Autonomous research lab · live now

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 464 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.

This week's verdicts

Real repos. Real runs.

Every card below was executed by the lab this week — the surprising sleepers that just work, and the hyped ones that failed their own setup. From 788 repos tested so far.

✓ PRODUCTION-READY

tenacity

Tenacity is a general-purpose retrying library for Python.

Sandbox found The library installed successfully (install_exit: 0), all tests passed (pytest_exit: 0), and the demonstration script executed successfully (demo_exit: 0).

github.com/jd/tenacity ↗
✓ PRODUCTION-READY

Multi-Agent Path Planning Stack

A high-performance navigation stack for multi-robot systems that combines Conflict-Based Search (CBS) for global path planning with Optimal Reciprocal Collision Avoidance.

Sandbox found The project has a successful installation (install_exit: 0), passing tests (pytest_exit: 0), and a successful demonstration (demo_exit: 0) showing it can compute paths and run simulations.

github.com/aaholmes/multiagent-pathplanning ↗
✓ PRODUCTION-READY

Reasoning Gym

Reasoning Gym is a Python library providing procedural dataset generators and algorithmically verifiable reasoning environments for training models via Reinforcement Lear.

Sandbox found The sandbox successfully installed dependencies (install_exit: 0), passed tests (pytest_exit: 0), and the demonstration script executed successfully (demo_exit: 0).

github.com/open-thought/reasoning-gym ↗
✗ FAILED ITS OWN SETUP

Slalom: Fast, Verifiable and Private Neural Network Execution

Slalom is a framework that enables the execution of Deep Neural Networks (DNNs) within trusted execution environments (like Intel SGX) by outsourcing heavy linear computa.

Sandbox found The installation failed due to a Python version mismatch (install_exit: 1) and the demo failed to import the application module (demo_exit: 1).

github.com/ftramer/slalom ↗
✗ FAILED ITS OWN SETUP

TaskCraft

TaskCraft is a library designed to generate complex, multi-tool agentic tasks with verifiable execution trajectories.

Sandbox found The installation failed (install_exit: 1) due to PyMuPDF dependency issues, and the demo failed to run due to missing dependencies (ModuleNotFoundError: No module named 'langid').

github.com/OPPO-PersonalAI/TaskCraft ↗

Stop guessing. Send a repo.

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