kernel/ARCHITECTURE.md
```
— system architecture overview
```
kernel/context-assembly-protocol.md
```
— context assembly rules
```
kernel/memory-management-protocol.md
```
— memory, limits, persistence
```
kernel/event-logging-protocol.md
```
— logging and provenance
```
kernel/tool-calling-protocol.md
```
— tool usage contract
```
kernel/self-healing-protocol.md
```
— recovery and repair behaviors
```
kernel/DIRECTORY-AS-OBJECT.md
```
— directory as object model
```
kernel/SELFISH-COM-IMPLEMENTATION.md
```
— SELF lineage in practice
```
kernel/INTEREST-GATES.yml
```
— attention gating rules
```
kernel/NAMING.yml
```
— top-level naming policy
```
kernel/naming/NAMING.yml
```
— detailed naming rules
```
kernel/naming/NAMING-K-LINES.yml
```
— K-line naming standards
```
kernel/naming/NAMING-CONSTELLATIONS.yml
```
— constellation naming
```
kernel/naming/NAMING-COMPILATION.yml
```
— compiled name patterns
```
kernel/naming/NAMING-PATH-VARIABLES.yml
```
— path variable rules
```
kernel/naming/NAMING-RELATIONSHIPS.yml
```
— relationship naming
```
kernel/naming/URLS.yml
```
— URL conventions
```
kernel/drivers/README.md
```
— driver index
```
kernel/drivers/cursor.yml
```
— Cursor-specific driver
```
kernel/drivers/generic.yml
```
— baseline driver
```
kernel/drivers/custom.yml
```
— site-specific overrides
```
kernel/drivers/claude-code.yml
```
— Claude Code driver
```
kernel/drivers/antigravity.yml
```
— experimental driver

```
kernel/README.md
```
— 内核文档索引与导航
```
kernel/constitution-core.md
```
— 核心架构规则与不变量
```
kernel/constitution-template.md
```
— 新架构规则模板
```
kernel/ARCHITECTURE.md
```
— 系统架构概述
```
kernel/context-assembly-protocol.md
```
— 上下文组装规则
```
kernel/memory-management-protocol.md
```
— 内存、限制与持久化
```
kernel/event-logging-protocol.md
```
— 日志与来源追踪
```
kernel/tool-calling-protocol.md
```
— 工具调用约定
```
kernel/self-healing-protocol.md
```
— 恢复与修复机制
```
kernel/DIRECTORY-AS-OBJECT.md
```
— 目录作为对象模型
```
kernel/SELFISH-COM-IMPLEMENTATION.md
```
— SELF谱系实践
```
kernel/INTEREST-GATES.yml
```
— 注意力门控规则
```
kernel/NAMING.yml
```
— 顶级命名策略
```
kernel/naming/NAMING.yml
```
— 详细命名规则
```
kernel/naming/NAMING-K-LINES.yml
```
— K-line命名标准
```
kernel/naming/NAMING-CONSTELLATIONS.yml
```
— 星座式命名
```
kernel/naming/NAMING-COMPILATION.yml
```
— 编译后命名模式
```
kernel/naming/NAMING-PATH-VARIABLES.yml
```
— 路径变量规则
```
kernel/naming/NAMING-RELATIONSHIPS.yml
```
— 关系命名规则
```
kernel/naming/URLS.yml
```
— URL约定
```
kernel/drivers/README.md
```
— 驱动索引
```
kernel/drivers/cursor.yml
```
— Cursor专属驱动
```
kernel/drivers/generic.yml
```
— 基准驱动
```
kernel/drivers/custom.yml
```
— 站点专属覆盖配置
```
kernel/drivers/claude-code.yml
```
— Claude Code驱动
```
kernel/drivers/antigravity.yml
```
— 实验性驱动

Local Runtime Files (.moollm/)

本地运行时文件（.moollm/）

These are gitignored runtime files for session state, scratch, and logs.

