PythonHub

Macro Evals for Agentic Systems This cookbook outlines a macro-evaluation workflow for analyzing multi-agent systems at scale using a simulated electric vehicle order pipeline. It demonstrates how to look past individual responses and evaluate systemic behaviors such as orchestration, routing, and tool choices by combining lower-level execution checks (via Promptfoo) into population-level trace analyses to discover and... https://developers.openai.com/cookbook/examples/partners/macro_evals_for_agentic_systems/macro_evals_for_agentic_systems

NVIDIA-AI-Blueprints / video-search-and-summarization Suite of reference architectures for building GPU-accelerated vision agents and AI-powered video analytics applications. https://github.com/NVIDIA-AI-Blueprints/video-search-and-summarization

Opaque Types in Python https://blog.glyph.im/2026/05/opaque-types-in-python.html

What types of exceptions should you catch? The trickiest programming bugs are often caused by catching exceptions that you didn't mean to catch or handling exceptions in ways that obfuscate the actual error that's occurring. Which exceptions should you catch and which should you leave unhandled? https://www.pythonmorsels.com/what-types-of-exceptions-should-you-catch/

When Python manual wiring turns into copy-paste architecture A small typed dependency injection approach for apps that outgrow copy-pasted constructors but do not need a full DI framework. https://vshulcz.hashnode.dev/when-python-manual-wiring-turns-into-copy-paste-architecture

Anthropic-Cybersecurity-Skills 754 production-grade cybersecurity skills · 26 security domains · 5 framework mappings · 26+ AI platforms. https://github.com/mukul975/Anthropic-Cybersecurity-Skills

Shrink Your Python Container in One Command with SlimToolkit Use SlimToolkit to shrink a Python container by half in one command. No Dockerfile changes. Walkthrough on a chatbot with common edge cases and fixes. https://codecut.ai/shrink-python-container-slimtoolkit/

ESPectre Motion detection system based on Wi-Fi spectre analysis (CSI), with native Home Assistant integration via ESPHome. https://github.com/francescopace/espectre

Katharos A library providing useful types and functions for functional programming in Python. https://github.com/kamalfarahani/katharos

google / skills Agent Skills for Google products and technologies https://github.com/google/skills

Python Hub Weekly Digest for 2026-05-31 https://pythonhub.dev/digest/2026-05-31/

Agent Evaluation: A Detailed Guide Best practices and common patterns for effectively evaluating AI agents. https://cameronrwolfe.substack.com/p/agent-evals

claude-for-legal A suite of plugins for legal workflows. https://github.com/anthropics/claude-for-legal

Articraft An Agentic System for Scalable Articulated 3D Asset Generation. https://github.com/mattzh72/articraft

Bridging Python's Logging Module to OpenTelemetry (Complete Guide) This guide walks through using the OpenTelemetry Python SDK's LoggingHandler to bridge Python's built-in logging module with an OpenTelemetry-compliant pipeline without changing your existing log statements. It demonstrates how to configure the handler (via dictConfig), map standard log records into structured OTel fields, and automatically correlate logs with active traces to route them... https://www.dash0.com/guides/opentelemetry-logging-python

Remove-AI-Watermarks Remove visible and invisible AI watermarks from images generated by Google Gemini (Nano Banana), ChatGPT / DALL-E, Stable Diffusion, Adobe Firefly, Midjourney, and other AI models. https://github.com/wiltodelta/remove-ai-watermarks

Decepticon Autonomous Hacking Agent for Red Team. https://github.com/PurpleAILAB/Decepticon

Headroom Headroom compresses everything your AI agent reads - tool outputs, logs, RAG chunks, files, and conversation history - before it reaches the LLM. Same answers, fraction of the tokens. https://github.com/chopratejas/headroom

Let’s Fix Bloated Python Classes Once and For All The video demonstrates how a single Python class can gradually become overloaded with unrelated responsibilities like validation, data processing, and model training, making the code harder to maintain and reason about. It then walks through refactoring the code into smaller, focused components while introducing a practical framework for deciding what logic should and should not belong i... https://www.youtube.com/watch?v=F5Av5yDGSQs

LLM Evaluation and AI Observability for Agent Monitoring A guide on LLM evaluation and AI observability, explaining how to monitor, test, and deploy reliable AI agents in production with confidence and control. https://blog.jetbrains.com/pycharm/2026/05/llm-evaluation-and-ai-observability-for-agent-monitoring/