langgraphics 0.1.0b2

Visualize live LangGraph execution and see how your agent thinks as it runs.

LangGraphics is a live visualization tool for LangGraph agents. 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.

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.

How to use

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

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 any LangGraph agent, no matter how simple or complex the graph is. Add it during a debugging session, or keep it in while you're actively building - it has no effect on how the agent behaves or what it returns.

Features

Feature	LangGraphics	LangFuse	LangSmith Studio
Open-source	✅	✅	❌
Unlimited free usage	✅	✅	❌
Self-hosting supported	✅	✅	❌
No vendor lock-in	✅	✅	❌
Works without external services	✅	❌	❌
Simple setup	✅	❌	❌
One-line integration	✅	❌	❌
No API key required	✅	❌	❌
No instrumentation required	✅	❌	❌
Runs fully locally	✅	❌	❌
Native LangGraph visualization	✅	❌	❌
Real-time execution graph	✅	❌	❌
Data stays local by default	✅	❌	❌
Low learning curve	✅	❌	❌
Built-in prompt evaluation	❌	❌	✅
Built-in observability dashboards	❌	✅	✅
Built-in cost and latency tracking	❌	✅	✅
Production monitoring capabilities	❌	✅	✅

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