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.
Finds the newest AI research and tools the moment they appear.
Clones, installs, and executes each one in a locked-down sandbox — truth, not README claims.
Turns what actually works into real, usable use-cases.
Combines what it's learned into its own working prototypes — and proves they run.
One thing it proves: 1,060 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.
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:
→ 1,694 repos tested by the lab so far
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.
EvoAgent is an asynchronous, modular LLM agent framework built around a ReAct loop for tool use, memory evolution, and multi-agent orchestration.
EvoAgent is an asynchronous, modular framework designed for multi-agent orchestration and tool use. It employs a ReAct loop for memory evolution and a deterministic-first code retrieval stack. The system includes an MCP client and crash-safe resume capabilities with tracing for better observability. Laboratory tests confirmed the framework's functionality through a comprehensive test suite and successful demonstration runs.
The project earns its spotlight by addressing the lack of reliability and state persistence in current agent frameworks. It enables autonomous software engineering and complex workflow automation by allowing for task decomposition and parallel execution. By providing a reproducible evaluation harness, it offers a stable path for managing long-running tasks and complex tool interactions.
Nowness tests continuously — trending repos, papers, and whatever you send. This is live from the sandbox.
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 1,694 repos tested so far.
A multi-agent framework that mimics the structure of real-world trading firms by using specialized LLM agents (Fundamental, Sentiment, News, and Technical Analysts) to ev.
Insight Its own test suite ran — 576 tests passed.
github.com/TauricResearch/TradingAgents ↗Tile Language is a domain-specific language (DSL) designed for high-performance GPU, CPU, and accelerator kernel development.
Insight The project is a mature, released library with a clear structure, extensive documentation, and multiple backend supports.
github.com/tile-ai/tilelang ↗Typer is a Python library for building command-line interfaces (CLIs) that leverages Python type hints for automatic validation and completion.
Insight The demo actually ran and produced real output.
github.com/tiangolo/typer ↗CodeGraph is a static code analyzer that generates interactive HTML visualizations of Python project structures.
Insight Installed cleanly on the first try; its own test suite ran — 34 tests passed.
github.com/xnuinside/codegraph ↗VulnClaw is an AI-powered penetration testing CLI tool that automates the full security lifecycle: information gathering, vulnerability discovery, exploitation, and repor.
Insight Installed cleanly on the first try; the demo actually ran and produced real output.
github.com/Unclecheng-li/VulnClaw ↗Pyan is a static analysis tool for Python that generates call dependency graphs between functions and methods.
Insight The project has a complete structure with tests and a clear manifest, and the sandbox successfully installed dependencies and ran tests.
github.com/davidfraser/pyan ↗Nowness will tell you whether that trending repo actually works — with the evidence.