Telt
Telt is a competitive arena where AI agents compete in poker and web-grounded quizzes to win real prize pools.
Insight Installed cleanly on the first try.
github.com/Iziedking/Telt ↗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.
of the 931 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.
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.
→ 1,509 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.
Telecraft is an asynchronous, MTProto-first Telegram client library for Python.
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 1,509 repos tested so far.
Telt is a competitive arena where AI agents compete in poker and web-grounded quizzes to win real prize pools.
Insight Installed cleanly on the first try.
github.com/Iziedking/Telt ↗DProvenanceKit is a local-first SDK for recording and verifying AI reasoning paths and agent behavior.
Insight The project has a complete structure, multiple language ports (Swift, Python), and clear documentation.
github.com/Therealdk8890/DProvenanceKit ↗A diagnostic framework for Retrieval-Augmented Generation (RAG) that provides trace-based observability and failure analysis.
Insight Installed cleanly on the first try; its own test suite ran — 89 tests passed; the demo actually ran and produced real output.
github.com/GioiaZheng/rag-observatory ↗Cairn is an open-source background agent system designed to automate end-to-end software engineering tasks directly within GitHub repositories.
Insight Installed cleanly on the first try.
github.com/cairn-dev/cairn ↗OpenASE is a ticket-driven automated software engineering platform that enables AI agents to autonomously execute workflows and complete software tasks.
Insight Judged statically, the project is a complete and well-structured Go application with a comprehensive documentation suite, multi-file structure, and clear project manifests.
github.com/PacificStudio/openase ↗A framework that combines Large Language Models (LLMs) with symbolic reasoning to define and monitor complex robot activities.
Insight The project contains a complete implementation with multiple modules (process extraction, planning, and simulation), clear documentation, and multiple sub-modules.
github.com/Fra-Tsuna/llm-to-symbolic-planner ↗Nowness will tell you whether that trending repo actually works — with the evidence.