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: 1,012 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:
→ 1,625 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.
Sibyl is an autonomous AI research organization that automates the end-to-end machine learning research lifecycle, from literature review and hypothesis generation to GPU experiment execution and pape.
Sibyl is an autonomous AI research organization that automates the machine learning lifecycle. It handles everything from literature reviews and hypothesis generation to GPU experiment execution and paper writing. The system uses a dual-loop architecture where one loop manages specific research tasks while the other allows the system to self-evolve by learning from previous iterations.
The project earns its spotlight by addressing the manual overhead and complexity of managing multi-agent workflows and academic writing. It allows for automated research production and provides tools for research augmentation. By automating the entire pipeline, Sibyl transforms how researchers explore topics and execute complex experiments.
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 1,625 repos tested so far.
A curated repository and directory of over 300 agentic AI projects, frameworks, and tools.
Insight A curated repository and directory of over 300 agentic AI projects, frameworks, and tools.
github.com/slavakurilyak/awesome-ai-agents ↗Puxti is a command-line tool that automates the propagation of schema and semantic changes across dbt projects.
Insight Installed cleanly on the first try; the demo actually ran and produced real output.
github.com/puxti-labs/puxti ↗Compass is a context engine that builds a temporal knowledge graph of organizational metadata, including entities, relationships, and documents.
Insight Installed cleanly on the first try.
github.com/raystack/compass ↗A framework for generating narrated MP4 videos and slideshows from a web-native scene source.
Insight Installed cleanly on the first try.
github.com/Oxiom-Systems/voiceover-video-starter ↗An experimental project focused on authoring web-native tabletop RPGs (TTRPGs) using agentic tooling.
Insight The project is in an experimental state with a monorepo structure.
github.com/villetakanen/free-fall ↗A web-native Question and Answering (Q&A) CLI tool that uses Thordata's SERP API and Universal Scrape for real-time data retrieval.
Insight Installed cleanly on the first try; the demo actually ran and produced real output.
github.com/Thordata/thordata-web-qa-agent ↗Nowness will tell you whether that trending repo actually works — with the evidence.