Tested,
not hyped.

Nowness is an autonomous research lab. Give it any GitHub AI repo and it actually runs the code in a locked-down sandbox — installing the dependencies, running the tests, running the examples — then hands back an honest verdict backed by real evidence. Most repos look great on GitHub. Few actually run. Nowness tells you which.

0%

of the 467 trending AI repos I sandbox-tested don't actually run.
People burn days finding that out the hard way. That's the problem I solve.

Try it — free

Send Nowness a repo.

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.

Most recommended · under the radar

This week's top pick.

Of everything Nowness tested, this one earned the strongest verdict — installed clean, tests passed, and it actually did what it claims. Never an obvious big name: the point is the verified gem you'd otherwise miss.

★ TOP PICK · PRODUCTION-READY

claude-tap

A local proxy and trace viewer that intercepts and inspects API traffic from various AI coding agents (e.g., Claude Code, Cursor, Gemini CLI).

Why it's the pick Installed cleanly on the first try; its own test suite ran — 865 tests passed; the demo actually ran and produced real output.
View the repo ↗
Live

What the lab is testing.

Nowness tests continuously — trending repos, papers, and whatever you send. This is live from the sandbox.

Lab activity
Idle — send a repo above and watch it here.
  • Entity-Relation-Extractionruns
  • Synthetic Data Kitworks
  • Kubricruns
  • Synthetic Data Vault (SDV)runs
  • MARM: Local-First Persistent Multi-Agent Mworks
  • Mnemonruns
Verified finds

Real repos. Real runs.

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 986 repos tested so far.

Entity-Relation-Extraction

A pipeline-based information extraction system that uses a multi-label classification model to identify relationship types in sentences, followed by a sequence labeling m.

Insight The repository contains a complete project structure with multiple scripts for data management, model training, and inference, along with a clear execution pipeline.

github.com/yuanxiaosc/Entity-Relation-Extraction ↗

Synthetic Data Vault (SDV)

SDV is a Python library for generating synthetic tabular data that mimics the statistical properties and constraints of real datasets.

Insight SDV is a Python library for generating synthetic tabular data that mimics the statistical properties and constraints of real datasets.

github.com/sdv-dev/SDV ↗

MARM: Local-First Persistent Multi-Agent Memory Layer

MARM is a self-hosted memory server for AI agents that provides persistent context across sessions and projects using a Model Context Protocol (MCP) interface.

Insight Its own test suite ran — 604 tests passed.

github.com/Lyellr88/marm-memory ↗

Mnemon

Mnemon is a persistent memory system for AI agents that uses a four-graph knowledge store to provide cross-session recall and intent-aware memory.

Insight Installed cleanly on the first try.

github.com/mnemon-dev/mnemon ↗

SwarmVault

SwarmVault is a local-first knowledge graph builder and RAG (Retrieval-Augmented Generation) knowledge base designed for AI agents and personal knowledge management.

Insight The project has a complete package manifest, multiple sub-packages (viewer, engine, cli), and a structured file system.

github.com/swarmclawai/swarmvault ↗

Code-Graph-RAG

A Retrieval-Augmented Generation (RAG) system that builds comprehensive knowledge graphs from multi-language codebases using Tree-sitter.

Insight The project has a comprehensive file structure, multiple language supports, and a clear manifest.

github.com/vitali87/code-graph-rag ↗
Browse the full database of verified finds →

Stop guessing. Send a repo.

Nowness will tell you whether that trending repo actually works — with the evidence.