Every card below was executed by the lab this week — the surprising sleepers that just work, and the hyped ones that failed their own setup. From 826 repos tested so far.
✓ PRODUCTION-READY
tenacity
Tenacity is a general-purpose retrying library for Python.
Sandbox found The library installed successfully (install_exit: 0), all tests passed (pytest_exit: 0), and the demonstration script executed successfully (demo_exit: 0).
github.com/jd/tenacity ↗
✓ PRODUCTION-READY
Multi-Agent Path Planning Stack
A high-performance navigation stack for multi-robot systems that combines Conflict-Based Search (CBS) for global path planning with Optimal Reciprocal Collision Avoidance.
Sandbox found The project has a successful installation (install_exit: 0), passing tests (pytest_exit: 0), and a successful demonstration (demo_exit: 0) showing it can compute paths and run simulations.
github.com/aaholmes/multiagent-pathplanning ↗
✓ PRODUCTION-READY
Reasoning Gym
Reasoning Gym is a Python library providing procedural dataset generators and algorithmically verifiable reasoning environments for training models via Reinforcement Lear.
Sandbox found The sandbox successfully installed dependencies (install_exit: 0), passed tests (pytest_exit: 0), and the demonstration script executed successfully (demo_exit: 0).
github.com/open-thought/reasoning-gym ↗
✗ FAILED ITS OWN SETUP
Dingo: AI Data & Model Quality Evaluation Tool
Dingo is a comprehensive evaluation framework designed to assess the quality of machine learning datasets, LLM training data, and RAG systems.
Sandbox found The sandbox encountered installation and test errors (install_exit: 1, pytest_exit: 2), but the demo_exit: 0 confirms the core logic successfully executed and produced expected output. The project structure is complete w
github.com/MigoXLab/dingo ↗
✗ FAILED ITS OWN SETUP
Agent-as-a-Judge
A framework for evaluating agentic workflows by using LLMs as automated judges that provide step-by-step feedback.
Sandbox found The sandbox failed to install dependencies (install_exit: 1) and the demo failed to run due to missing modules (demo_exit: 1).
github.com/metauto-ai/agent-as-a-judge ↗