https://github.com/invariantlabs-ai/explorer

A better way of testing, inspecting, and analyzing AI Agent traces.
https://github.com/invariantlabs-ai/explorer

agent agents ai debugging

Last synced: 3 days ago
JSON representation

A better way of testing, inspecting, and analyzing AI Agent traces.

• Host: GitHub
• URL: https://github.com/invariantlabs-ai/explorer
• Owner: invariantlabs-ai
• Created: 2024-12-09T12:38:04.000Z (about 1 month ago)
• Default Branch: main
• Last Pushed: 2025-01-03T10:49:18.000Z (5 days ago)
• Last Synced: 2025-01-03T11:41:09.126Z (5 days ago)
• Topics: agent, agents, ai, debugging
• Language: TypeScript
• Homepage: https://invariantlabs.ai/blog/explorer
• Size: 11.1 MB
• Stars: 16
• Watchers: 3
• Forks: 0
• Open Issues: 2
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

• awesome_ai_agents - Explorer - A better way of testing, inspecting, and analyzing AI Agent traces. (Building / Testing)
• awesome_ai_agents - Explorer - A better way of testing, inspecting, and analyzing AI Agent traces. (Building / Testing)

README

        
# Invariant Explorer

A tool for visualizing and exploring agent traces. [Hosted Version](https://explorer.invariantlabs.ai).



## Getting Started

Prerequisites: [Docker Compose](https://docs.docker.com/compose/install/)

To pull and launch Explorer, run the following commands:

```

# install Invariant package

pip install invariant-ai

# pull and launch Explorer application

invariant explorer

```

You can then access your Explorer instance via `http://localhost`. Data will be stored at `./data` of the current working directory.

Alternatively, you can try the _public and managed instance_ at [https://explorer.invariantlabs.ai](https://explorer.invariantlabs.ai).

## Development Setup

To get started, run the following command. Make sure you first install [Docker Compose](https://docs.docker.com/compose/install/).

```bash

./explorer.py

```

To open the Explorer interface go to `http://localhost`

This will automatically launch a local Explorer instance on your machine.

All data will be stored in `./data`. To reset the data, simply delete the `./data` directory.