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: 1,404 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:
→ 3,338 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.
Rapid is a property-based testing library for Go that verifies high-level properties across a wide range of automatically generated test cases.
Rapid is a property-based testing library for Go that verifies high-level properties across a wide range of automatically generated test cases. It features an imperative API with type-safe data generation and automatically minimizes failing test cases to simplify debugging. The library allows developers to verify that data structures maintain invariants and that complex types remain consistent through encoding and decoding roundtrips.
This tool earns its spotlight by addressing the limitations of manual test definition. Instead of writing individual cases, developers can use rapid to generate diverse inputs and state machine transitions. By automatically shrinking failing cases to their smallest reproducible form, it streamlines the identification of bugs in complex systems and ensures business logic consistency across all possible inputs.
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 3,338 repos tested so far.
A framework for program synthesis that represents programs as graphs, separating perception (converting raw data into objects) from symbolic reasoning.
Insight The project contains a complete structure and library of operators.
github.com/ethanbond64/abstract-port-graphs ↗modAL is a modular active learning framework for Python that builds on top of scikit-learn.
Insight Installed cleanly on the first try.
github.com/modAL-python/modAL ↗A multi-agent travel planning system that uses LangGraph to coordinate specialized AI agents for tasks like flight research, hotel suggestions, and itinerary building.
Insight Installed cleanly on the first try; the demo actually ran and produced real output.
github.com/PratikhyaManas/Multi-Agent-Travel-Planner-with-LangGraph ↗A multi-agent LLM framework that simulates a professional trading firm by deploying specialized agents (Fundamental, Sentiment, News, and Technical Analysts) to evaluate .
Insight Installed cleanly on the first try; its own test suite ran — 576 tests passed.
github.com/TauricResearch/TradingAgents ↗A set of high-performance utilities for handling large JSON datasets and streaming JSONL/NDJSON data.
Insight Installed cleanly on the first try.
github.com/discoveryjs/json-ext ↗A graph-based AI system that uses LangGraph to create stateful workflows for multi-step reasoning.
Insight Installed cleanly on the first try.
github.com/MK19-Tech/ai-agentic-graph-reasoning ↗Nowness will tell you whether that trending repo actually works — with the evidence.