InstaGraph

Stale
GitHub Python MIT

Description

InstaGraph is a GPT-powered tool that turns text or URLs into color-coded knowledge graphs of entities and relationships, with optional Neo4j and FalkorDB persistence for explainable AI agent memory structures.

Key Features

  • Text to graph - extract entities and relationships from natural language or URLs
  • Color-coded visualization - nodes and edges are color-coded for instant entity-type readability
  • Responsive web UI - browser interface that works on desktop and mobile
  • Graph persistence - optional Neo4j or FalkorDB backends for storing generated knowledge graphs
  • History view - REST endpoints to revisit and expand on previously generated graphs
  • Simple API - exposes GET Response, GET Graph, and GET History REST endpoints

Use Cases

💡 Extract entity-relationship graphs from long documents or web pages
💡 Build explainable, visual long-term memory for AI agents
💡 Accumulate and query historical knowledge graphs in Neo4j or FalkorDB
💡 Teach or research by visualizing connections between concepts
💡 Use as a prompt-engineering visualizer to debug LLM output structure

Tags

knowledge-graph llm neo4j entity-extraction visualization

Categories

📊 Observability

Quick Start

# Clone and install dependencies
git clone https://github.com/yoheinakajima/instagraph.git
cd instagraph
pip install -r requirements.txt

# Configure OpenAI key
mv .env.example .env
echo "OPENAI_API_KEY=sk-..." >> .env

# Launch the Flask app
python main.py

# Open http://localhost:8080 in your browser and submit text or a URL
Visit GitHub Visit Website

Related Projects