Tested,
not hyped.

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.

What the lab does — on its own, non-stop
01 · Discover

Hunts the frontier

Finds the newest AI research and tools the moment they appear.

02 · Prove

Runs it for real

Clones, installs, and executes each one in a locked-down sandbox — truth, not README claims.

03 · Translate

Research → use‑cases

Turns what actually works into real, usable use-cases.

04 · Invent

Builds new tech

Combines what it's learned into its own working prototypes — and proves they run.

0%

One thing it proves: 1,246 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.

Try it

Send Nowness a repo.

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:

Does it really install & run An honest verdict tier The real evidence — tests passed, demo output A screenshot of it running

2,037 repos tested by the lab so far

The daily pick · under the radar

Today's verified pick.

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.

run‑verified · sandbox
★ DAILY PICK · 29 Jul 2026 ✓ production-ready Agent

Lavern

Lavern is a multi-agent legal system featuring 67 specialized AI agents that perform document review through a debate-based protocol.

1,686tests passed
~280★github stars
27 Julverdict earned
Why it's today's pick — exactly

Lavern is a multi-agent legal system that utilizes specialized AI agents to perform document review through a debate-based protocol. It employs a three-layer verification process involving an evaluator gate, adversarial debate, and a multi-pass pipeline to ensure accuracy. The system includes mandatory human gates for critical decisions and addresses the reliability issues and hallucinations common in legal AI.

The project earns its spotlight because it provides a complete architectural implementation for automated legal research and risk assessment. By utilizing a multi-agent debate and multi-pass verification, it ensures evidence-backed citations and isolated audit trails for multi-client processing. The lab's successful execution of the codebase confirms the system's ability to handle complex legal document analysis with rigorous verification.

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 verdict2026-07-28
SocratiCodeworks
Its own test suite ran — 1,011 tests passed.
  • Contextualized Path Weighting (Nowness…runs
  • SocratiCodeworks
  • Refinersruns
  • Silicon Rider Benchruns
  • IP-Adapterruns
  • Certified Runtime Safety for Tool-Using…paper
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 2,037 repos tested so far.

SocratiCode

SocratiCode is an enterprise-grade codebase intelligence engine that provides AI assistants with deep semantic understanding of large codebases.

Insight Its own test suite ran — 1,011 tests passed.

github.com/giancarloerra/SocratiCode ↗

Refiners

Refiners is a microframework built on PyTorch designed to simplify the training and deployment of adapters (like LoRA, ControlNet, IP-Adapter) on foundation models.

Insight The project is a mature, released library with a clear structure, comprehensive documentation, and multiple production-level integrations.

github.com/finegrain-ai/refiners ↗

Silicon Rider Bench

A benchmarking framework that evaluates the tool-calling and decision-making capabilities of AI agents by simulating a food delivery rider's workflow.

Insight Installed cleanly on the first try; its own test suite ran — 441 tests passed.

github.com/KCORES/silicon-rider-bench ↗

IP-Adapter

IP-Adapter is a lightweight adapter that enables text-to-image diffusion models to generate images based on image prompts.

Insight Installed cleanly on the first try.

github.com/tencent-ailab/IP-Adapter ↗

ichibi-lake

A Node.js-based data lake gateway that provides a unified interface for DuckDB, supporting REST/GraphQL APIs, blob storage, and Kafka integration.

Insight A Node.js-based data lake gateway that provides a unified interface for DuckDB, supporting REST/GraphQL APIs, blob storage, and Kafka integration.

github.com/stephen-kruger/ichibi-lake ↗

Migration Pathways AI Agent

An AI-powered agent that provides personalized international migration and visa recommendations using Google's Gemini LLM.

Insight Installed cleanly on the first try.

github.com/brainox/immigration-pathways-agent ↗
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.