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 478 trending AI repos I sandbox-tested don't actually run.
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.

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

claude-tap

A local proxy and trace viewer that intercepts and inspects API traffic from various AI coding agents (e.g., Claude Code, Cursor, Gemini CLI).

Why it's the pick Installed cleanly on the first try; its own test suite ran — 865 tests passed; the demo actually ran and produced real output.
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
Idle — send a repo above and watch it here.
  • Airflow to Manage Talend ETL Jobspaper
  • Dagrsworks
  • 2389 Research Claude Code Plugin Marketplaruns
  • AI-Powered Distributed Database Engine (APpaper
  • Alive-NJruns
  • notebooklm-pyworks
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 1,042 repos tested so far.

Dagrs

Dagrs is a high-performance Rust framework for asynchronous task orchestration using Flow-Based Programming (FBP).

Insight Installed cleanly on the first try.

github.com/dagrs-dev/dagrs ↗

2389 Research Claude Code Plugin Marketplace

A collection of 28 plugins and MCP servers designed for Claude Code and other AI agents.

Insight The project is a collection of functional plugins and MCP servers with a clear structure, and the repository's own test suite passed successfully.

github.com/2389-research/claude-plugins ↗

Alive-NJ

Alive-NJ is a reimplementation of the Automated LLVM's InstCombine Verifier that provides automated reasoning for integer and floating-point peephole optimizations.

Insight The project contains a complete structure with a test suite, multiple implementation files, and a clear README describing its functionality and requirements.

github.com/rutgers-apl/alive-nj ↗

notebooklm-py

An unofficial Python API and agentic skill that provides programmatic access to Google NotebookLM's features.

Insight Its own test suite ran — 10,615 tests passed.

github.com/teng-lin/notebooklm-py ↗

Pydantic AI

Pydantic AI is a production-grade Python framework for building generative AI agents and workflows.

Insight The library imports without errors.

github.com/pydantic/pydantic-ai ↗

Hacettepe AI Client

A specialized AI assistant for university students that uses Retrieval-Augmented Generation (RAG) to provide accurate information.

Insight Installed cleanly on the first try.

github.com/UfukTanriverdi8/HacettepeAI-client ↗
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.