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

Live AI Trading Competition: Watch DeepSeek, Gemini 3, GPT-5.1, Claude, and Qwen manage $100k stock portfolios in real-time. Who wins? Check the leaderboard.

The communications platform that puts data protection first. - RocketChat/Rocket.Chat

Generate audiobooks from EPUBs, PDFs and text with synchronized captions. - denizsafak/abogen

Abogen is a powerful text-to-speech conversion tool that makes it easy to turn ePub, PDF, text, markdown, or subtitle files into high-quality audio with matching subtitles in seconds. Use it for audiobooks, voiceovers for Instagram, YouTube, TikTok, or any project that needs natural-sounding text-to-speech, using Kokoro-82M.

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.

The giant list of questions to ask employers Do you get sytmied when you’re asked if you have any questions in an inteview? Have we got a list for you.

the first 90 days in a new job are critical.

When you accept a new job, you don’t know who you are going to work with, what you are going to be doing, and how much (or little) you’re going to like it.

Your job interview isn’t over until you’ve changed to become part of a new team.

Listening is always hard, and it only gets harder at scale.

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.

The simplest, fastest repository for training/finetuning small-sized VLMs. - huggingface/nanoVLM

A blazingly fast, open-source, single-executable, featureful Firebase alternative.

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.

Office Libre Collabora

Abstract page for arXiv paper 2510.01171: Verbalized Sampling: How to Mitigate Mode Collapse and Unlock LLM Diversity

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

Explore Biohub’s mission to cure and prevent all disease through AI-powered biology, frontier research, and state-of-the-art technology.

Learn about Biohub’s virtual cells platform, models and datasets — available for the scientific community for early access use and feedback.

The highest-quality tracked light-sheet microscopy datasets of developing embryos.

Tabula Sapiens is a benchmark, first-draft human cell atlas of over 1.1M cells from 28 organs of 24 normal human subjects.

Tabula Sapiens is a benchmark, first-draft human cell atlas of over 1.1M cells from 28 organs of 24 normal human subjects. The data portal comprises both Tabula Sapiens publications (Tabula Sapiens v1(Science, 2022) and Tabula Sapiens v2 (biorxiv, 2024)). This work is the product of the Tabula Sapiens Consortium. Special thanks to the Chan Zuckerberg Initiative for funding this project and to the CZI Science Technology team for creating Chan Zuckerberg CELL by GENE (CZ CELLxGENE), the tool that makes the visualization of this research possible.