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: 1,053 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:
→ 1,686 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.
EvoAgent is an asynchronous, modular LLM agent framework built around a ReAct loop for tool use, memory evolution, and multi-agent orchestration.
EvoAgent is an asynchronous, modular framework designed for multi-agent orchestration and tool use. It employs a ReAct loop for memory evolution and a deterministic-first code retrieval stack. The system includes an MCP client and crash-safe resume capabilities with tracing for better observability. Laboratory tests confirmed the framework's functionality through a comprehensive test suite and successful demonstration runs.
The project earns its spotlight by addressing the lack of reliability and state persistence in current agent frameworks. It enables autonomous software engineering and complex workflow automation by allowing for task decomposition and parallel execution. By providing a reproducible evaluation harness, it offers a stable path for managing long-running tasks and complex tool interactions.
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 1,686 repos tested so far.
OpenAgent is an open-source personal AI assistant that integrates LLMs, RAG (Retrieval-Augmented Generation), and autonomous agent loops into a single self-hostable platf.
Insight Judged statically, the project is a complete, well-structured repository with multi-platform binaries, Docker support, and a clear implementation of complex features.
github.com/the-open-agent/openagent ↗A framework that enhances LLM agents with the Model Context Protocol (MCP) to enable contextual reasoning and structured task execution.
Insight A framework that enhances LLM agents with the Model Context Protocol (MCP) to enable contextual reasoning and structured task execution.
github.com/TheWorldAvatar/mcp-tool-layer ↗Hyperion is a framework for identifying inconsistencies between Decentralized Application (DApp) descriptions and their underlying smart contract code.
Insight Hyperion is a framework for identifying inconsistencies between Decentralized Application (DApp) descriptions and their underlying smart contract code.
github.com/shuo-young/Hyperion ↗Memanto is an active memory agent that provides persistent context for AI agents by offering 'remember', 'recall', and 'answer' operations.
Insight The demo actually ran and produced real output.
github.com/moorcheh-ai/memanto ↗A graph-based deep learning library built on PyTorch for creating and training Graph Neural Networks (GNNs).
Insight The project is a mature, production-stable library (version 2.9.0) with a comprehensive file structure and clear documentation.
github.com/pyg-team/pytorch_geometric ↗FlashInfer is a high-performance kernel library designed for Large Language Model (LLM) inference.
Insight The project is a mature, well-documented library with a clear structure, multiple release versions, and comprehensive documentation.
github.com/flashinfer-ai/flashinfer ↗Nowness will tell you whether that trending repo actually works — with the evidence.