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 917 AI repos I actually ran in a sandbox don't work.
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.

1,506 repos tested by the lab so far

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

Telecraft

Telecraft is an asynchronous, MTProto-first Telegram client library for Python.

Why it's the pick Installed cleanly on the first try; its own test suite ran — 3,458 tests passed.
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
Latest verdict2026-07-19
Itas: Iterative Program Synthesis with Code…paper
Read and distilled by the lab — a paper or reference resource, not runnable code.
  • Itas: Iterative Program Synthesis with…paper
  • ResearchMind: Multi-Agentic Research…runs
  • VahanGraph: Agentic Vehicle Registration…runs
  • EvoAgentworks
  • Qlaimoza Revenue Integrity Operating…runs
  • Telecraftworks
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 1,506 repos tested so far.

ResearchMind: Multi-Agentic Research System

An autonomous research pipeline that uses a multi-agent architecture (Searcher, Reader, Writer, Critic) to automate deep-web investigation and content synthesis.

Insight The demo actually ran and produced real output.

github.com/Anvesh-Vishwakarma/Multi-Agentic-Research-System- ↗

VahanGraph: Agentic Vehicle Registration Analytics

VahanGraph is an AI-powered analytics system that uses LangGraph to convert natural language queries into executable Python code for analyzing vehicle registration datase.

Insight Installed cleanly on the first try.

github.com/yatokai-3/Agentic-Vehicle-Analytics ↗

EvoAgent

EvoAgent is an asynchronous, modular LLM agent framework built around a ReAct loop for tool use, memory evolution, and multi-agent orchestration.

Insight Installed cleanly on the first try; its own test suite ran — 692 tests passed; the demo actually ran and produced real output.

github.com/mingbo-yang/EvoAgent ↗

Qlaimoza Revenue Integrity Operating System

Qlaimoza is an autonomous revenue integrity system designed for healthcare providers.

Insight The demo actually ran and produced real output.

github.com/satvikshrivastava06/Qlaimoza ↗

Telecraft

Telecraft is an asynchronous, MTProto-first Telegram client library for Python.

Insight Installed cleanly on the first try; its own test suite ran — 3,458 tests passed.

github.com/meniwap/telecraftor ↗

PentestThinkingMCP

A Model Context Protocol (MCP) server that provides a structured reasoning engine for penetration testing and CTF solving.

Insight Installed cleanly on the first try.

github.com/ibrahimsaleem/PentestThinkingMCP ↗
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.