InnerVault

Library

85,762 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.

Results

  1. VisualAgentBench

    Agents & frameworks

    Towards Large Multimodal Models as Visual Foundation Agents

    Stale GitHub, THUDM 278 ★Apache-2.0Updated 19 months ago

    git clone https://github.com/THUDM/VisualAgentBench.git
  2. sglang

    AI repositories

    SGLang is a high-performance serving framework for large language models and multimodal models.

    Indexed GitHub, sgl-project 38.9k ★Apache-2.0Updated today

    git clone https://github.com/sgl-project/sglang.git
  3. awesome-ai-for-games

    AI repositories

    A curated, searchable collection of research on AI and foundation models across the game lifecycle.

    Stale GitHub, Eurekaleo 390 ★MITUpdated 7 days ago

    git clone https://github.com/Eurekaleo/awesome-ai-for-games.git
  4. 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.

    Indexed GitHub, huggingface 169.0k ★Apache-2.0Updated today

    git clone https://github.com/huggingface/transformers.git
  5. 🔥🔥🔥 A curated list of papers on LLMs-based multimodal generation (image, video, 3D and audio).

    Stale GitHub, YingqingHe 551 ★Updated 6 days ago

    git clone https://github.com/YingqingHe/Awesome-LLMs-meet-Multimodal-Generation.git
  6. VideoGLaMM

    Agents & frameworks

    [CVPR 2025 🔥]A Large Multimodal Model for Pixel-Level Visual Grounding in Videos

    Stale GitHub, mbzuai-oryx 106 ★Updated 2 months ago

    git clone https://github.com/mbzuai-oryx/VideoGLaMM.git
  7. 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.

    Stale GitHub, mbzuai-oryx 969 ★Apache-2.0Updated 2 months ago

    git clone https://github.com/mbzuai-oryx/groundingLMM.git
  8. vllm-mlx

    AI repositories

    High-performance OpenAI and Anthropic compatible LLM inference server for Apple Silicon. Native MLX, continuous batching, multimodal models, MCP tool calling, and Claude Code support.

    Stale GitHub, waybarrios 1,646 ★Apache-2.0Updated 11 days ago

    git clone https://github.com/waybarrios/vllm-mlx.git
  9. GPA-LM

    Agents & frameworks

    This 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".

    Stale GitHub, BAAI-Agents 162 ★Updated 2 years ago

    git clone https://github.com/BAAI-Agents/GPA-LM.git
  10. Amazon 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.

    Indexed OpenRouter model list, amazon Updated 12 months ago

    amazon/nova-premier-v1
  11. Amazon 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...

    Indexed OpenRouter model list, amazon Updated 23 months ago

    amazon/nova-pro-v1
  12. 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...

    Indexed OpenRouter model list, meta Updated 3 months ago

    meta/muse-glimmer-30b
  13. Amazon 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...

    Indexed OpenRouter model list, amazon Updated 23 months ago

    amazon/nova-lite-v1
  14. 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...

    Indexed OpenRouter model list, meta Updated 3 months ago

    meta/muse-glimmer-30b:batch
  15. Gemma 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...

    Indexed OpenRouter model list, google Updated 7 months ago

    google/gemma-4-31b-it
  16. Gemma 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...

    Indexed OpenRouter model list, google Updated 7 months ago

    google/gemma-4-31b-it:free
  17. Kimi 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...

    Indexed OpenRouter model list, moonshotai Updated 9 months ago

    moonshotai/kimi-k2.5
  18. 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...

    No longer listed OpenRouter model list, qwen Updated 13 months ago

    qwen/qwen3-vl-30b-a3b-thinking
  19. 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...

    Indexed OpenRouter model list, qwen Updated 13 months ago

    qwen/qwen3-vl-30b-a3b-instruct
  20. MiniMax-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,...

    Indexed OpenRouter model list, minimax Updated 28 days ago

    minimax/minimax-m3.1-flash
  21. 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...

    Indexed OpenRouter model list, qwen Updated 13 months ago

    qwen/qwen3-vl-235b-a22b-instruct
  22. 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...

    Indexed OpenRouter model list, nvidia Updated 6 months ago

    nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free
  23. Qwen3.6-35B-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...

    Indexed OpenRouter model list, qwen Updated 6 months ago

    qwen/qwen3.6-35b-a3b
  24. Kimi 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...

    Indexed OpenRouter model list, moonshotai Updated 7 months ago

    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.