Fast, filterable PR review. Entirely client-side via GitHub’s CORS API.

In which I talk about the process involved in switching forges, and how well that went.

Course to get into Large Language Models (LLMs) with roadmaps and Colab notebooks.

mlabonne.github.io/blog/

Molly is a hardened version of Signal for Android, the fast simple yet secure messaging app by Signal Foundation.

Molly is a hardened version of Signal for Android, the fast simple yet secure messaging app by Signal Foundation.

The “you only glance once” object detection model. Contribute to czbiohub-sf/yogo development by creating an account on GitHub.

A version of the YOLO architecture (versions 1 through 3), optimized for inference speed on simple object detection problems. Designed for the remoscope project by the bioengineering team at the Chan-Zuckerberg Biohub SF.

Use mkslides to easily turn markdown files into beautiful slides using the power of Reveal.js!

MkSlides is a static site generator that’s geared towards building slideshows. Slideshow source files are written in Markdown, and configured with a single YAML configuration file. The workflow and commands are heavily inspired by MkDocs and reveal-md.

Lightning-fast, on-device TTS — running natively via ONNX. - supertone-inc/supertonic

Supertonic is a lightning-fast, on-device text-to-speech system designed for extreme performance with minimal computational overhead. Powered by ONNX Runtime, it runs entirely on your device—no cloud, no API calls, no privacy concerns.

Verbalized Sampling, a training-free prompting strategy to mitigate mode collapse in LLMs by requesting responses with probabilities. Achieves 2-3x diversity improvement while maintaining quality. Model-agnostic framework with CLI/API for creative writing, synthetic data generation, and dialogue simulation. - CHATS-lab/verbalized-sampling

Open-Source Memory Engine for LLMs, AI Agents

What is Memori Memori enables any LLM to remember conversations, learn from interactions, and maintain context across sessions with a single line: memori.enable(). Memory is stored in standard SQL databases (SQLite, PostgreSQL, MySQL) that you fully own and control.

Why Memori?

One-line integration - Works with OpenAI, Anthropic, LiteLLM, LangChain, and any LLM framework SQL-native storage - Portable, queryable, and auditable memory in databases you control 80-90% cost savings - No expensive vector databases required Zero vendor lock-in - Export your memory as SQLite and move anywhere Intelligent memory - Automatic entity extraction, relationship mapping, and context prioritization

Penpot: The open-source design tool for design and code collaboration - penpot/penpot

Penpot is the first open-source design tool for design and code collaboration.

Designers can create stunning designs, interactive prototypes, design systems at scale, while developers enjoy ready-to-use code and make their workflow easy and fast. And all of this with no handoff drama.

Available on browser or self-hosted, Penpot works with open standards like SVG, CSS, HTML and JSON, and it’s free!

Fara-7B is Microsoft’s first agentic small language model (SLM) designed specifically for computer use.

With only 7 billion parameters, Fara-7B is an ultra-compact Computer Use Agent (CUA) that achieves state-of-the-art performance within its size class and is competitive with larger, more resource-intensive agentic systems.

Gemini CLI Tips and Tricks.

This guide covers ~30 pro-tips for effectively using Gemini CLI for agentic coding

Gemini CLI is an open-source AI assistant that brings the power of Google’s Gemini model directly into your terminal. It functions as a conversational, “agentic” command-line tool - meaning it can reason about your requests, choose tools (like running shell commands or editing files), and execute multi-step plans to help with your development workflow.

In practical terms, Gemini CLI acts like a supercharged pair programmer and command-line assistant. It excels at coding tasks, debugging, content generation, and even system automation, all through natural language prompts. Before diving into pro tips, let’s quickly recap how to set up Gemini CLI and get it running.

AI-Powered Data Processing: Use LOTUS to process all of your datasets with LLMs and embeddings. Enjoy up to 1000x speedups with fast, accurate query processing, that’s as simple as writing Pandas code - lotus-data/lotus

LOTUS is an open-source query engine that makes programming as easy as writing Pandas and optimizes your programs for up to 400x speedups.

:books: Freely available programming books. Contribute to EbookFoundation/free-programming-books development by creating an account on GitHub.

Welcome to Fastreach Fastreach determines the reachable area of public transport given a start station, date and maximum travel duration (isochrone). These parameters can be configured on the panel in the top-left. The travel duration is capped at 120 minutes.

Between stations Fastreach considers walking as well as trains, trams and busses according to their timetables. The reachable area is visualized via a multi-polygon. It’s properties are described in the top-right panel.

Fastreach uses the weekly timetable data provided by Delfi e.V. from the 15 September 2025. Accordingly, timetables can only be considered complete from 15 September to 21 September. Data for walkways is taken from OpenStreetMap. Fastreach’s source code lives on GitHub.

No personal information is processed on this site. For the map tiles your browser makes requests to OpenStreetMap. Their privacy policy can be found here.

JupyterGIS - Collaborative GIS editor in Jupyter.

Features - Collaborative GIS Environment: Work together on geographic data projects in real-time.

QGIS File Support: Load, visualize, and manipulate QGIS project files (.qgs, .qgz), and other GIS data formats.

Interactive Maps: Render interactive maps and geospatial visualizations within Jupyter notebooks using the JupyterGIS Python API.

This demo runs a JupyterLab instance entirely in your browser with WebAssembly! 🤯