Starred repositories
Rubik cube game with instructor to learn how to solve, made with Qwen, Three.js, FastAPI, Svelte
Cuber is a Rubik’s Cube simulator. (ORIGINAL DEMO)
Crosslingual Reasoning through Test-Time Scaling
SkillsBench evaluates how well skills work and how effective agents are at using them.
Ray + Anyscale + Robotics + VLA finetuning + SimEval + W&B
A comprehensive evaluation framework for the SEA region
Evaluation code for Kaleidoscope: In-language Exams for Massively Multilingual Vision Evaluation
AssetOpsBench - Industry 4.0: A unified benchmark and framework for building, orchestrating, and evaluating domain-specific AI agents for Industry 4.0 asset operations and maintenance, with 460+ sc…
A collection of tools for your LLMs that run on Modal
Standalone Gemma 4 PyTorch Model using Claude Code
Vivaria is METR's tool for running evaluations and conducting agent elicitation research.
A light-weight and powerful meta-prompting, context engineering and spec-driven development system for Claude Code by TÂCHES.
The first open-source agentic AI physicist, by Physical Superintelligence PBC (PSI).
AI agents running research on single-GPU nanochat training automatically
Pasal.id - The first open, AI-native Indonesian legal platform. MCP server + REST API + web app giving AI grounded access Indonesian laws.
MedAgentBench: A Realistic Virtual EHR Environment to Benchmark Medical LLM Agents
Part of Tiny Aya Expedition - Tiny Aya Vision
The simplest, fastest repository for training/finetuning small-sized VLMs.
PyTorch Re-Implementation of "The Sparsely-Gated Mixture-of-Experts Layer" by Noam Shazeer et al. https://arxiv.org/abs/1701.06538
AI agents running research on single-GPU nanochat training automatically
Maya: An Instruction Finetuned Multilingual Multimodal Model using Aya