vibelens 0.8.0

Agent Trajectory visualization and analysis platform

VibeLens

Agent trajectory visualization and analysis platform. Parses, normalizes, and visualizes conversation histories from coding agent CLIs using the ATIF v1.6 trajectory model.

Live Demo: vibelens.chats-lab.org

Features

• Multi-agent parsing — Claude Code, Codex CLI, Gemini CLI, and Dataclaw formats with auto-detection
• Step timeline — Visual timeline with elapsed time, tool call details, and sub-agent spawn indicators

Quick Start

Install and run

pip install vibelens
vibelens serve

Or run without installing:

uvx vibelens serve

VibeLens opens your browser automatically and reads your local ~/.claude/ sessions by default. Use --no-open to disable the browser auto-open.

Development install

git clone https://github.com/yejh123/VibeLens.git
cd VibeLens
uv sync
uv run vibelens serve

Configuration

YAML-based configuration with environment variable overrides (VIBELENS_*). See config/vibelens.example.yaml for all options.

# Use a config file
vibelens serve --config config/self-use.yaml

# Override host/port
vibelens serve --host 0.0.0.0 --port 8080

Data Donation

VibeLens supports donating your agent conversation data to advance research on coding agent behavior. Donated sessions are collected by CHATS-Lab (Conversation, Human-AI Technology, and Safety Lab) at Northeastern University.

We welcome contributions of real-world coding agent trajectories across all supported formats. Your data helps the research community better understand how developers interact with AI coding assistants.

To donate, upload your data, select the sessions you want to donate, and click the Donate button.

Development

# Lint and test
uv run ruff check src/ tests/
uv run pytest tests/ -v -s

# Frontend dev server (hot reload)
cd frontend && npm install && npm run dev

Contributing

Contributions are welcome! Please ensure code passes ruff check and pytest before submitting.