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: 1,231 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:
→ 2,015 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.
Prax is an agent runtime that enables LLMs to perform autonomous tasks using 'test-verify-fix' loops.
Prax is an agent runtime that enables large language models to perform autonomous tasks through test-verify-fix loops. It supports multi-model orchestration and cross-project memory while automating the execution of code and tests. The lab's run proved the system can successfully execute and verify tasks, achieving a high volume of passing tests and a successful exit status.
This project earns its spotlight by addressing the fact that AI agents often hallucinate or fail to verify if their code changes actually work. Prax provides a structured environment for execution and verification. It handles tasks ranging from automated bug fixing and pull request triage to scheduled data scraping and content creation.
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 2,015 repos tested so far.
A local-only Go static analysis engine that builds a structural graph of repositories to provide AI coding agents with deterministic awareness of call graphs, impact anal.
Insight The build and help commands executed successfully, and the project has a comprehensive structure with multiple query capabilities.
github.com/ozgurcd/gograph ↗Typer is a Python library for building command-line interfaces (CLIs) that leverages Python type hints for automatic validation and completion.
Insight The project is a well-established, published library with a clear structure and comprehensive documentation.
github.com/tiangolo/typer ↗ConstraintLLM is a neuro-symbolic framework that combines Large Language Models (LLMs) with symbolic solvers to automatically generate and evaluate industrial-level Const.
Insight The project provides a complete implementation including a dataset, knowledge base, and multiple retrieval methods.
github.com/william4s/ConstraintLLM ↗Synalinks is a neuro-symbolic framework for building and deploying Language Model (LM) applications like RAGs and autonomous agents.
Insight The project has a clear structure, extensive documentation, a comprehensive set of examples, and a CLI that successfully installed and ran.
github.com/SynaLinks/synalinks ↗TokenSpeed is a high-performance LLM inference engine optimized for agentic workloads.
Insight Installed cleanly on the first try.
github.com/lightseekorg/tokenspeed ↗OpenSpace is a skill management layer for AI agents designed to handle the full lifecycle of agent capabilities, including retrieval, evaluation, and evolution.
Insight The project has a comprehensive structure including a dashboard, TUI, and multi-language support.
github.com/HKUDS/OpenSpace ↗Nowness will tell you whether that trending repo actually works — with the evidence.