
Claude 代码的上下文管理。钩子通过账本和切换维护状态。MCP 执行无上下文污染。智能体编排,带有隔离上下文窗口。
概览
一个基于Claude代码构建的持久、学习型、多代理开发环境 将 Claude Code 转变为一个持续学习的系统,能够在会话间保持上下文,协调专业代理,并通过智能代码分析消除代币浪费。 Claude Code 有一个:当上下文填满时,系统会压缩你的对话,丢失会话中细微差别的理解和决策。 自动提取学习内容,然后用完整的上下文重新开始。 这个名字是双关语。因为Claude会在会话间保持状态。因为每次会话都让系统更智能——学习内容像复利一样累积。 我们抵制插件的蔓延。你添加的每一个MCP、订阅和工具都承诺改进,但却有可能因冲突而破坏上下文、工具或提示。 - — 无需强制付费服务。复杂性和NIA是可选的、每个代币价值较高的系统。- — 一个学习处理边缘情况的系统,而非收集插件的系统。
概述(AI 翻译)
一个基于Claude代码构建的持久、学习型多代理开发环境
连续Claude将Claude代码转变为一个持续学习的系统,能够在会话间保持上下文,协调专业代理,并通过智能代码分析消除代币浪费。
目录
- 为什么是连续的克洛德?
- 设计原则
- 如何与克劳德交谈
- 快速入门
- 建筑学
- 核心系统
- 技能(109)
- 特工(32)
- 胡克斯(30)
- 简要代码分析
- 记忆系统
- 连续性系统
- 数学系统
- 工作流程
- 安装
- 更新
- 配置
- 贡献
- 许可证
为什么是连续的克劳德?
Claude Code 存在一个压缩问题:当上下文填满时,系统会压缩你的对话,丢失会话中细致的理解和决策。
**连续Claude用以下方式解决这个问题:
| 问题 | 解决方案 |
|---|---|
| 压缩时的上下文丢失 | YAML 切换——更高效的令牌传输 |
| 每次会话重新开始 | 记忆系统回忆 + 守护进程自动提取学习内容 |
| 读取整个文件会烧毁令牌 | 五层代码分析 + 语义索引 |
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。
Continuous Claude
A persistent, learning, multi-agent development environment built on Claude Code
Continuous Claude transforms Claude Code into a continuously learning system that maintains context across sessions, orchestrates specialized agents, and eliminates wasting tokens through intelligent code analysis.
Table of Contents
- Why Continuous Claude?
- Design Principles
- How to Talk to Claude
- Quick Start
- Architecture
- Core Systems
- Workflows
- Installation
- Updating
- Configuration
- Contributing
- License
Why Continuous Claude?
Claude Code has a compaction problem: when context fills up, the system compacts your conversation, losing nuanced understanding and decisions made during the session.
Continuous Claude solves this with:
| Problem | Solution |
|---|---|
| Context loss on compaction | YAML handoffs - more token-efficient transfer |
| Starting fresh each session | Memory system recalls + daemon auto-extracts learnings |
| Reading entire files burns tokens | 5-layer code analysis + semantic index |
| Complex tasks need coordination | Meta-skills orchestrate agent workflows |
| Repeating workflows manually | 109 skills with natural language triggers |
The mantra: Compound, don’t compact. Extract learnings automatically, then start fresh with full context.
Why “Continuous”? Why “Compounding”?
The name is a pun. Continuous because Claude maintains state across sessions. Compounding because each session makes the system smarter—learnings accumulate like compound interest.
Design Principles
An agent is five things: Prompt + Tools + Context + Memory + Model.
| Component | What We Optimize |
|---|---|
| Prompt | Skills inject relevant context; hooks add system reminders |
| Tools | TLDR reduces tokens; agents parallelize work |
| Context | Not just what Claude knows, but how it’s provided |
| Memory | Daemon extracts learnings; recall surfaces them |
| Model | Becomes swappable when the other four are solid |
Anti-Complexity
安装
This server does not publish a one-line install command.
Open the repository installation guide 新手?先看 mcpskill.org 教程 →