Library
86,219 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.
Results
-
OpenAI: GPT-6.1 Terra
ModelsGPT-6.1 Terra is the mid-tier model in OpenAI's GPT-6.1 series, priced below GPT-6.1 Sol. It is suited for everyday agentic, coding, and writing work, is particularly strong at understanding screenshots...
openai/gpt-6.1-terra -
ViNano
MCP serversImage generation, image editing and text/image-to-video with credit quotes and connection budgets.
-
optics-framework
MCP serversOpen-source test automation for Android, iOS, web, smart TV (Android TV, Tizen, webOS) and Bluetooth (BLE) devices. Write tests as CSV/YAML, record them live, or let an AI agent build them over MCP. Self-healing locators: XPath, text, OCR, image.
git clone https://github.com/mozarkai/optics-framework.git -
HunyuanVideo-Avatar
Modelsimage to video model by tencent
tencent/HunyuanVideo-Avatar -
LTX2.3-10Eros
Modelsimage to video model by TenStrip · diffusers
TenStrip/LTX2.3-10Eros -
Cosmonote
MCP serversAccess your Cosmonote audio notes, transcriptions, summaries, and action items.
-
Hunyuan-GameCraft-1.0
Modelsimage to video model by tencent
tencent/Hunyuan-GameCraft-1.0 -
MAGI-1
Modelsimage to video model by sand-ai · diffusers
sand-ai/MAGI-1 -
Wan_2.2_ComfyUI_Repackaged
Modelsimage to video model by Comfy-Org · diffusion-single-file
Comfy-Org/Wan_2.2_ComfyUI_Repackaged -
kineo
Agents & frameworks🎬 端到端 AI 漫剧 / 动画短剧 Multi-Agent 多智能体协作创作平台 (Kineo AI)。基于 Hub-and-Spoke 智能体架构、ProjectBlackboard 共享黑板、自定义 Agent 扩展插件、角色 Consistency 锚定与 4K GPU 压制。
git clone https://github.com/Agions/kineo.git -
Computer Vision Client
Public APIsThe Computer Vision API provides state-of-the-art algorithms to process images and return information. For example, it can be used to determine if an image contains mature content, or it can be used to find all the faces in an image. It also has other features like estimating dominant and accent colors, categorizing the content of images, and describing an image with complete English sentences…
-
Computer Vision Client
Public APIsThe Computer Vision API provides state-of-the-art algorithms to process images and return information. For example, it can be used to determine if an image contains mature content, or it can be used to find all the faces in an image. It also has other features like estimating dominant and accent colors, categorizing the content of images, and describing an image with complete English sentences…
-
OpenAI: GPT-5.6 Luna (batch)
ModelsGPT-5.6 Luna is a fast, cost-efficient model in OpenAI's GPT-5.6 series. It is suited for high-volume, latency-sensitive tasks such as chat, classification, and lightweight agentic workflows, providing capable reasoning for...
openai/gpt-5.6-luna:batch -
GPT-6.1 Terra is the mid-tier model in OpenAI's GPT-6.1 series, priced below GPT-6.1 Sol. It is suited for everyday agentic, coding, and writing work, is particularly strong at understanding screenshots...
openai/gpt-6.1-terra:batch -
Moltline Vision Maths
MCP serversImage header probing, bbox conversion, resize plans and colour maths. 4 of 6 free.
-
seamless-m4t-v2-large
Modelsautomatic speech recognition model by facebook · transformers
facebook/seamless-m4t-v2-large -
Indian-Emotional-Speech-Corpus
Datasets & benchmarksHugging Face dataset by humyn-labs
humyn-labs/Indian-Emotional-Speech-Corpus -
Wan2.2-I2V-A14B
Modelsimage to video model by Wan-AI · wan2.2
Wan-AI/Wan2.2-I2V-A14B -
mobile-actions
Datasets & benchmarksHugging Face dataset by google
google/mobile-actions -
tts-1.6b-en_fr
Modelstext to speech model by kyutai · moshi
kyutai/tts-1.6b-en_fr -
Use the attached still (step 1: a geyser erupting in a snowy volcanic valley at sunrise) as the exact first frame and animate it into a 6-second, 16:9 cinematic shot. Keep every element where it is in the still: the…
-
VoxCPM2
Modelstext to speech model by openbmb · voxcpm
openbmb/VoxCPM2 -
gigaspeech
Datasets & benchmarksHugging Face dataset by speechcolab
speechcolab/gigaspeech -
MARS5-TTS
Modelstext to speech model by CAMB-AI · mars5-tts
CAMB-AI/MARS5-TTS
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.