explaingit

deepagentlabs/agentic-chaos

Analysis updated 2026-05-18

13PythonAudience · developerComplexity · 3/5Setup · easy

TLDR

A Python toolkit that deliberately injects failures into LLM calls and multi-agent systems to test how well an app handles them.

Mindmap

mindmap
  root((agentic-chaos))
    What it does
      Fault injection for LLM calls
      Multi agent fault testing
      Standalone reports
    LLM faults
      Token timeout
      Rate limit storm
      Silent degradation
    Agent faults
      Tool call failure
      Memory corruption
      Infinite loop
    Use cases
      Resilience testing
      Catch silent bugs

Code map

Detail Auto

An interactive map of this repo's files and how they connect — its source is parsed live in your browser. Click Visualize to build it.

filefunction / class

What do people build with it?

USE CASE 1

Test whether an app handles a hung or timed-out LLM call gracefully

USE CASE 2

Simulate a rate-limit storm to check retry and backoff logic

USE CASE 3

Catch silent output corruption that normal monitoring would miss

USE CASE 4

Verify a multi-agent system has safeguards against infinite loops or tool failures

What is it built with?

Python

How does it compare?

deepagentlabs/agentic-chaos1lystore/awaek47cid/wp2shell-lab
Stars131313
LanguagePythonPythonPython
Setup difficultyeasymoderatemoderate
Complexity3/52/54/5
Audiencedevelopervibe coderresearcher

Figures from each repo's GitHub metadata at analysis time.

How do you get it running?

Difficulty · easy Time to first run · 30min

Installs standalone via pip install agentic-chaos, with no required dependency on other packages.

In plain English

agentic-chaos is a Python testing toolkit that deliberately breaks an application's calls to language models and multi-agent systems, then reports exactly what happened, so a developer can see how their code handles failure before it happens in production. It installs on its own with pip and does not require any other package to work, including a related project called AgenticLens, though it can optionally feed its results into that tool if someone uses both. At the center of the library is a function called chaos_call, which wraps a normal function call and only misbehaves when it is running inside an active chaos session. Outside of that session, it passes straight through as if the library were not there, so the same instrumented code stays safe to ship. The three faults available in this first version are a token timeout that hangs a call before raising an error, a rate limit storm that fails the first few calls before letting things through normally, and silent degradation, which lets a call succeed but quietly corrupts its returned text while keeping the timing and token counts looking normal. That last one is called out as the hardest to catch, since nothing in ordinary cost or latency monitoring would look wrong. A second version adds agent level faults for testing systems made of multiple cooperating agents: forcing a specific tool call to error, time out, or return empty, corrupting shared memory between agents by truncating or garbling it, and forcing an agent to loop past its intended turn limit to check whether it has a safeguard against that. A wrap_tool helper applies these faults transparently to existing tool functions while also recording which agent called which tool, building a map of how the system is actually wired together. Everything can be run from the command line against a real script, printing a table of what faults fired and what happened, with the option to save a standalone JSON report that needs no other tool to read. A planned third version, a prompt and model drift detector, is listed on the roadmap but not yet built.

Copy-paste prompts

Prompt 1
Show me how to wrap my LLM retriever call with chaos_call to test for token timeouts.
Prompt 2
Use agentic-chaos to simulate a rate-limit storm against my app and show me the resulting report.
Prompt 3
Explain how the silent_degradation fault works and why it's hard to detect.
Prompt 4
Set up wrap_tool and TopologyTracker to test my multi-agent app's tool call failures.

Frequently asked questions

What is agentic-chaos?

A Python toolkit that deliberately injects failures into LLM calls and multi-agent systems to test how well an app handles them.

What language is agentic-chaos written in?

Mainly Python. The stack also includes Python.

How hard is agentic-chaos to set up?

Setup difficulty is rated easy, with roughly 30min to a first successful run.

Who is agentic-chaos for?

Mainly developer.

Open on GitHub → Explain another repo

This repo across BitVibe Labs

Verify against the repo before relying on details.