pythea

LLM reliability research from Hassana Labs.

https://github.com/leochlon/pythea

stocksTUI

Real-time stock market data in your terminal.

https://github.com/andriy-git/stocksTUI

ComposioHQ / awesome-claude-skills

A curated list of awesome Claude Skills, resources, and tools for customizing Claude AI workflows

https://github.com/ComposioHQ/awesome-claude-skills

Engram

Conditional Memory via Scalable Lookup: A New Axis of Sparsity for Large Language Models.

https://github.com/deepseek-ai/Engram

memU

Memory infrastructure for LLMs and AI agents.

https://github.com/NevaMind-AI/memU

The Right Way to Use AI for Writing Maintainable Code

Arjan argues that long-term code maintainability with AI requires developers to act as high-level architects, constantly refining design patterns and decoupling responsibilities rather than accepting the first "working" output. The video demonstrates this iterative process by showing a real interaction with ChatGPT, where he systematically guides the AI to replace messy if-statements wit...

https://www.youtube.com/watch?v=8Pi6vGRlp1c

NitroGen

A Foundation Model for Generalist Gaming Agents.

https://github.com/MineDojo/NitroGen

FastAPI Tutorials

In this series, we'll be learning how to build a full-featured web application from the ground up using the FastAPI framework in Python. We'll build both a JSON API for programmatic access and HTML pages for users to browse in the browser. Throughout the series, we'll set up a database with SQLAlchemy, create Pydantic models for data validation, and implement complete CRUD operations. We...

https://www.youtube.com/playlist?list=PL-osiE80TeTsak-c-QsVeg0YYG_0TeyXI

A field guide to sandboxes for AI

Luis Cardoso breaks down the technical differences between containers, microVMs, gVisor, and WebAssembly to help developers choose the right isolation boundary for running untrusted AI agents. He emphasizes that a secure sandbox requires a clear distinction between the isolation boundary, the access policy, and the lifecycle management of the environment to prevent malicious code from co...

https://www.luiscardoso.dev/blog/sandboxes-for-ai

GrantFlow.AI

GrantFlow.ai is a platform for creating grant applications using ML and AI.

https://github.com/grantflow-ai/grantflow

alirezarezvani / claude-skills

A Collection of Skills for Claude Code and Claude AI for real-world Usage. Including Claude Code Subagents, Claude Code Commnads

https://github.com/alirezarezvani/claude-skills

FlashInfer

Kernel Library for LLM Serving.

https://github.com/flashinfer-ai/flashinfer

Under the Hood: Universal Commerce Protocol (UCP)

Google has introduced the Universal Commerce Protocol (UCP), an open-source standard designed to enable seamless "agentic commerce" across AI platforms like Gemini and Search. The protocol eliminates integration bottlenecks by providing a unified abstraction layer for discovery and transactions, allowing AI agents to handle the entire shopping journey from product search to secure payment.

https://developers.googleblog.com/en/under-the-hood-universal-commerce-protocol-ucp/

Beyond One-Size-Fits-All RAG: Why Different Knowledge Sources Need Different Retrieval Strategies

Jo Chen argues that high-performance RAG systems require specialized retrieval pipelines for different data types, such as contextual prefixes for technical manuals and whole-document summaries for blog content. The post details a multi-layered defense strategy involving hybrid search, LLM reranking, and aggressive caching to improve accuracy while managing the high costs of production AI.

https://blog.gopenai.com/beyond-one-size-fits-all-rag-why-different-knowledge-sources-need-different-retrieval-strategies-355f4fe7897e

ralph-orchestrator

An improved implementation of the Ralph Wiggum technique for autonomous AI agent orchestration.

https://github.com/mikeyobrien/ralph-orchestrator

Jetbase

Jetbase is a simple, lightweight database migration tool for Python projects.

https://github.com/jetbase-hq/jetbase

How we made Python's packaging library 3x faster

Henry Schreiner and Damian Shaw significantly improved the performance of the Python packaging library by using new profiling tools to eliminate redundant regular expressions. The update delivers speed increases up to 5x for version filtering which helps resolve dependencies much faster within the Python ecosystem.

https://iscinumpy.dev/post/packaging-faster/

Supercharging LLMs: Scalable RL with torchforge and Weaver

PyTorch has introduced torchforge and Weaver, a new open-source stack designed to simplify and scale reinforcement learning for large language models across hundreds of GPUs. The system uses Weaver to provide reliable reward signals without human annotations, while torchforge provides the native primitives to manage complex distributed coordination and fault tolerance.

https://pytorch.org/blog/supercharging-llms-scalable-rl-with-torchforge-and-weaver/

rendercv / rendercv

CV/resume generator for academics and engineers, YAML to PDF

https://github.com/rendercv/rendercv