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: 1,236 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:
→ 2,020 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 2,020 repos tested so far.
ProSense is a multi-stage training framework that improves LLM truthfulness and adversarial resilience using Graph-of-Thought (GoT) reasoning.
Insight ProSense is a multi-stage training framework that improves LLM truthfulness and adversarial resilience using Graph-of-Thought (GoT) reasoning.
github.com/iamimpeccable/Prosense-Defending-Text-Generation-with-Adversarial-Feedback ↗SigNoz is an open-source observability platform built on OpenTelemetry that provides a unified interface for logs, metrics, and distributed traces.
Insight Judged statically, the project is a complete, well-documented, and released enterprise-grade observability platform.
github.com/SigNoz/signoz ↗ACP is a cloud-native orchestrator for AI agents built on Kubernetes.
Insight The project structure is complete with clear CRDs, operator code, and documentation for Kubernetes deployment.
github.com/humanlayer/agentcontrolplane ↗A long-term memory server for Model Context Protocol (MCP) agents that provides persistent, graph-like structured memory.
Insight The project has a clear structure, a functional frontend with passing tests and a complete implementation of a memory server and visual dashboard.
github.com/Dataojitori/nocturne_memory ↗Typer is a Python library for building command-line interfaces (CLIs) based on type hints.
Insight The project is a well-established library with a clear structure, comprehensive documentation, and a published manifest.
github.com/tiangolo/typer ↗Gograph is a local-only Go static analysis engine that builds a structural graph of repositories including call graphs and symbol search.
Insight Installed cleanly on the first try.
github.com/ozgurcd/gograph ↗Nowness will tell you whether that trending repo actually works — with the evidence.