AI Agent Skills

A Survey on Multimodal Retrieval-Augmented Generation

This repo contains the code for "VLM2Vec: Training Vision-Language Models for Massive Multimodal Embedding Tasks" [ICLR 2025]

Multi-Agent System Powered by LLMs for End-to-end Multimodal ML Automation

🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and traini…

Open-source AI orchestration framework for building context-engineered, production-ready LLM applications. Design modular pipelines and agent workflows with explicit con…

SeaTunnel is a multimodal, high-performance, distributed, massive data integration tool.

AI powered open source recommender system engine supports classical/LLM rankers and multimodal content via embedding

Swap GPT for any LLM by changing a single line of code. Xinference lets you run open-source, speech, and multimodal models on cloud, on-prem, or your laptop — all throug…

Deeplake is AI Data Runtime for Agents. It provides serverless postgres with a multimodal datalake, enabling scalable retrieval and training.

One delightful Ruby framework for every major AI provider. Build AI agents, chatbots, RAG apps, and multimodal workflows in beautiful, expressive code.

🤖 Type-safe, provider-agnostic TypeScript AI SDK for streaming chat, tool calling, agents, and multimodal apps across OpenAI, Anthropic, Gemini, React, Vue, Svelte, and…

Towards Large Multimodal Models as Visual Foundation Agents

AppAgent: Multimodal Agents as Smartphone Users, an LLM-based multimodal agent framework designed to operate smartphone apps.

Represent, send, store and search multimodal data

Cambrian-1 is a family of multimodal LLMs with a vision-centric design.

[EMNLP-2024] Build multimodal language agents for fast prototype and production