Apps tagged with 'Multimodal'

Trae is an adaptive AI IDE that transforms how you work, collaborating with you to run faster.

Autoregressive models that unify multimodal tasks, surpassing specialized models with visual path decoupling, autoregressive integration, and flexible design.

The main goal of llama.cpp is to enable LLM inference with minimal setup and state-of-the-art performance on a wide range of hardware - locally and in the cloud.

Clef is a 27B multimodal model that turns a state and a schema of typed questions into decisions. It reads the state as text, JSON, images, or video, and returns a probability for every allowed option of every question in a single forward pass.

Pipecat is a framework for building voice (and multimodal) conversational agents. Things like personal coaches, meeting assistants, story-telling toys for kids, customer support bots, intake flows, and snarky social companions.

Amazon Nova is a new generation of foundation models with frontier intelligence and industry leading price performance. Generate text, code, and images with natural language prompts.

An Extensible Multi-person interactive Agent Framework Powered by LLM Code Generation; Support: QQ, Discord, Minecraft, Bilibili Live, SSE(SDK) ...

PixelRAG renders documents — web pages, PDFs, images — as screenshots and retrieves over the images directly. Visual structure that HTML parsing throws away — tables, charts, layout, infographics — stays intact, so the reader model can actually answer questions about it.

Have a truly private AI conversation with powerful models and compare results. Brainstorm, create, and analyze without compromising your data.

LLM Hub is an open-source Android app for on-device LLM chat and image generation. It's optimized for mobile usage (CPU/GPU/NPU acceleration) and supports multiple model formats so you can run powerful models locally and privately.

Marqo is an AI-native ecommerce search and product discovery platform built for retail brands in fashion, beauty, footwear, and home goods.

Nexa Studio: Offline, Private AI with Unlimited Use.

An end-to-end MLLM that accept any-form referring and ground anything in response.

LLMII uses a local AI to label metadata and index images. It does not rely on a cloud service or database.

Fenn is a powerful, AI-driven desktop search engine for macOS that makes your files instantly searchable—including videos, audio, PDFs, Word documents, Excel sheets, and images. Just type or upload an image to find exactly where any object, person, or concept appears.

Gai is a beginner-friendly AI toolkit with no ads, no registration, and no other permissions required, except for Internet.

Reka.ai is a multimodal AI platform that builds advanced models from scratch, enabling agents that can see, hear, and reason across text, images, audio, and video—deployable anywhere from lightweight devices to enterprise systems.

Cognigy.AI is the Conversational AI Platform focused on the needs of large enterprises to develop, deploy and run Conversational AIs on any conversational channel.

OmniSVG is the first family of end-to-end multimodal SVG generators that leverage pre-trained Vision-Language Models (VLMs), capable of generating complex and detailed SVGs, from simple icons to intricate anime characters.

Seedream is a multimodal AI image generation and editing model developed by ByteDance Seed. It is designed for creating detailed visual assets from text prompts, sketches, annotations, and reference images, with a focus on professional design and production use cases.

Run and fine-tune generative AI models with easy-to-use APIs and highly scalable infrastructure. Train and deploy models at scale on our AI Acceleration Cloud and scalable GPU clusters. Optimize performance and cost.

A free, open-source app to discover, run, and use AI models on your own computer, with hardware-aware recommendations, easy setup, and advanced controls when needed.

Store, search, and query multi-modal data with fine-grained access control and built-in security. Build AI applications with confidence and speed.

DataChain builds a suite of tools for data preprocessing and management, experiment tracking, ML models versioning, and pipeline automation.

Open-source multimodal model with 7B active parameters for tasks like text-to-image, image editing, visual manipulation, multiview synthesis, and world navigation.