# Claude Memory Compiler — Evolving Knowledge Base

> Auto-capture Claude Code sessions into a structured knowledge base. Hooks extract decisions and lessons, compiler organizes into cross-referenced articles. No vector DB needed. 365+ stars.

## Install

Save the content below to `.claude/skills/` or append to your `CLAUDE.md`:

## Quick Use

1. Clone and install:
```bash
git clone https://github.com/coleam00/claude-memory-compiler.git
cd claude-memory-compiler
uv sync
```

2. Copy the hooks config to your project:
```bash
cp .claude/settings.json your-project/.claude/settings.json
```

3. Use Claude Code as normal — sessions are captured automatically. Compile daily:
```bash
uv run python scripts/compile.py
```

---

## Intro

Claude Memory Compiler is an evolving personal knowledge base for Claude Code with 365+ GitHub stars. It automatically captures your Claude Code sessions via hooks, extracts key decisions and lessons using the Claude Agent SDK, and compiles them into structured, cross-referenced knowledge articles. No vector database needed — uses a structured `index.md` approach that works better at personal scale. Inspired by Karpathy's LLM Knowledge Base architecture. Best for power users of Claude Code who want persistent memory across sessions.

See also: [Claude Code Skills on TokRepo](https://tokrepo.com/en/collections/skills).

---

## Claude Memory Compiler — Build Memory from Your AI Sessions

### The Problem

Claude Code sessions are ephemeral — valuable decisions, debugging insights, and architectural choices are lost when the session ends. You end up re-explaining the same context over and over.

### The Solution

Claude Memory Compiler hooks into your Claude Code workflow and builds a growing knowledge base automatically:

1. **Session End** → hooks trigger `flush.py`
2. **Extraction** → Claude Agent SDK identifies decisions, patterns, and lessons
3. **Daily Logs** → insights saved to timestamped daily files
4. **Compilation** → `compile.py` organizes into cross-referenced articles
5. **Injection** → SessionStart hook loads `index.md` into next session

### Key Features

- **Automatic capture** — hooks fire on session end + pre-compaction safety net
- **Knowledge extraction** — AI identifies decisions, patterns, and lessons learned
- **No vector database** — structured `index.md` works better at personal scale
- **Health checks** — `lint.py` runs 7 checks (broken links, orphans, contradictions, staleness)
- **Daily compilation** — automatically triggers after 6 PM local time
- **Query interface** — search your knowledge base from the command line

### Setup

```bash
# Install dependencies
uv sync

# Copy hooks config to your project
cp .claude/settings.json your-project/.claude/settings.json

# Compile knowledge base
uv run python scripts/compile.py

# Query your knowledge base
uv run python scripts/query.py "How did I handle the auth migration?"

# Run health checks
uv run python scripts/lint.py
```

### How Knowledge Is Organized

```
knowledge/
  index.md          # Master index, injected into each session
  architecture/     # System design decisions
  debugging/        # Bug patterns and solutions
  conventions/      # Code style and project rules
  integrations/     # Third-party service patterns
```

### FAQ

**Q: What is Claude Memory Compiler?**
A: An open-source tool that automatically captures Claude Code sessions and compiles them into a structured, searchable knowledge base that persists across conversations.

**Q: Does it require a vector database?**
A: No. It uses a structured `index.md` approach inspired by Karpathy's LLM Knowledge Base architecture, which works better than RAG at personal scale.

**Q: How does it integrate with Claude Code?**
A: Via Claude Code hooks — it captures sessions automatically on end, extracts insights, and injects the knowledge index at session start.

---

## Source & Thanks

> Created by [Cole Medin](https://github.com/coleam00). Licensed under open source.
>
> [claude-memory-compiler](https://github.com/coleam00/claude-memory-compiler) — ⭐ 365+

Thanks to Cole Medin for building a practical memory system for Claude Code power users.

---

<!-- ZH -->

## 快速使用

1. 克隆并安装：
```bash
git clone https://github.com/coleam00/claude-memory-compiler.git
cd claude-memory-compiler
uv sync
```

2. 复制 hooks 配置到你的项目：
```bash
cp .claude/settings.json your-project/.claude/settings.json
```

3. 正常使用 Claude Code，会话自动捕获。每日编译：
```bash
uv run python scripts/compile.py
```

---

## 简介

Claude Memory Compiler 是一个 Claude Code 的个人知识库工具，GitHub 365+ star。自动通过 hooks 捕获 Claude Code 会话，用 Claude Agent SDK 提取关键决策和经验教训，编译成结构化、交叉引用的知识文章。不需要向量数据库，使用结构化 index.md 方式。灵感来源于 Karpathy 的 LLM 知识库架构。适合 Claude Code 重度用户。

---

## Claude Memory Compiler — 从 AI 会话构建记忆

### 工作流程

1. **会话结束** → hooks 触发 flush.py
2. **知识提取** → Claude Agent SDK 识别决策、模式、教训
3. **每日日志** → 保存到带时间戳的文件
4. **编译** → compile.py 组织成交叉引用文章
5. **注入** → SessionStart hook 加载 index.md 到下次会话

### 核心特性

- **自动捕获** — hooks 在会话结束时触发
- **无需向量数据库** — 结构化 index.md 在个人规模更好用
- **健康检查** — lint.py 运行 7 项检查
- **查询接口** — 命令行搜索知识库

### FAQ

**Q: Claude Memory Compiler 是什么？**
A: 自动捕获 Claude Code 会话并编译成结构化、可搜索知识库的开源工具。

**Q: 需要向量数据库吗？**
A: 不需要，使用结构化 index.md 方式，在个人规模比 RAG 更好用。

---

## 来源与感谢

> Created by [Cole Medin](https://github.com/coleam00). Licensed under open source.
>
> [claude-memory-compiler](https://github.com/coleam00/claude-memory-compiler) — ⭐ 365+


---
Source: https://tokrepo.com/en/workflows/4388e2e8-33ce-11f1-9bc6-00163e2b0d79
Author: Skill Factory