MoveBench is a rubric-based benchmark for evaluating large language models in sports and health coaching, combining multiple-choice questions with open-ended answers grounded in real-world scenarios. The paper evaluated 15 LLMs on 809 questions and 5,012 rubric-level criteria, with the authors reporting substantial variation in safety awareness, program design, and personalization. It was submitted to arXiv on October 19, 2026 and revised on October 26.
What problem it solves
Organizations need a distributed storage layer that can serve objects, files, tables, and vectors while keeping administration and horizontal expansion straightforward. SeaweedFS addresses this by providing these capabilities on shared storage and allowing capacity to grow by adding volume servers.
Key features
Unified distributed storage — A single cluster exposes S3 object…
What problem it solves
Kubernetes environments require security checks across development, deployment, and runtime, including configuration, vulnerability, compliance, and policy enforcement concerns. Kubescape addresses this by combining on-demand scanning, continuous in-cluster monitoring, remediation, and runtime analysis in one platform.
Key features
Lifecycle Security Scanning — Scan running …
What problem it solves
Modern websites may serve different content to browsers, crawlers, and other client environments, making it difficult to inspect access controls, headers, and delivery behavior. Developers need a way to request and modify proxied responses for legitimate testing, research, and quality assurance.
Key features
Response and request modification — Rules can modify response heade…
What problem it solves
Building, deploying, and managing AI agents requires integrating agent behavior, runtime configuration, tools, models, sessions, and observability. The project addresses this with a declarative Kubernetes-based framework that supports multiple runtimes, model providers, and MCP tools.
Key features
Declarative Agent Management — Agents are Kubernetes custom resources that com…
What problem it solves
AI coding agents often live in separate terminal sessions, lose context when those sessions end, and require repeated supervision. Teams need a shared workspace that connects assigned work, execution, decisions, and results while preserving human review before changes ship.
Key features
Agents as teammates — Create named AI agents with a provider and runtime, then assign the…
What problem it solves
Teams need to bring documents together so they can be searched, reasoned over and kept up to date. They also need a way to move from source-grounded retrieval to multi-step tasks while maintaining organized, current knowledge.
Key features
Three knowledge workflows — RAG supports lookup, an agent handles multi-step tasks, and a wiki organizes knowledge. All three operate on …