Type a name, or just describe what you need. Results blend keyword and meaning-based search. 10 matches, each with an EU availability status.
Library
Open-source library, proxy and MCP server that compresses tool outputs, logs, RAG chunks and history before they reach an LLM.
Model · NVIDIA
NVIDIA family of multilingual text embedding models (8B and 1B) for retrieval, RAG and coding agents.
App
Open-source, self-hostable alternative to Google NotebookLM with multi-provider AI, local models and multi-speaker podcasts.
App · Google
Google's AI research and note-taking assistant (formerly NotebookLM) that answers from sources you upload.
Model · Google
Google's small open embedding model that maps text, code, images, video and audio into a shared embedding space.
Model · Perplexity
Open-weights vision-language embedding models from Perplexity (9B and 600M) for text, image and document retrieval.
App · Hyperagent
Web platform for deploying AI agents as staff that perform business tasks and learn how an organization operates.
Model · Cactus Compute
Tiny ~51M-parameter vision model from Cactus Compute for on-device object detection, text reading and spatial understanding.
Open-source, self-hostable workspace for named AI agents with memory, routines, and approval controls; bring your own model.
Model · Mirage
Avatar video model from Mirage, marketed for identity preservation in AI-generated talking-person videos.
