Library
86,219 resources from 11 public sources. 46 checked by hand; the rest are unreviewed.
Results
-
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 -
VAR
AI repositories[NeurIPS 2024 Best Paper Award][GPT beats diffusion🔥] [scaling laws in visual generation📈] Official impl. of "Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale Prediction". An *ultra-simple, user-friendly yet state-of-the-art* codebase for autoregressive image generation!
git clone https://github.com/FoundationVision/VAR.git -
MiniMax-Music3
Modelstext to audio model by MiniMaxAI · diffusers
MiniMaxAI/MiniMax-Music3 -
open-webui-tools
Agents & frameworksOpen‑WebUI Tools is a modular toolkit designed to extend and enrich your Open WebUI instance, turning it into a powerful AI workstation. With a suite of over 15 specialized tools, function pipelines, and filters, this project supports academic research, agentic autonomy, multimodal creativity, workflows, and more
git clone https://github.com/Haervwe/open-webui-tools.git -
Hugging Face
Public APIsAI model hub with inference API for NLP, computer vision, and audio
-
Ace-Step1.5
Modelstext to audio model by ACE-Step · transformers
ACE-Step/Ace-Step1.5 -
EgoDemo
Datasets & benchmarksHugging Face dataset by LightwheelAI
LightwheelAI/EgoDemo -
bark
Modelstext to speech model by suno · transformers
suno/bark -
NVIDIA Nemotron 3.5 Content Safety is a compact 4B-parameter multimodal guardrail model from NVIDIA, fine-tuned from Google Gemma-3-4B. It moderates both inputs to and responses from LLMs and VLMs, accepting...
nvidia/nemotron-3.5-content-safety -
Anthropic: Claude Opus 4.5
ModelsClaude Opus 4.5 is Anthropic’s frontier reasoning model optimized for complex software engineering, agentic workflows, and long-horizon computer use. It offers strong multimodal capabilities, competitive performance across real-world coding and...
anthropic/claude-opus-4.5 -
Mistral: Mistral Medium 3
ModelsMistral Medium 3 is a high-performance enterprise-grade language model designed to deliver frontier-level capabilities at significantly reduced operational cost. It balances state-of-the-art reasoning and multimodal performance with 8× lower cost...
mistralai/mistral-medium-3 -
SFX Engine
MCP serversGenerate sound effects and music from text for games, apps and videos. Returns audio file URLs.
-
Interactive-LLM-Powered-NPCs
Agents & frameworksInteractive LLM Powered NPCs, is an open-source project that completely transforms your interaction with non-player characters (NPCs) in any game! 🎮🤖🚀
git clone https://github.com/AkshitIreddy/Interactive-LLM-Powered-NPCs.git -
image to video model by stabilityai · diffusers
stabilityai/stable-video-diffusion-img2vid-xt -
Open-AI-Micro-Drama-Generator
Agents & frameworksAI short drama & micro-drama video generator — turns any idea into a complete short-form drama using multi-agent AI pipeline (screenwriter → storyboard → frames → video). Seedance 2 VIP, Kling 3.0 Pro, Veo 3.1, Sora 2.
git clone https://github.com/Anil-matcha/Open-AI-Micro-Drama-Generator.git -
Google: Nano Banana 2.1
ModelsNano Banana 2.1 (Gemini Nano Banana 2.1) is Google's image generation and editing model on the Flash tier, succeeding Nano Banana 2 and Nano Banana Pro. It improves product recontextualization,...
google/gemini-nano-banana-2.1 -
Seedance 2.0 MCP
MCP serversCreate AI videos with Seedance 2.0 by text to video, text to image, image editing, and image to
-
OpenAI: GPT-5.4 Nano
ModelsGPT-5.4 nano is the most lightweight and cost-efficient variant of the GPT-5.4 family, optimized for speed-critical and high-volume tasks. It supports text and image inputs and is designed for low-latency...
openai/gpt-5.4-nano -
One reviewed image or one 8 second video from a text prompt. Paid per call by x402, no account.
-
Video to Audio Converter MCP
MCP serversVideo to Audio Converter is a free, browser-based tool that extracts audio tracks from common video
-
MoonshotAI: Kimi K2.7 Code
ModelsMoonshotAI: Kimi K2.7 Code is a coding-focused model in Moonshot AI's Kimi K2 family, built to complete end-to-end programming tasks reliably over long contexts. It uses a native multimodal mixture-of-experts...
moonshotai/kimi-k2.7-code -
NVIDIA Nemotron 3.5 Content Safety is a compact 4B-parameter multimodal guardrail model from NVIDIA, fine-tuned from Google Gemma-3-4B. It moderates both inputs to and responses from LLMs and VLMs, accepting...
nvidia/nemotron-3.5-content-safety:free -
Claude Opus 4.5 is Anthropic’s frontier reasoning model optimized for complex software engineering, agentic workflows, and long-horizon computer use. It offers strong multimodal capabilities, competitive performance across real-world coding and...
anthropic/claude-opus-4.5:batch -
superCMO-skills
SkillsOpen-source skills that empower any AI agent (Claude, Cursor, Hermes, etc.) to generate end-to-end marketing campaigns - UGC videos, ad videos, product photography and more.
git clone https://github.com/SupercmoHQ/superCMO-skills.git
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.