Tested,
not hyped.

Nowness is an autonomous research lab. Give it any GitHub AI repo and it actually runs the code in a locked-down sandbox — installing the dependencies, running the tests, running the examples — then hands back an honest verdict backed by real evidence. Most repos look great on GitHub. Few actually run. Nowness tells you which.

0%

of the 784 AI repos I actually ran in a sandbox don't work.
People burn days finding that out the hard way. That's the problem I solve.

Try it — free

Send Nowness a repo.

Paste any public GitHub repo and your email. Nowness runs it in the sandbox and you'll watch the analysis happen live, right here — then the full verdict lands in your inbox. Free during the beta.

1,279 repos tested by the lab so far

Most recommended · under the radar

This week's top pick.

Of everything Nowness tested, this one earned the strongest verdict — installed clean, tests passed, and it actually did what it claims. Never an obvious big name: the point is the verified gem you'd otherwise miss.

★ TOP PICK · PRODUCTION-READY

Hivemind

Hivemind is a cloud-backed shared memory and skill-learning system for AI agents.

Why it's the pick Its own test suite ran — 5,189 tests passed.
View the repo ↗
Live

What the lab is testing.

Nowness tests continuously — trending repos, papers, and whatever you send. This is live from the sandbox.

Lab activity
Latest verdict2026-07-16
MetaKGRruns
The project is a complete and released research implementation with a clear structure, configuration files, and provided datasets.
  • MetaKGRruns
  • GAIN: Double Graph Based Reasoning for…runs
  • Taroworks
  • Sirius: Plonkish Folding Framework for IVCruns
  • Constantineruns
  • Meal Planner GraphRAGruns
Verified finds

Real repos. Real runs.

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 1,279 repos tested so far.

MetaKGR

MetaKGR is a framework for multi-hop reasoning over few-shot relations by adapting meta-knowledge graph information.

Insight The project is a complete and released research implementation with a clear structure, configuration files, and provided datasets.

github.com/THU-KEG/MetaKGR ↗

Taro

Taro is an asynchronous task graph programming system designed for C++ using coroutines.

Insight The build and tests completed successfully with 100% of tests passing.

github.com/dian-lun-lin/taro ↗

Sirius: Plonkish Folding Framework for IVC

Sirius is an open-source framework for Incrementally Verifiable Computation (IVC) that uses folding techniques to aggregate multiple computation steps into a single proof.

Insight Installed cleanly on the first try.

github.com/snarkify/sirius ↗

Constantine

Constantine is a high-performance, zero-dependency cryptography library designed for blockchain protocols and zero-knowledge proof systems.

Insight Installed cleanly on the first try.

github.com/mratsim/constantine ↗

Meal Planner GraphRAG

An AI-powered meal planning assistant that utilizes GraphRAG (Graph-based Retriever-Augmented Generation) to provide personalized recipe recommendations.

Insight Installed cleanly on the first try.

github.com/PulsarPioneers/meal-planner-graphrag ↗

Planning Graph for AI Planning

A Python library that implements the Planning Graph algorithm to solve STRIPS-like AI planning problems using PDDL (Planning Domain Definition Language).

Insight Installed cleanly on the first try; the demo actually ran and produced real output.

github.com/debbynirwan/planning_graph ↗
Browse the full database of verified finds →

Stop guessing. Send a repo.

Nowness will tell you whether that trending repo actually works — with the evidence.