jacobphillips99/ares

ARES - Automatic Robot Evaluation System. A simple, scalable solution for robotics research

40
/ 100
Emerging

Ingests raw robot data into structured `Rollout` objects using Vision Language Models, then annotates episodes with pseudo-labels and curates datasets through FAISS vector search and MongoDB storage. Supports multimodal inputs (video, pointclouds, actions, states) and runs inference via litellm across multiple model providers (OpenAI, Anthropic, Gemini) or local compute through Modal, eliminating the need for dedicated GPU infrastructure.

No commits in the last 6 months.

Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 8 / 25
Maturity 16 / 25
Community 14 / 25

How are scores calculated?

Stars

67

Forks

9

Language

Python

License

Apache-2.0

Last pushed

May 28, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/jacobphillips99/ares"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.