Nexus

AI tracing and instrumentation for LangChain and custom Python agents

Nexus helps you trace AI execution in two ways:

• Automatic tracing via a LangChain callback handler.
• Manual tracing via NexusClient spans in your own code.

You can log runs, connect parent and child operations, and inspect tree structures from stored traces.

Start here

Quickstart

Install the package and send your first trace.

Manual tracing

Instrument custom Python code with span context managers.

LangChain integration

Attach PrintingHandler to chains, tools, and agents.

Configuration

Configure DB and trigger behavior for your environment.

What Nexus captures

• run_id, trace_id, parent_run_id, and user_id
• event category (chain, llm, tool, agent, retriever, and more)
• name metadata (for model, chain, tool, and agent nodes)
• JSON payloads for input, output, and error

This structure lets you reconstruct execution trees after a run and debug both failed and successful paths.

Choose your tracing path

I use LangChain

Plug in a callback and collect traces with minimal code changes.

I need full control

Add spans exactly where your app does meaningful work.

Your Nexus API key (nexus_api_key) is available on the Nexus platform.