Langgraphics AI Agent

<p align="center"> <picture class="github-only"> <source media="(prefers-color-scheme: light)" srcset="https://github.com/user-attachments/assets/58ee0608-b00c-4de5-b97a-736dda05d30a"> <source media="(prefers-color-scheme: dark)" srcset="https://github.com/user-attachments/assets/4f750d9e-21c3-4a6f-a07b-d1b51d1186bb"> <img alt="LangGraphics" src="https://github.com/user-attachments/assets/58ee0608-b00c-4de5-b97a-736dda05d30a" width="250px"> </picture> </p>

LangGraphics is a live visualization tool for LangGraph-based agent orchestration frameworks such as LangGraph and DeepAgents. It's especially useful when working with large networks: graphs with many nodes, branching conditions, and cycles are hard to reason about from the logs alone.

<p align="center"> <img alt="Workflow Visualization Demo" src="https://github.com/user-attachments/assets/1db519fb-0dd9-4fee-8bc8-f6b12cbf1342" width="800px"> </p>

Why it helps

Seeing the execution path visually makes it immediately obvious which branches were taken, where loops occurred, and where the agent got stuck or failed. It also helps when onboarding to an unfamiliar graph - a single run tells you more about the workflow than reading the graph definition ever could.

<p align="center"> <img alt="Full Window Demo" src="https://github.com/user-attachments/assets/32d63519-9622-4908-b0fd-67d0119cd3eb" width="800px"> </p>

How to use

One line is all it takes - wrap the compiled graph of your agent workflow with LangGraphics' watch function before invoking it, the visualization opens in your browser automatically, tracks the agent in real time, and makes tracing easy using the inspect panel.

from langgraph.graph import StateGraph, MessagesState
from langgraphics import watch

workflow = StateGraph(MessagesState)
workflow.add_node(...)
workflow.add_edge(...)

graph = watch(workflow.compile())

await graph.ainvoke({"messages": [...]})

Works with LangGraph-based agents of any level of complexity. Just add it during a debugging session, or keep it in while you're actively building - it does not affect how the agent behaves or what it returns.

Features

Feature	LangGraphics	LangFuse	LangSmith
Fully local
Standalone
Replay mode
Easy to learn
One-line setup
Data stays local
No API key required
Live execution graph
Subgraph visualization
No refactoring required
Self-hosted
No vendor lock-in
Unlimited free usage
Graph visualization
Cost & latency tracking
Prompt evaluation

Contribute

Any contribution is welcome. Feel free to open an issue or a discussion if you have any questions not covered here. If you have any ideas or suggestions, please open a pull request.

License

Copyright (C) 2026 Artyom Vancyan. MIT