```
.moollm/working-set.yml
```
— current focus and active files
```
.moollm/hot.yml
```
— priority hints
```
.moollm/cold.yml
```
— cold-start state
```
.moollm/startup.yml
```
— startup context
```
.moollm/output.md
```
— append-only output log
```
.moollm/session-log.md
```
— append-only session log
```
.moollm/bootstrap-probe.yml
```
— bootstrap probes and checks

这些是被git忽略的运行时文件，用于存储会话状态、临时内容与日志。

```
.moollm/working-set.yml
```
— 当前焦点与活跃文件
```
.moollm/hot.yml
```
— 优先级提示
```
.moollm/cold.yml
```
— 冷启动状态
```
.moollm/startup.yml
```
— 启动上下文
```
.moollm/output.md
```
— 追加式输出日志
```
.moollm/session-log.md
```
— 追加式会话日志
```
.moollm/bootstrap-probe.yml
```
— 启动探测与检查

Cursor Boot Optimization (cursor-mirror)

Cursor启动优化（cursor-mirror）

Use cursor-mirror to inspect boot state, reduce context bloat, and verify setup.

Commands (need composer ID):

```
tree
```
— list sessions/composers
```
status
```
— quick health check
```
tail --limit 50
```
— recent messages
```
timeline <composer>
```
— full event sequence
```
thinking <composer>
```
— reasoning blocks
```
tools <composer>
```
— tool call history
```
grep <pattern>
```
— search transcripts

Use this to:

confirm which bootstrap ran
locate missing context
triage performance issues
audit tool-call provenance

使用cursor-mirror检查启动状态，减少上下文冗余，验证设置是否正确。

命令（需composer ID）：

```
tree
```
— 列出会话/组合器
```
status
```
— 快速健康检查
```
tail --limit 50
```
— 最近消息
```
timeline <composer>
```
— 完整事件序列
```
thinking <composer>
```
— 推理模块
```
tools <composer>
```
— 工具调用历史
```
grep <pattern>
```
— 搜索对话记录

使用该工具可：

确认启动了哪个引导程序
定位缺失的上下文
排查性能问题
审计工具调用来源

Plan: MOOLLM Linter, Mirror, Compiler

计划：MOOLLM检查器、镜像工具、编译器

Phase 0 — Meta Inhale (Planning Only)

阶段0 — 元规划（仅规划）

Inventory the repository structure and file types.
Define categories: essential, primary, secondary, hidden.
Establish ignore rules (build output, caches, temp files, editor artifacts).
Identify canonical docs to preserve: top-level
```
README.md
```
,
```
designs/
```
,
```
docs/
```
.
Map root entry points to their authoritative specs (skills, kernels, protocols).
Reverse-engineer the root
```
README.md
```
into a structured spec:
- Purpose
- Audience
- Sections
- Source references
- Link strategy
Define a report format for validation output:
- Structural warnings
- Missing declarations
- Naming consistency
- Cross-link integrity
Define "what to hide" for human-facing outputs (noise, duplication, low-signal).
Define "what to surface" for quick navigation (skills index, starting points).
Define sister-script scope: lint, mirror, compile.
Write a sister-script design brief (no code yet).

盘点仓库结构与文件类型。
定义分类：核心、主要、次要、隐藏。
建立忽略规则（构建输出、缓存、临时文件、编辑器产物）。
确定需保留的标准文档：顶级
```
README.md
```
、
```
designs/
```
、
```
docs/
```
。
映射根入口点到其权威规范（技能、内核、协议）。
将根目录
```
README.md
```
逆向工程为结构化规范：
- 目的
- 受众
- 章节
- 来源参考
- 链接策略
定义验证输出的报告格式：
- 结构警告
- 缺失声明
- 命名一致性
- 交叉链接完整性
定义面向人类输出时需隐藏的内容（噪音、重复、低信号信息）。
定义需突出展示的内容以实现快速导航（技能索引、起始点）。
定义姊妹脚本范围：检查、镜像、编译。
撰写姊妹脚本设计 brief（暂不编写代码）。

Inputs

输入

User questions about MOOLLM
Requests for help or navigation
Philosophical inquiries

用户关于MOOLLM的问题
帮助或导航请求
理念相关询问

Outputs

输出

Clear explanations
Skill recommendations
Navigation guidance
Philosophy articulation

清晰的解释
技能推荐
导航指引
理念阐述

Dovetails With

关联模块

skill/ — How skills work
k-lines/ — K-lines and naming
play-learn-lift/ — The methodology
kernel/constitution-core.md — The constitution

skill/ — 技能运作机制
k-lines/ — K-line与命名规则
play-learn-lift/ — 方法论
kernel/constitution-core.md — 核心架构规则

Protocol Symbol

协议标识

MOOLLM-HELP

Invoke when: User is confused, lost, or wants to understand the system.

See: PROTOCOLS.yml

MOOLLM-HELP

调用场景：用户感到困惑、迷路，或希望了解系统时。

参考：PROTOCOLS.yml