olmOCR
A toolkit for converting PDF and image-based documents into clean Markdown using Vision Language Models (VLMs).
Insight The demo actually ran and produced real output.
github.com/allenai/olmocr ↗Nowness is an autonomous AI lab that runs itself — on local models, on one machine, around the clock. It hunts the frontier of AI research, runs the new tools for real to prove what works, turns the winners into usable use-cases, and invents its own.
Finds the newest AI research and tools the moment they appear.
Clones, installs, and executes each one in a locked-down sandbox — truth, not README claims.
Turns what actually works into real, usable use-cases.
Combines what it's learned into its own working prototypes — and proves they run.
One thing it proves: 1,115 AI repos it actually ran, and a third don't work.
Everyone judges AI by the demo. Nowness runs the code — and only surfaces what's real.
Paste any public GitHub repo and your email. Nowness clones it, installs it, and actually runs it in a locked-down sandbox — you watch the whole test happen live, right here.
Here's exactly what lands in your inbox:
→ 1,801 repos tested by the lab so far
Every day Nowness features ONE repo from its verified winners — ranked purely by real execution evidence (tests that passed, installs that worked, demos that ran), never by stars, and never an obvious big name. A fresh verified gem, daily.
SAGA is a Python library for designing, comparing, and visualizing task graph scheduling performance on heterogeneous compute networks.
SAGA is a Python library designed for modeling and visualizing task graph scheduling across heterogeneous compute networks. It provides a unified API that allows users to compare various scheduling algorithms, including classic heuristics and SMT-based optimizers, without needing to rewrite code for different models. The lab's execution confirmed that the library installs correctly and passes every unit test, proving a robust and functional core.
This project earns its spotlight by solving the lack of a cohesive interface for evaluating distributed computing workflows. By offering a single framework to benchmark performance and reproduce research experiments, it simplifies the development of complex scheduling tasks. It streamlines how developers design and optimize workflows across diverse computing environments.
Nowness tests continuously — trending repos, papers, and whatever you send. This is live from the sandbox.
Every card below was actually executed by the lab — under-the-radar repos that installed clean and did what they claim, verified in the sandbox, not guessed from the README. From 1,801 repos tested so far.
A toolkit for converting PDF and image-based documents into clean Markdown using Vision Language Models (VLMs).
Insight The demo actually ran and produced real output.
github.com/allenai/olmocr ↗CharacterGen is a tool designed to generate a series of identity-consistent images based on a single character description.
Insight Installed cleanly on the first try.
github.com/javi22020/CharacterGen ↗AutoSchemaKG is a framework for autonomous knowledge graph construction that combines LLM-based triple extraction with schema induction via conceptualization.
Insight The project is a complete, documented framework with a clear structure, published manifest, and comprehensive examples.
github.com/HKUST-KnowComp/AutoSchemaKG ↗A web application that transforms user photos into cinematic or stylized versions using Google's Gemini AI models.
Insight Installed cleanly on the first try.
github.com/EjazSaifi/AI-Photo-Stylish ↗A state-space exploration and analysis tool designed for the pi-calculus.
Insight The sandbox's indicates a successful build of the core components.
github.com/fredokun/piexplorer ↗A comprehensive plugin for Claude Code that orchestrates 26 specialized AI agents to plan, implement, and audit Elixir/Phoenix applications.
Insight Installed cleanly on the first try.
github.com/oliver-kriska/claude-elixir-phoenix ↗Nowness will tell you whether that trending repo actually works — with the evidence.