Cosmo banner
fltman fltman

Cosmo

Data community

Description

AI-powered data analytics with GPU-accelerated graph visualization. Two AI agents debate your data autonomously.

Installation

This entry records only its repository, not the path inside it, so there is no exact command to give. Open the source below and copy the folder into ~/.claude/skills/, or the file into ~/.claude/agents/.

README

Cosmo

[![Support me on Patreon](https://img.shields.io/badge/Patreon-Support%20my%20work-FF424D?style=flat&logo=patreon&logoColor=white)](https://www.patreon.com/AndersBjarby)

**AI-powered data analytics with GPU-accelerated graph visualization.**

Drop any CSV or JSON. Two AI agents (Claude + Gemini) autonomously analyze your data, debate findings, create charts, and navigate a live graph — all in real time.

![Stack](https://img.shields.io/badge/Frontend-Vite%20%2B%20Cosmograph%202.0-blue) ![Stack](https://img.shields.io/badge/Backend-FastAPI%20%2B%20Pandas-green) ![Stack](https://img.shields.io/badge/AI-Claude%20%2B%20Gemini%20via%20OpenRouter-purple)

Quick Start

1. Clone and install

git clone  && cd cosmo-filesystem

# Frontend
npm install

# Backend
python3 -m venv venv
source venv/bin/activate
pip install -r backend/requirements.txt

2. Configure

cp .env.example .env
# Edit .env and add your OpenRouter API key

3. Run

# Terminal 1 — Backend
source venv/bin/activate
export $(cat .env | xargs)
python backend/server.py

# Terminal 2 — Frontend
npm run dev

Open **http://localhost:5199**

4. Use

  1. Drop a CSV or JSON file onto the page
  2. Ask a question: "give me insights"
  3. Enable the Companion checkbox for autonomous multi-agent debate

Features

Multi-Agent Debate

Two LLMs analyze your data simultaneously. The analyst (Claude Sonnet 4.6) responds first, then the companion (Gemini 3.1 Pro) challenges and extends. They alternate for 4 rounds, each updating the graph.

**Companion themes:**

Theme Behavior
Default Dig deeper, challenge conclusions
Devil's Advocate Poke holes, find counterexamples
Anomaly Hunter Focus on outliers and oddities
Optimizer Find actionable improvements
Connector Build relationships between data points
Storyteller Weave data into a narrative

Self-Building Analytics

The AI writes custom P