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.
02 · Prove
Runs it for real
Clones, installs, and executes each one in a locked-down sandbox — truth, not README claims.
03 · Translate
Research → use‑cases
Turns what actually works into real, usable use-cases.
04 · Invent
Builds new tech
Combines what it's learned into its own working prototypes — and proves they run.
0%
One thing it proves: 1,371 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.
Try it
Send Nowness a repo.
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:
✓ Does it really install & run✓ An honest verdict tier✓ The real evidence — tests passed, demo output✓ A screenshot of it running
→ 2,839 repos tested by the lab so far
nowness · sandbox
The daily pick · under the radar
Today's verified pick.
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.
run‑verified · sandbox
★ DAILY PICK · 03 Aug 2026✓ production-readyAgent
MemKraft
MemKraft is a zero-dependency compound knowledge system that allows AI agents to maintain long-term memory in plain Markdown files.
2,231tests passed
~200★github stars
2 Augverdict earned
Why it's today's pick — exactly
MemKraft is a zero-dependency compound knowledge system designed to provide AI agents with long-term memory. It allows agents to store and retrieve information in plain Markdown files by auto-extracting and classifying data. The system supports searching and time-traveling through memory states, utilizing bitemporal validity and decay mechanisms. Lab tests confirmed the project successfully installs and runs its demo, establishing a functional architecture for persistent, structured memory.
This project earns its spotlight by addressing the limitations of fragmented information and context window constraints in AI systems. By offering a way to maintain shared knowledge bases and auditable logs, MemKraft enables agents to track complex entity relationships and project tasks. It provides a robust solution for creating persistent memory that remains queryable across different models and multi-agent systems.
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 2,839 repos tested so far.
Pascal Editor
A 3D architectural building editor built with React Three Fiber and WebGPU.
Insight The project is a well-structured, comprehensive monorepo with clear package separation, documentation, and published npm packages.