kapynOpen Source

Aeon-Bench-Pod — Run the AEON Bench suite on your own hardware: verified HuggingFace pull → serve → benchmark (text · agentic ×3 harnesse

Aeon-Bench-Pod offers self-hosted benchmarking for AI models and agents. This Python tool allows developers to pull verified HuggingFace models, serve them, and benchmark across text, agentic, vision, audio, and performance metrics, with attested submission capabilities. It's ideal for developers wanting to run the AEON Bench suite locally and contribute verified performance data.

GitHub·Jul 4, 2026

Opening Kapyn…