TL;DR
A state-of-PyTorch-hardware report meets a deep dive into agent memory; PEP 816 formalizes WASI support and a Bloom filter makes an API 16x faster.
🦄
Articles & Tutorials
× 12 01 Deprecations via warnings don’t work for Python libraries
02 PEP 816 – WASI Support
03 State of PyTorch Hardware Acceleration 2025
04 Build a RAG app with Django & MongoDB Backend in 30 minutes
05 Regex Golf
06 Introducing Django RAPID Architecture
07 Application Logging in Python: Recipes for Observability
08 Python Guide for Japanese Corpus Linguistics
09 Useful patterns for building HTML tools
10 Create A Pandas Dataframe AI Agent With Generative AI, Python And OpenAI
11 Making Sense of Memory in AI Agents
12 Bloom filters: the niche trick behind a 16× faster API
🐿️
Projects & Resources
× 12 01 lada: Restore videos with pixelated/mosaic regions
02 hello-agents: A comprehensive guide to building AI agents from scratch
03 TotalSegmentator: Tool for robust segmentation of >100 important anatomical structures in CT and MR images
04 -mcp-server: The power of Claude Code / GeminiCLI / CodexCLI + [Gemini / OpenAI / OpenRouter / Azure / Grok / Ollama / Custom Model / All Of The Above] working as one.
05 MemMachine: Universal memory layer for AI Agents.
06 flask-pydantic: flask extension for integration with the awesome pydantic package
07 ten-framework: Open-source framework for conversational voice AI agents
08 GLM-V: GLM-4.6V/4.5V/4.1V-Thinking: Towards Versatile Multimodal Reasoning with Scalable Reinforcement Learning
09 cutile-python: cuTile is a programming model for writing parallel kernels for NVIDIA GPUs
10 tau2-bench: τ²-Bench: Evaluating Conversational Agents in a Dual-Control Environment
11 metacode: A standard language for machine-readable code comments
12 Syd: Air-Gapped Cybersecurity Assistant