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

What it solves

It simplifies complex research tasks by providing a research canvas application that integrates real-time web search with an interactive, agentic interface, allowing for human-in-the-loop collaboration.

How it works

The application uses LangGraph to power the agent logic, Tavily for real-time search capabilities, and CopilotKit to provide the agentic user interface and connectivity between the frontend and the agent.

Who it’s for

Researchers and users who need an interactive tool to conduct complex research tasks with the assistance of an AI agent.

Highlights

  • Human-in-the-Loop capabilities for interactive research.
  • Integration with Tavily for real-time web searching.
  • Powered by LangGraph for agent orchestration.
  • Agent Native Application (ANA) architecture.

Related

  • Project
    langchain-ai/agent-inbox

    A user interface for LangGraph agents that allows humans to review, edit, and respond to agent interrupts in a centralized inbox.

  • Project
    GiovanniPasq/agentic-rag-for-dummies

    A modular Agentic RAG framework using LangGraph that implements hierarchical indexing, multi-agent parallel retrieval, and human-in-the-loop query clarification.

  • Project
    NeuroAIHub/BrainPilot

    An open-source, human-in-the-loop agentic research system for brain science that coordinates specialist agents to automate literature review, experiment design, and data analysis.

  • Project
    erthorpabar/pabar_agent_runtime

    An AI agent runtime framework that integrates chat, RAG, and agentic loops to enable professional automation tasks across desktop and mobile platforms.

  • Project
    langchain-ai/react-agent

    A LangGraph template for implementing a ReAct agent that iteratively reasons and executes tool-based actions to solve complex user queries.