open-research-ANA 🔍

This demo showcases ANA (Agent Native Application), a research canvas app that combines Human-in-the-Loop capabilities with Tavily's real-time search and CopilotKit's agentic interface.

Powered by LangGraph, it simplifies complex research tasks, making them more interactive and efficient.

Explore the CopilotKit docs »

Quick Start 🚀

1. Prerequisites

This projects uses the following tools:

• pnpm
• Docker
• Langgraph CLI

2. API Keys Needed

Running locally, you'll need the following API keys:

• OpenAI
• Tavily
• LangSmith
• CopilotKit

3. Start the Agent

There are two main components to this project: the agent and the frontend. First, we'll start the agent.

cd agent

# Create and populate .env
cat << EOF > .env
OPENAI_API_KEY=your_key
TAVILY_API_KEY=your_key
LANGSMITH_API_KEY=your_key
EOF

## Start the agent
langgraph up

# Note the API URL from the output (e.g., http://localhost:8123)

4. Open a tunnel to your local agent

Create a tunnel to your local agent:

npx copilotkit@latest dev --port 8123

5. Start the Frontend

Next, we'll start the frontend.

cd frontend
pnpm install

# Create and populate .env
cat << EOF > .env
OPENAI_API_KEY=your_openai_key
LANGSMITH_API_KEY=your_langsmith_key
NEXT_PUBLIC_COPILOT_CLOUD_API_KEY=your_copilot_cloud_key
EOF

# Start the app
pnpm run dev

Documentation 📚

• CopilotKit Docs
• LangGraph Platform Docs

Note: This project has been consolidated into the CopilotKit monorepo. The latest version lives at examples/showcases/research-canvas. Please open issues and pull requests in the main CopilotKit repository.