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: 1,065 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:
→ 1,701 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 1,701 repos tested so far.
A comprehensive AI agent harness designed for complex codebases, featuring multi-model orchestration and parallel background agents.
Insight A comprehensive AI agent harness designed for complex codebases, featuring multi-model orchestration and parallel background agents.
github.com/code-yeongyu/oh-my-openagent ↗SWE-bench is a benchmark designed to evaluate the ability of Large Language Models (LLMs) to resolve real-world software engineering issues.
Insight The demo actually ran and produced real output.
github.com/SWE-bench/SWE-bench ↗Lada is a video processing tool designed to restore pixelated or mosaic regions in adult videos.
Insight Lada is a video processing tool designed to restore pixelated or mosaic regions in adult videos.
github.com/ladaapp/lada ↗Crawl4AI is an open-source web crawler and scraper designed to generate LLM-friendly Markdown content for RAG and AI agents.
Insight Installed cleanly on the first try.
github.com/unclecode/crawl4ai ↗Metatheory.jl is a Julia library for term rewriting, metaprogramming, and algebraic equational reasoning.
Insight The project has a stable release (v2.0), comprehensive documentation, and a clear structure.
github.com/JuliaSymbolics/Metatheory.jl ↗Typer is a Python library designed for building Command Line Interfaces (CLIs) by leveraging Python type hints.
Insight The demo actually ran and produced real output.
github.com/fastapi/typer ↗Nowness will tell you whether that trending repo actually works — with the evidence.