Learn Agentic AI By Building.
No Code Required.

LangConfig is an open-source visual builder for LangChain and LangGraph. Drag, drop, connect, and deploy multi-agent workflows.

Simple enough for mom. Powerful enough for devs.

Building AI agents shouldn't require a PhD in LangChain.

You have an idea—a research assistant, a content pipeline, an automated analyst. But getting from concept to working agent means wrestling with graph definitions, state management, prompt engineering, and tool integration. By the time you've wired it all together, you've lost momentum.

verified

LangConfig gives you a visual canvas where agents become drag-and-drop components. Connect them. Test them live. Watch them think. Export production-ready code when you're done.

See Your Agents Think

Watch tool selection, reasoning chains, and outputs stream in real-time. Debug by seeing, not by reading logs.

  • check_circle Live execution streaming
  • check_circle Visual error detection
  • check_circle Interactive tool inspection

From Canvas to Production

Export your workflow as a standalone Python package with Streamlit UI—or share as JSON that anyone can import in one click.

  • check_circle One-click Python export
  • check_circle Streamlit UI included
  • check_circle JSON configuration sharing
LangConfig Workflow Export
lock

Your Data Stays Yours

Runs entirely local. Use your own API keys or local LLMs. No cloud dependencies. No data leaves your machine.

code_blocks

Built on LangChain & LangGraph

Not a black box—LangConfig generates real LangChain code. Eject anytime. You're never locked in.

Everything You Need to Build Agents

From first concept to final deployment, LangConfig covers the entire lifecycle.

construction

Build

  • Visual Workflow Canvas – Drag, drop, and connect agents
  • Custom Agent Builder – Configure prompts & tools with AI assist
  • RAG Knowledge Base – Upload docs for semantic search
  • Multi-Model Support – OpenAI, Anthropic, Gemini, Local models
science

Test

  • Interactive Chat – Test agents with live streaming
  • Real-Time Monitoring – Watch tool selection & tokens
  • Human-in-the-Loop – Add checkpoints for critical decisions
  • Iterate Quickly – Tweak and rerun in seconds
rocket_launch

Ship

  • Export to Code – Production-ready Python packages
  • Streamlit UI – Auto-generated web interface
  • JSON Sharing – Share workflows with one click
  • Local-First – Your data never leaves your machine

About

LangConfig is built and maintained by Cade Russell.

Langconfig's aspirations are to help others discover, learn, and build multi-agent systems with the lowest barrier possible. Whether you're a developer prototyping your next big idea or someone just getting started with agentic AI, LangConfig exists to empower more exploration into what we can leverage AI within our professions and daily lives.

Ready to stop context-switching?

LangConfig puts agent development in one place.
Clone the repo and build your first workflow in 10 minutes.

Get Started on GitHub