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: 1,162 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:
→ 1,867 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.
Hyper-Extract is an LLM-powered framework that transforms unstructured text into structured Knowledge Abstracts, including Knowledge Graphs, Hypergraphs, and Spatio-Temporal Graphs.
Hyper-Extract is an LLM-powered framework that converts unstructured text into structured Knowledge Abstracts. It generates Knowledge Graphs, Hypergraphs, and Spatio-Temporal Graphs by utilizing multiple extraction engines. The system provides a command-line interface for multi-format data extraction and incremental knowledge evolution. Lab tests confirmed the project's comprehensive structure and successful execution, proving it can effectively transform messy documents into queryable graph representations.
This project earns its spotlight by streamlining the transition from raw data to organized knowledge. It allows users to build private knowledge bases and convert academic papers into interactive graphs. By enabling the export of structured knowledge to platforms like Obsidian, it solves the difficulty of organizing complex information. It offers a clear path for turning messy documents into structured, interconnected data.
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 1,867 repos tested so far.
Langflow is an open-source platform for building and deploying AI agents and workflows using a visual authoring interface.
Insight The project is a mature, released open-source tool with comprehensive documentation, multiple deployment options (Docker, Desktop, Python), and a clear file structure.
github.com/langflow-ai/langflow ↗A comprehensive AI agent toolkit featuring a unified multi-provider LLM API, a core agent runtime with state management and tool calling, and an interactive coding agent .
Insight The project has a comprehensive monorepo structure, clear documentation, and multiple packages.
github.com/earendil-works/pi ↗A web-based user interface for the pi coding agent that provides a browser workspace for managing AI-driven development tasks.
Insight Installed cleanly on the first try.
github.com/agegr/pi-web ↗OmniRoute is a unified AI gateway and router that provides a single endpoint for over 250 AI providers, including support for 90+ free tiers.
Insight The project is a mature, published package with a comprehensive file structure, Docker support, and extensive documentation.
github.com/diegosouzapw/OmniRoute ↗A Model Context Protocol (MCP) server that enables AI agents to retrieve precise code symbols (functions, classes, methods) using tree-sitter AST parsing.
Insight The library successfully imported and the project structure shows a complete, production-stable package with extensive documentation and multiple deployment paths.
github.com/jgravelle/jcodemunch-mcp ↗A general-purpose retrying library for Python that allows developers to retry failed operations.
Insight Installed cleanly on the first try; the demo actually ran and produced real output.
github.com/jd/tenacity ↗Nowness will tell you whether that trending repo actually works — with the evidence.