DiffMem

Git Based Memory Storage for Conversational AI Agent.

https://github.com/Growth-Kinetics/DiffMem

LEANN

RAG on Everything with LEANN. Enjoy 97% storage savings while running a fast, accurate, and 100% private RAG application on your personal device.

https://github.com/yichuan-w/LEANN

GENIE

Experience near-instantaneous speech synthesis on your CPU.

https://github.com/High-Logic/Genie

oLLM

oLLM is a lightweight Python library for large-context LLM inference, built on top of Huggingface Transformers and PyTorch. It enables running models like Llama-3.1-8B-Instruct on 100k context using ~$200 consumer GPU with 8GB VRAM. Example performance: ~20 min for the first token, ~17s per subsequent token.

https://github.com/Mega4alik/ollm

TIL: Using SQLModel Asynchronously with FastAPI (and Air) with PostgreSQL

This post explains how to leverage SQLModel with FastAPI and PostgreSQL to enable fully asynchronous database operations, improving scalability and efficiency for concurrent web applications. Key steps include setting up async database engines and sessions, using dependency injection in FastAPI, and aligning everything with non-blocking patterns.

https://daniel.feldroy.com/posts/til-2025-08-using-sqlmodel-asynchronously-with-fastapi-and-air-with-postgresql

Scheduling Background Tasks in Python with Celery and RabbitMQ

We'll build background tasks using Celery and RabbitMQ to create a weather notification service.

https://blog.appsignal.com/2025/08/27/scheduling-background-tasks-in-python-with-celery-and-rabbitmq.html

Elysia

Elysia is an agentic platform designed to use tools in a decision tree. A decision agent decides which tools to use dynamically based on its environment and context.

https://github.com/weaviate/elysia

Build an AI Coding Agent in Python

This tutorial teaches how to build a functional agentic AI coding assistant in Python using the free Gemini Flash API, covering agentic loops, tool-calling, file manipulation, and autonomous debugging. By constructing an agent that can read, modify, and execute code, viewers gain practical skills and deep insight into how modern coding agents operate beneath the surface.

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

playwright-use

playwright-use turns natural-language UI test goals into executable Playwright steps using AI, then produces human-friendly and machine-readable reports with screenshots, video, and traces.

https://pypi.org/project/playwright-use/

Python: capture stdout and stderr in unittest

The article explains how to capture stdout and stderr during Python unittest runs using contextlib.redirectstdout and redirectstderr, enabling tests to programmatically access console output. It also provides examples and custom context managers to simplify capturing both streams simultaneously, improving test logging and debugging capabilities.

https://adamj.eu/tech/2025/08/29/python-unittest-capture-stdout-stderr/

When You No Longer Need That Object • Dealing With Garbage in Python

Let's explore reference counting and cyclic garbage collection in Python.

https://www.thepythoncodingstack.com/p/python-garbage-collection-reference-counting-and-cyclic

Speeding up PyTorch inference by 87% on Apple devices with AI-generated Metal kernels

The post describes how AI models can automatically generate optimized Metal GPU kernels that speed up PyTorch inference on Apple devices by an average of 87% across 215 modules, with some kernels running hundreds of times faster than baseline. Using an agentic swarm approach and adding context like CUDA references and profiling data, the system outperforms standalone models, making kerne...

https://gimletlabs.ai/blog/ai-generated-metal-kernels

PageIndex

PageIndex is a reasoning-based RAG system that simulates how human experts navigate and extract knowledge from long documents through tree search, enabling LLMs to think and reason their way to the most relevant document sections.

https://github.com/VectifyAI/PageIndex