https://github.com/copilotkit/open-research-ana
🤖 An open-source, AI agent-native research canvas application that performs real-time search with HITL (Human in The Loop) capabilities, powered by CopilotKit, Tavily and LangGraph
https://github.com/copilotkit/open-research-ana
agent-native ai anthropic canvas chatbot chatgpt copilotkit hitl human-in-the-loop langchain langgraph openai realtime research tavily
Last synced: 7 months ago
JSON representation
🤖 An open-source, AI agent-native research canvas application that performs real-time search with HITL (Human in The Loop) capabilities, powered by CopilotKit, Tavily and LangGraph
- Host: GitHub
- URL: https://github.com/copilotkit/open-research-ana
- Owner: CopilotKit
- Created: 2024-11-04T01:08:35.000Z (12 months ago)
- Default Branch: main
- Last Pushed: 2025-04-01T23:39:15.000Z (7 months ago)
- Last Synced: 2025-04-02T03:17:55.151Z (7 months ago)
- Topics: agent-native, ai, anthropic, canvas, chatbot, chatgpt, copilotkit, hitl, human-in-the-loop, langchain, langgraph, openai, realtime, research, tavily
- Language: TypeScript
- Homepage: https://open-research-ana.vercel.app
- Size: 641 KB
- Stars: 211
- Watchers: 5
- Forks: 52
- Open Issues: 2
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
- awesome-ChatGPT-repositories - open-research-ANA - 🤖 An open-source, AI agent-native research canvas application that performs real-time search with HITL (Human in The Loop) capabilities, powered by CopilotKit, Tavily and LangGraph (Chatbots)
README
# open-research-ANA 🔍
This demo showcases ANA (Agent Native Application), a research canvas app that combines Human-in-the-Loop capabilities with [Tavily's](https://tavily.com/) real-time search and [CopilotKit's](https://copilotkit.ai) agentic interface.
Powered by [LangGraph](https://www.langchain.com/langgraph), it simplifies complex research tasks, making them more interactive and efficient.
## Quick Start 🚀
### 1. Prerequisites
This projects uses the following tools:
- [pnpm](https://pnpm.io/installation)
- [Docker](https://docs.docker.com/get-docker/)
- [Langgraph CLI](https://langchain-ai.github.io/langgraph/cloud/reference/cli/)
### 2. API Keys Needed
Running locally, you'll need the following API keys:
- [OpenAI](https://platform.openai.com/api-keys)
- [Tavily](https://tavily.com/#pricing)
- [LangSmith](https://docs.smith.langchain.com/administration/how_to_guides/organization_management/create_account_api_key)
- [CopilotKit](https://cloud.copilotkit.ai)
### 3. Start the Agent
There are two main components to this project: the agent and the frontend. First, we'll start the agent.
```bash
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:
```bash
npx copilotkit@latest dev --port 8123
```
### 5. Start the Frontend
Next, we'll start the frontend.
```bash
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](https://docs.copilotkit.ai/coagents)
- [LangGraph Platform Docs](https://langchain-ai.github.io/langgraph/cloud/deployment/cloud/)