Skip to content

Latest commit

 

History

History

Folders and files

NameName
Last commit message
Last commit date

parent directory

..
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

README.md

DevOps AI Toolkit — Documentation

AI-powered, read-only DevOps troubleshooting for logs, YAML, Terraform, Kubernetes, OpenStack and more. One shared analysis engine powers a CLI, a Python SDK, and a REST API — so you get identical behaviour everywhere.

The toolkit is read-only: it inspects text and produces guidance. It never executes commands, mutates files, or touches your infrastructure. It is offline-first: a packaged knowledge base of YAML "signatures" does the analysis with no API key required. Optional LLM providers add narrative enrichment behind a vendor-agnostic adapter.

from devops_ai_toolkit import AnalysisEngine

result = AnalysisEngine().analyze_file("nova.log")
print(result.summary)
pip install devops-ai-toolkit
devops-ai analyze nova.log
devops-ai explain CrashLoopBackOff

Table of contents

Get started

Using the toolkit

Plugins

  • Plugins — the plugin architecture: the AnalyzerPlugin interface, discovery, lifecycle, and CLI/REST
  • Plugin development — scaffold, test, package, and publish a plugin
  • Plugin marketplace — the PluginMetadata schema and the registry vision
  • Enterprise plugins — private, signed, offline, and pinned plugins; the trust model
  • LLM providers — the provider plugin point (Anthropic/OpenAI/Gemini/Azure/Ollama/null)

Understanding it

Contributing & development

Planned interfaces (design notes)

Project links

License

MIT. See the repository for full text.