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: 1,397 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

3,012 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 · 04 Aug 2026 ✓ production-ready MCP server

trelix

Trelix is a code intelligence tool that indexes repositories using Tree-sitter AST parsing and hybrid search (BM25 + vector + call-graph).

1,858tests passed
~1★github stars
2 Augverdict earned
Why it's today's pick — exactly

Trelix is a code intelligence tool that indexes repositories using Tree-sitter AST parsing and hybrid search. It combines BM25, vector, and call-graph analysis to provide contextual retrieval and LLM synthesis for understanding and reviewing codebases. The lab's run confirmed the project's comprehensive structure and its ability to integrate with multiple frameworks.

The tool earns its spotlight by addressing the limitations of standard grep and simple vector embeddings. By incorporating structural awareness, it accurately handles complex questions about code logic. It enables natural language search, automated code review analysis, and multi-repository federated search. It also generates knowledge graphs and provides context for LLM agents.

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 verdict2026-08-03
Reason-Mediated Behavioral Models for Auditing LLM…paper
Read and distilled by the lab — a paper or reference resource, not runnable code.
  • Reason-Mediated Behavioral Models for…paper
  • Flyte 2 SDKruns
  • FF4J (Feature Flipping for Java)runs
  • LangGraph Agentic AIpaper
  • KAOS: K8s Agent Orchestration Systemruns
  • Exceptiontrap PHP Notifierruns
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 3,012 repos tested so far.

Flyte 2 SDK

Flyte 2 is a type-safe, distributed orchestration framework for ML pipelines, models, and agents.

Insight The project has a comprehensive structure, clear documentation, and a robust set of dependencies.

github.com/flyteorg/flyte-sdk ↗

KAOS: K8s Agent Orchestration System

KAOS is a Kubernetes-native framework designed to deploy and manage AI agent networks with tool access and multi-agent coordination.

Insight The project provides a comprehensive set of documentation, a CLI, a Helm chart, and a clear architectural framework.

github.com/axsaucedo/kaos ↗

FlowX DataFlow Validator

An enterprise-grade asynchronous data ingestion and validation engine built with FastAPI.

Insight The project has a complete structure with a comprehensive list of dependencies, multiple source files, and a clear project manifest.

github.com/Raghu1986/FlowX ↗

Typer

Typer is a Python library for building command-line interfaces (CLIs) that leverages Python type hints for automatic validation and completion.

Insight Installed cleanly on the first try; its own test suite ran — 966 tests passed.

github.com/tiangolo/typer ↗

Carbon Design System

Carbon is IBM's open-source design system providing a comprehensive set of React and web components, Sass styles, and design tokens.

Insight The project is a mature, well-documented, and widely-used open-source design system with a complete package structure.

github.com/carbon-design-system/carbon ↗

babel-plugin-feature-flags

A Babel transform that implements feature flags by replacing `isEnabled('feature')` calls with boolean literals during the build process.

Insight Installed cleanly on the first try.

github.com/ember-cli/babel-plugin-feature-flags ↗
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.