Metadata-Version: 2.4
Name: claudetimeline
Version: 0.1.0
Summary: Extract, index, and visualize Claude Code conversation history
Project-URL: Homepage, https://github.com/smm-h/claudetimeline
Project-URL: Repository, https://github.com/smm-h/claudetimeline
Project-URL: Issues, https://github.com/smm-h/claudetimeline/issues
Author-email: smm-h <smmh72@gmail.com>
License: Proprietary
License-File: LICENSE
Keywords: claude,claude-code,conversation,dashboard,history,rlsbl,timeline
Classifier: Development Status :: 4 - Beta
Classifier: Environment :: Console
Classifier: Environment :: Web Environment
Classifier: Framework :: FastAPI
Classifier: Intended Audience :: Developers
Classifier: License :: Other/Proprietary License
Classifier: Programming Language :: Python :: 3.11
Classifier: Programming Language :: Python :: 3.12
Classifier: Topic :: Software Development :: Documentation
Requires-Python: >=3.11
Requires-Dist: fastapi>=0.115.0
Requires-Dist: pyarrow>=24.0.0
Requires-Dist: slowapi>=0.1.9
Requires-Dist: uvicorn[standard]>=0.34.0
Provides-Extra: build
Requires-Dist: hdbscan>=0.8.41; extra == 'build'
Requires-Dist: numpy>=2.4.3; extra == 'build'
Requires-Dist: scikit-learn>=1.6.0; extra == 'build'
Requires-Dist: sentence-transformers>=5.3.0; extra == 'build'
Requires-Dist: umap-learn>=0.5.11; extra == 'build'
Description-Content-Type: text/markdown

# ClaudeTimeline

Extract, index, and visualize all Claude Code conversation history from your machine.

## Install

```
pip install claudetimeline
```

## Usage

```bash
# Build the database from your Claude Code history
claudetimeline build

# Start the dashboard
claudetimeline serve start

# Build + serve + open browser
claudetimeline open

# Development mode (hot reload)
claudetimeline dev
```

## Requirements

- Python 3.11+
- Claude Code conversation history (`~/.claude-*` profile directories)

## What it does

ClaudeTimeline discovers Claude Code profile directories, extracts user messages and tool calls from JSONL session files, and builds a SQLite database with full-text search, vector embeddings, and conversation tree reconstruction. The dashboard is a Svelte 5 + D3 frontend served by a FastAPI backend.
