Library
85,762 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.
Results
-
VisualAgentBench
Agents & frameworksTowards Large Multimodal Models as Visual Foundation Agents
git clone https://github.com/THUDM/VisualAgentBench.git -
sglang
AI repositoriesSGLang is a high-performance serving framework for large language models and multimodal models.
git clone https://github.com/sgl-project/sglang.git -
awesome-ai-for-games
AI repositoriesA curated, searchable collection of research on AI and foundation models across the game lifecycle.
git clone https://github.com/Eurekaleo/awesome-ai-for-games.git -
transformers
AI repositories🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.
git clone https://github.com/huggingface/transformers.git -
Awesome-LLMs-meet-Multimodal-Generation
AI repositories🔥🔥🔥 A curated list of papers on LLMs-based multimodal generation (image, video, 3D and audio).
git clone https://github.com/YingqingHe/Awesome-LLMs-meet-Multimodal-Generation.git -
VideoGLaMM
Agents & frameworks[CVPR 2025 🔥]A Large Multimodal Model for Pixel-Level Visual Grounding in Videos
git clone https://github.com/mbzuai-oryx/VideoGLaMM.git -
groundingLMM
Agents & frameworks[CVPR 2024 🔥] Grounding Large Multimodal Model (GLaMM), the first-of-its-kind model capable of generating natural language responses that are seamlessly integrated with object segmentation masks.
git clone https://github.com/mbzuai-oryx/groundingLMM.git -
vllm-mlx
AI repositoriesHigh-performance OpenAI and Anthropic compatible LLM inference server for Apple Silicon. Native MLX, continuous batching, multimodal models, MCP tool calling, and Claude Code support.
git clone https://github.com/waybarrios/vllm-mlx.git -
GPA-LM
Agents & frameworksThis repo is a live list of papers on game playing and large multimodality model - "A Survey on Game Playing Agents and Large Models: Methods, Applications, and Challenges".
git clone https://github.com/BAAI-Agents/GPA-LM.git -
Amazon: Nova Premier 1.0
ModelsAmazon Nova Premier is the most capable of Amazon’s multimodal models for complex reasoning tasks and for use as the best teacher for distilling custom models.
amazon/nova-premier-v1 -
Amazon: Nova Pro 1.0
ModelsAmazon Nova Pro 1.0 is a capable multimodal model from Amazon focused on providing a combination of accuracy, speed, and cost for a wide range of tasks. As of December...
amazon/nova-pro-v1 -
Meta: Muse Glimmer 30B
ModelsMuse Glimmer 30B is a dense, open-weight multimodal model from Meta Superintelligence Labs, distilled from Muse Spark and optimized for autonomous agents on consumer hardware. It is suited for long-horizon...
meta/muse-glimmer-30b -
Amazon: Nova Lite 1.0
ModelsAmazon Nova Lite 1.0 is a very low-cost multimodal model from Amazon that focused on fast processing of image, video, and text inputs to generate text output. Amazon Nova Lite...
amazon/nova-lite-v1 -
Muse Glimmer 30B is a dense, open-weight multimodal model from Meta Superintelligence Labs, distilled from Muse Spark and optimized for autonomous agents on consumer hardware. It is suited for long-horizon...
meta/muse-glimmer-30b:batch -
Google: Gemma 4 31B
ModelsGemma 4 31B Instruct is Google DeepMind's 30.7B dense multimodal model supporting text and image input with text output. Features a 256K token context window, configurable thinking/reasoning mode, native function...
google/gemma-4-31b-it -
Google: Gemma 4 31B (free)
ModelsGemma 4 31B Instruct is Google DeepMind's 30.7B dense multimodal model supporting text and image input with text output. Features a 256K token context window, configurable thinking/reasoning mode, native function...
google/gemma-4-31b-it:free -
MoonshotAI: Kimi K2.5
ModelsKimi K2.5 is Moonshot AI's native multimodal model, delivering state-of-the-art visual coding capability and a self-directed agent swarm paradigm. Built on Kimi K2 with continued pretraining over approximately 15T mixed...
moonshotai/kimi-k2.5 -
Qwen3-VL-30B-A3B-Thinking is a multimodal model that unifies strong text generation with visual understanding for images and videos. Its Thinking variant enhances reasoning in STEM, math, and complex tasks. It excels...
qwen/qwen3-vl-30b-a3b-thinking -
Qwen3-VL-30B-A3B-Instruct is a multimodal model that unifies strong text generation with visual understanding for images and videos. Its Instruct variant optimizes instruction-following for general multimodal tasks. It excels in perception...
qwen/qwen3-vl-30b-a3b-instruct -
MiniMax: MiniMax M3.1 Flash
ModelsMiniMax-M3.1-Flash is a multimodal model from MiniMax. Compared with M3, it delivers significant improvements across multiple benchmarks, particularly in complex agentic tasks, coding, and cybersecurity. It is built for complex,...
minimax/minimax-m3.1-flash -
Qwen3-VL-235B-A22B Instruct is an open-weight multimodal model that unifies strong text generation with visual understanding across images and video. The Instruct model targets general vision-language use (VQA, document parsing, chart/table...
qwen/qwen3-vl-235b-a22b-instruct -
NVIDIA Nemotron™ 3 Nano Omni is a 30B-A3B open multimodal model designed to function as a perception and context sub-agent in enterprise agent systems. It accepts text, image, video, and...
nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free -
Qwen: Qwen3.6 35B A3B
ModelsQwen3.6-35B-A3B is an open-weight multimodal model from Alibaba Cloud with 35 billion total parameters and 3 billion active parameters per token. It uses a hybrid sparse mixture-of-experts architecture combining Gated...
qwen/qwen3.6-35b-a3b -
MoonshotAI: Kimi K2.6
ModelsKimi K2.6 is Moonshot AI's next-generation multimodal model, designed for long-horizon coding, coding-driven UI/UX generation, and multi-agent orchestration. It handles complex end-to-end coding tasks across Python, Rust, and Go, and...
moonshotai/kimi-k2.6
Indexed entries aren't reviewed or tested by InnerVault. Details come straight from each source. Anything that can reach your accounts, files or browser can do damage, so read the source before you install it.