Quickstart | ARGUS Docs

Prerequisites

Requirements

Python 3.9 or higher
pip (or any Python package manager)
A LangGraph pipeline (or any Python callable to test with)

Installation

bash

pip install argus-agents

That's it. No extra dependencies, no config files needed to start. ARGUS ships with sensible defaults that work out of the box.

Setup — Pick Whichever Fits Your Code

Option A — Pass graph to constructor (recommended)

python

from argus import ArgusWatcher

watcher = ArgusWatcher(graph)      # attaches monitoring automatically
app = graph.compile()
result = app.invoke(initial_state) # run auto-saves when the last node finishes
print(watcher.run_id)              # access the run ID directly

Option B — Separate watch call

python

from argus import ArgusWatcher

watcher = ArgusWatcher()
watcher.watch(graph)       # before graph.compile()
app = graph.compile()
result = app.invoke(initial_state)

Option C — After compile

python

from argus import ArgusWatcher

watcher = ArgusWatcher()
app = graph.compile(checkpointer=memory)
app = watcher.watch_compiled(app)   # works on already-compiled graphs
result = app.invoke(initial_state)

All three work. No changes to your node functions.

When is finalize() needed?

Runs are saved automatically for linear and fan-out/fan-in graphs. Only cyclic graphs (with back-edges) need a manual watcher.finalize() call.

Full Example

Here's a complete example — a simple LangGraph pipeline with ARGUS instrumentation:

pythonexample.py

1from argus import ArgusWatcher
2from langgraph.graph import StateGraph
3
4# 1. Create the watcher with graph (recommended)
5watcher = ArgusWatcher(graph)
6
7# 2. Define your graph (your existing code)
8graph = StateGraph(AgentState)
9graph.add_node("agent", call_model)
10graph.add_node("tools", tool_node)
11# ... add edges ...
12
13# 3. Compile and run
14app = graph.compile()
15result = app.invoke(initial_state)
16
17# Run auto-saves for linear/fan-out graphs
18# For cyclic graphs, call watcher.finalize()

View Results

After your run completes, you can view results in several ways:

bash

# List all runs
argus list

# View the most recent run
argus show last

# View a specific run by ID (or 8-char prefix)
argus show run abc12345

# Launch the web dashboard
argus ui

Video coming soon

Running argus show and viewing results in the terminal

Quick walkthrough of the ARGUS CLI trace viewer

Next Steps

Core Concepts — understand Watchers, Detectors, Traces, and Forensics
Configuration — customize detection sensitivity, enable semantic judging, configure storage
CLI Reference — all available commands and flags