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. No cloud, no human in the loop. Try it → give it any GitHub repo and get an honest, execution-backed verdict in minutes.
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: 1,107 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 runs it in the sandbox and you'll watch the analysis happen live, right here — then the full verdict lands in your inbox. Free during the beta.
→ 1,809 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.
MAPLE is a multi-agent communication framework that combines autonomous agentic AI with production-grade infrastructure.
MAPLE is a multi-agent communication framework that integrates autonomous agentic AI with production-grade infrastructure. It provides tools for resource-aware messaging, type-safe error handling, and distributed state synchronization. The lab's run confirms the project maintains a comprehensive structure and high test coverage across multiple adapters.
The project earns its spotlight by bridging the gap between infrastructure-heavy frameworks and autonomy-focused systems. It addresses the need for fault-tolerant task scheduling and secure messaging while enabling complex agentic workflows. By supporting priority message queuing and integration with existing protocols, MAPLE allows for the creation of autonomous teams that can handle shared state and resource negotiation.
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 1,809 repos tested so far.
A System 2 Cognitive Middleware that replaces static RAG pipelines with a Code Augmented Generation (CAG) approach.
Insight Installed cleanly on the first try.
github.com/marcopatzelt/agentic-orchestration-layer-model ↗A remote code execution (RCE) engine that evaluates programming submissions in isolated Docker containers.
Insight Installed cleanly on the first try.
github.com/bluemincoder/Online-Judge ↗A Python-based exploit script targeting a Server-Side Template Injection (SSTI) vulnerability in CrushFTP.
Insight Installed cleanly on the first try.
github.com/gotr00t0day/CVE-2024-4040 ↗Tessera.io is a collaborative developer sandbox and IDE engine designed for human-AI pair programming.
Insight The project has a complete monorepo structure with multiple services (web, sync, execution, AI).
github.com/Kushaal-k/Tessera.io ↗A deterministic parallel orchestration system that uses a graph-based knowledge synthesis approach for multi-agent workflows.
Insight Installed cleanly on the first try; its own test suite ran — 76 tests passed.
github.com/nenadatanasovski/memory-cube ↗Axiom Cortex is an Obsidian plugin that integrates Graph RAG (Retrieval-Augmented Generation) to enable knowledge synthesis and proactive link discovery.
Insight Its own test suite ran — 125 tests passed.
github.com/juliancanaless/obsidian-axiom-cortex ↗Nowness will tell you whether that trending repo actually works — with the evidence.