InnerVault

Library

86,235 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.

Results

11,936 results with any of your words Clear search and filters
  1. NVIDIA Nemotron 3.5 Super VL is an open multimodal mixture-of-experts model from NVIDIA, with 12B active parameters out of 120B total. It takes text, images, documents, GUI screenshots, and video...

    Indexed OpenRouter model list, nvidia Updated 33 days ago

    nvidia/nemotron-3.5-super-vl
  2. Gemini 4 Carbon is a frontier Gemini 4 model from Google for coding, agentic and complex reasoning work. It takes text, image, audio, video and file input, supports long decode...

    Indexed OpenRouter model list, google Updated 7 days ago

    google/gemini-4-carbon:batch
  3. notebooklm-mcp

    MCP servers

    MCP server for Google NotebookLM — 27 tools for notebooks, sources, research, and studio content generation

    Stale GitHub, m4yk3ldev 20 ★MITUpdated 28 days ago

    git clone https://github.com/m4yk3ldev/notebooklm-mcp.git
  4. New updated extracted System Prompts from popular chatbots like ChatGPT, Claude & Gemini

    Stale GitHub, zebbern 30 ★Updated 16 months ago

    git clone https://github.com/zebbern/system_prompts_leaks.git
  5. The Qwen3.5 native vision-language Flash models are built on a hybrid architecture that integrates a linear attention mechanism with a sparse mixture-of-experts model, achieving higher inference efficiency. Compared to the...

    Indexed OpenRouter model list, qwen Updated 8 months ago

    qwen/qwen3.5-flash-02-23
  6. tensorzero

    AI repositories

    TensorZero is an open-source LLMOps platform that unifies an LLM gateway, observability, evaluation, optimization, and experimentation.

    Stale Archived GitHub, tensorzero 11.7k ★Apache-2.0Updated 5 months ago 1 note

    git clone https://github.com/tensorzero/tensorzero.git
  7. Online CPR, AED & first aid courses, prices and employer-acceptance wording. Read-only, no sign-in.

    Stale Official MCP Registry, com.getmandatorytraining Updated 40 days ago 1 note

  8. 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
  9. NVIDIA Nemotron 3.5 Super VL is an open multimodal mixture-of-experts model from NVIDIA, with 12B active parameters out of 120B total. It takes text, images, documents, GUI screenshots, and video...

    Indexed OpenRouter model list, nvidia Updated 33 days ago

    nvidia/nemotron-3.5-super-vl:free
  10. saymaker-mcp

    MCP servers

    Generate and edit AI images and video on SayMaker: Veo 3.1, Kling 3.0, Seedance 2.0, Nano Banana 2.

    Stale Official MCP Registry, ai.saymaker Updated 43 days ago 1 note

    saymaker-mcp@0.1.1
  11. Generate and edit HappyHorse videos with Ace Data Cloud; retrieve the original task for results.

    Indexed Official MCP Registry, io.github.AceDataCloud Updated 2 days ago 3 notes

    mcp-happyhorse@2026.11.15.1
  12. Read EXIF, GPS, XMP, C2PA and AI-generator metadata from a public image or video URL. Read-only.

    Stale Official MCP Registry, com.metadataremoverai Updated 12 days ago 1 note

  13. VeritasGraph

    AI repositories

    VeritasGraph — open-source Knowledge Graph & GraphRAG framework on GitHub. Build multi-hop reasoning, ontology-aware retrieval, and verifiable attribution over your own data. Nodes, edges, RDF, linked-data — runs locally or in the cloud.

    Indexed GitHub, bibinprathap 327 ★MITUpdated 6 days ago

    git clone https://github.com/bibinprathap/VeritasGraph.git
  14. dataset

    Prompts

    Generative AI-based CyberSecurity-focused Prompt Dataset for Benchmarking Large Language Models

    Stale GitHub, cysecbench 50 ★MITUpdated 22 months ago

    git clone https://github.com/cysecbench/dataset.git
  15. Step 1 — Image (Nano Banana 2.1): generate the product poster An epic minimalist poster for a walkman product called Explo, all in matte white style colors, thin font, the product has a slight neon glow around it, dark…

    Indexed prompts.chat (CC0 prompt collection), f CC0-1.0

  16. MCP server for China Railway 12306 ticket availability: schedules and seats by Chinese station name.

    Stale Official MCP Registry, cn.pianam.mcp Updated 2 months ago 1 note

  17. 🚀 An awesome list of curated Seedance 2.5 prompts and examples. Your go-to resource for mastering prompt engineering and exploring the creative potential of Seedance 2.5 AI video model.

    Indexed GitHub, ZeroLu 150 ★MITUpdated today

    git clone https://github.com/ZeroLu/awesome-seedance-2.5.git
  18. image text to text model by nota-ai · transformers

    Stale Hugging Face Hub, nota-ai 20 ♥otherUpdated 11 days ago 1 note

    nota-ai/Kimi-K3.1-Pro-Global-Pruned-30
  19. { "role": "Calm, careful passenger-rights assistant who helps train travelers understand a delay or cancellation, gather evidence, check whether compensation or a refund may apply under the rules for their region…

    Indexed prompts.chat (CC0 prompt collection), f CC0-1.0

  20. upres-cli

    MCP servers

    UpRes MCP: list models, credits, submit 4K image and video upscale jobs.

    Stale Official MCP Registry, io.github.auroracapital Updated 59 days ago 1 note

    https://github.com/auroracapital/upres-cli/releases/download/v0.2.0/upres-cli-0.2.0.mcpb
  21. Indox

    MCP servers

    Convert documents, images, video, 3D models and fonts with the Indox API.

    Stale Official MCP Registry, org.indox Updated 3 days ago 3 notes

    indox-mcp@0.10.0
  22. Director

    Agents & frameworks

    AI video agents framework for next-gen video interactions and workflows.

    Indexed GitHub, video-db 1,588 ★MITUpdated 3 days ago

    git clone https://github.com/video-db/Director.git
  23. Step 3.7 Flash is StepFun's latest high-efficiency multimodal Mixture-of-Experts model. It pairs a 196B-parameter language backbone with a vision encoder for native image and video understanding, activating roughly 11B parameters...

    Indexed OpenRouter model list, stepfun Updated 5 months ago

    stepfun/step-3.7-flash
  24. MiMo-V2.5 is a native omnimodal model by Xiaomi. It delivers Pro-level agentic performance at roughly half the inference cost, while surpassing MiMo-V2-Omni in multimodal perception across image and video understanding...

    Indexed OpenRouter model list, xiaomi Updated 6 months ago

    xiaomi/mimo-v2.5

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.