#Python

MMMU-Benchmark

MMMU

★ 597

This repo contains evaluation code for the paper "MMMU: A Massive Multi-discipline Multimodal Understanding and Reasoning Benchmark for Expert AGI"

AMA-CMFAI

LAMBDA

★ 597

This is the offical repository of paper "LAMBDA: A large Model Based Data Agent". https://www.polyu.edu.hk/ama/cmfai/lambda.html

LiteReality

LiteReality-Agent

★ 597

LiteReality-Agent: Turn the real world into simulation-ready environments.

FlashML-org

flashlib

★ 596

Fast and memory-efficient classical machine learning operators

virajmavani

semi-auto-image-annotation-tool

★ 596

Anno-Mage: A Semi Automatic Image Annotation Tool which helps you in annotating images by suggesting you annotations using user-defined labels

kevinzakka

mjbatch

★ 596

A Python library for running thousands of MuJoCo simulations in parallel on CPU

LayrKits

Sprite-Pipeline

★ 595

2D Sprite Sheet Creation Pipeline

xiao24bei

xiaobei-skill

★ 594

Xiaobei's open-source collection of Codex Skills built during grad school: Image to VBA, Academic Paper to PPT, and other AI + research workflows.

Siddhant-Goswami

100x-LLM

★ 593

Code snippets and examples from the 100x Applied AI cohort lectures.

timbmg

Sentence-VAE

★ 593

PyTorch Re-Implementation of "Generating Sentences from a Continuous Space" by Bowman et al 2015 https://arxiv.org/abs/1511.06349

thousandbrainsproject

tbp.monty

★ 592

Monty is a sensorimotor learning framework based on the thousand brains theory of the neocortex.

DevnorsAI

devnors-data-python

★ 592

Devnors Data Python SDK: APIs for legal case documents and law articles, company registry and annual reports, tax invoicing, dishonest-judgment-debtor and enforcement-debtor checks, keyword and WeChat index, hot search rankings, and express delivery tracking, via /v1/data/query with an API key; supports MCP and AI agents.

remyxai

VQASynth

★ 591

Compose multimodal datasets 🎹

ARahim3

kaggle-tpu-lab

★ 591

Frontier-class open models on a free Kaggle TPU v5e-8: GLM-5.3-Flash 320B MoE (~64 tok/s, our own JAX engine) and Qwen3.8-27B bf16 (~130 tok/s), 262k context, prefix caching. Works with Claude Code, Codex, opencode and pi.

wanshuiyin

ARIS-in-AI-Offer

★ 591

Bilingual (Chinese + English) ML / LLM / diffusion / agent interview cheat sheets for China's AI recruiting season, generated by ARIS /interview-cheatsheet and rendered by /render-html into single-file HTML that reads anywhere, plus a CV-to-DBLP fact-checked academic homepage generator and hand-authored long-form blogs.

louisedesadeleer

clipify

★ 590

Claude Code skill: turn long videos into social-ready clips. Auto-find funny moments, cut, reframe to 9:16 with face-tracking, and burn opus-style captions.

gokayfem

ComfyUI_VLM_nodes

★ 589

ComfyUI nodes for vision-language models: Qwen3-VL, Moondream 3, Florence-2, SmolVLM2, InternVL, Gemma 3, MiniCPM-V. Plus open-vocabulary detection, SAM2/SAM3 segmentation, video temporal reasoning, GGUF via llama.cpp, and hosted LLM/VLM APIs.

stevesolun

ctx

★ 588

Repo-aware recommendations for skills, agents, MCP servers, and model harnesses. Use your own inventory or the shipped 79,958-node graph with 68,494 skills, 467 agents, 10,790 MCPs, and 207 harnesses.

yanhua1010

self-media-content-workflow

★ 588

A modular, tool-agnostic self-media content skill suite for content production and operations.

baidubce

app-builder

★ 587

appbuilder-sdk: the Qianfan AppBuilder SDK helps developers flexibly and quickly build AI-native applications.