Freelance
Freelance is a framework for enforcing structured workflows and providing persistent memory for AI coding agents.
Insight Its own test suite ran — 540 tests passed.
github.com/duct-tape-and-markdown/freelance ↗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: 1,363 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:
→ 2,776 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.
Loushang is an AI-native agent harness designed for complex software development workflows.
Loushang is an AI-native agent harness built for complex software development workflows. It provides a framework for multi-model orchestration and stateful sessions, treating work methods and execution steps as runtime objects. The lab's run proved the system can handle complex engineering tasks by successfully installing and passing a high volume of tests during a demo execution.
This project earns its spotlight by addressing the loss of context and lack of persistence in multi-step software projects. It allows for persistent coding sessions that can be resumed and audited while providing governance over custom tool sets. By enabling provider-aware routing and method-guided workflows, it solves the difficulty of managing AI agents in sophisticated development environments.
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 2,776 repos tested so far.
Freelance is a framework for enforcing structured workflows and providing persistent memory for AI coding agents.
Insight Its own test suite ran — 540 tests passed.
github.com/duct-tape-and-markdown/freelance ↗Graphlink is a local-first, graph-based AI workspace that replaces linear chat interfaces with a visual node-based canvas.
Insight Its own test suite ran — 1,173 tests passed.
github.com/dovvnloading/Graphlink ↗A headless, unopinionated data table library for Svelte that provides logic for complex data grids without dictating UI or markup.
Insight Installed cleanly on the first try; its own test suite ran — 87 tests passed.
github.com/bryanmylee/svelte-headless-table ↗Stash is a shared memory and knowledge base system designed for AI coding agents.
Insight Installed cleanly on the first try.
github.com/Fergana-Labs/stash ↗A comprehensive data grid component for the Nette Framework that provides features like filtering, sorting, pagination, and tree/table views.
Insight The project has a clear structure, comprehensive documentation, and multiple stable versions.
github.com/contributte/datagrid ↗A highly customizable data table component for React built on Material UI.
Insight Installed cleanly on the first try.
github.com/material-table-core/core ↗Nowness will tell you whether that trending repo actually works — with the evidence.