Adrian

Open-source runtime AI agent security tool - monitors and controls AI agents, catching malicious tool use, prompt injection, and policy drift in real time, before the agent acts.

https://github.com/secureagentics/Adrian

dottxt-ai / outlines

Structured Outputs

https://github.com/dottxt-ai/outlines

FastAPI and GraphQL overview - with Strawberry!

In this video, we'll look at GraphQL in a FastAPI app, using the Strawberry package to define types, queries and mutations, and integrating with FastAPI via the GraphQLRouter object.

https://www.youtube.com/watch?v=uSGR6FviCiY

mrexodia / ida-pro-mcp

AI-powered reverse engineering assistant that bridges IDA Pro with language models through MCP.

https://github.com/mrexodia/ida-pro-mcp

QueryTuner

AI-Powered SQL Query Diagnostics.

https://github.com/AutoShiftOps/querytuner

GeoEq

Geotechnical engineering, solved in Python. 170+ validated functions for soil mechanics, SPT, CPT, bearing capacity, settlement, liquefaction & slope stability. Apache 2.0.

https://github.com/geoeq/geoeq

esp32-ai

Running a 28.9M parameter LLM on a microcontroller.

https://github.com/slvDev/esp32-ai

Setting Django's DEBUG safely

Deploying Django with DEBUG=True exposes your app to attackers. Learn why it's risky and how to fail closed so DEBUG=False stays the safe default.

https://lincolnloop.com/blog/setting-djangos-debug-safely/

ADR

ADR secures enterprise AI agents through observability, security benchmarking, and threat detection. Deployed at Uber.

https://github.com/uber/ADR

Projects I Wouldn't Use Python For in 2026

A longtime Python developer reflects on decades of using Python for almost everything, then explains why it is no longer always his first choice and what he often uses instead. It also covers where Python still shines and why it remains an important part of his toolkit.

https://menno.io/presentations/not-python-2026/index.html#/

LoopX

Lightweight loop engineering state kernel for long-running AI agent teams. Agent-loop agnostic across Codex, Claude Code, and other coding agents, with durable goals, quota-aware auto-wake, executable todos, evidence logs, and verifiable handoffs.

https://github.com/huangruiteng/loopx

Voice-Pro

An AI-powered web application for speech recognition, translation, and dubbing.

https://github.com/abus-aikorea/voice-pro

smevals

A framework for running evals against small (and large) models

https://github.com/prime-radiant-inc/smevals

code_puppy

The sassy AI code agent that makes IDEs look outdated.

https://github.com/mpfaffenberger/code_puppy

Why dict[str, Any] Slowly Destroys Your Code

A Python booking system is refactored from loose dictionaries into a stronger domain model using dataclasses, enums, and value objects. The video shows where stronger types improve maintainability and where keeping a simple string is still the better choice.

https://www.youtube.com/watch?v=lM7zWJRrRtg