Modal

Stop renting your intelligence. Own it with AnythingLLM. Everything you need for a powerful local-first agent experience

Build and run agents you can see, understand and trust.

ModelScope: bring the notion of Model-as-a-Service to life.

The most accurate document search and store for building AI apps

Hugging Face model with 3624 likes. Tags: transformers, pytorch, multi_modality, muiltimodal, text-to-image, unified-model, any-to-any, arxiv:2501.17811, licens…

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

🎨 NeMo Data Designer: Generate high-quality synthetic data from scratch or from seed data.

SDK libraries for Modal

An Asynchronous Reinforcement Learning Engine for Omni-Modal Post-Training at Scale

Multimodal RAG to search and interact locally with technical documents of any kind

autoupdate paper list

World-class multimodal RAG system for financial document analysis. Built to production standards: async, observable, secure, multi-tenant, CI-gated.

One lib to rule them all (gen ai)

Build use cases with VideoDB

Testing Theory of Mind (ToM) in language models with epistemic logic

An open vision-language model for captioning and VQA.

Joint training recipes that align images and text in one embedding space.

A starter kit for training vision-language models.