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.
All of it on local AI, on one machine, around the clock — no cloud, no human in the loop.
One thing it proves: 965 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.
→ 1,582 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.
Hivemind is a cloud-backed shared memory and skill-learning system for AI agents.
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 1,582 repos tested so far.
LLM-Adapters is a framework for Parameter-Efficient Fine-Tuning (PEFT) that integrates multiple adapter types (LoRA, AdapterH, AdapterP, Prefix Tuning, etc.) into Large L.
Insight LLM-Adapters is a framework for Parameter-Efficient Fine-Tuning (PEFT) that integrates multiple adapter types (LoRA, AdapterH, AdapterP, Prefix Tuning, etc.) into Large Language Models.
github.com/AGI-Edgerunners/LLM-Adapters ↗XMem is a multi-modal, multi-agentic long-term memory layer that provides persistent context for AI agents and LLM interfaces.
Insight XMem is a multi-modal, multi-agentic long-term memory layer that provides persistent context for AI agents and LLM interfaces.
github.com/XortexAI/XMem ↗QMedia is an open-source AI content search engine designed for content creators to search and analyze multi-modal data including text, images, and short videos.
Insight Installed cleanly on the first try.
github.com/QmiAI/Qmedia ↗OWASP Nettacker is an automated penetration testing and information-gathering framework written in Python.
Insight The demo actually ran and produced real output.
github.com/OWASP/Nettacker ↗RHA-RAG is an agentic Retrieval-Augmented Generation (RAG) system that forces LLMs to build explicit, verifiable proof chains instead of just retrieving and summarizing t.
Insight The project has a complete structure, including a Docker configuration, LangGraph orchestration, and web UI.
github.com/YufSunny/RHA-RAG ↗A TypeScript framework for building deterministic CLI tools that LLM agents can interact with using structured Zod schemas.
Insight Installed cleanly on the first try.
github.com/beogip/code-first-agents-tool ↗Nowness will tell you whether that trending repo actually works — with the evidence.