Available apps

App name
Description

A web-based remote shell instrumented with Apolo CLI, providing immediate access to dedicated compute resources.

A highly-available LLM inference service with an OpenAI-compatible API, capable of efficiently serving both standard and quantized models available on HuggingFace.

An industry-standard relational database system that includes pgvector for advanced semantic search capabilities.

Text Embeddings Inference (TEI) is a comprehensive toolkit designed for efficient deployment and serving of open source text embeddings models. It enables high-performance extraction for the most popular models.

An interactive tool that enables the creation and sharing of documents with live code, visualizations, and narrative text.

A lightweight, powerful source code editor with a rich ecosystem of extensions for many languages and runtimes.

A Python IDE for data science and web development.

A tool that streamlines the full lifecycle of machine learning projects, enhancing manageability, traceability, and reproducibility.

A simple model deployment service leveraging Triton and MLflow as its core inference servers.

Open-source LLM app development platform

A robust, open-source vector database enabling semantic search. Store and query data based on meaning using its GraphQL, REST, and gRPC APIs for seamless integration with your applications. Supports various modules for extended functionality.

Fooocus is a free, offline, open-source image generator that creates images from prompts without manual tweaking, requiring minimal GPU memory (4GB).

Open-source image generation and editing platform powered by advanced latent diffusion models.

Integration with Hugging Face hub allows you to manage your account token, cache models and datasets on the platform.

Deploy, auto-scale, securely expose to outer world any containerized application.

Unified analytics engine for large-scale data processing that provides high-level APIs in Java, Scala, Python, and R.

Spin-up secure version of context-aware ChatGPT without a fear of data leak.

Superset is fast, lightweight, intuitive, and loaded with options that make it easy for users of all skill sets to explore and visualize their data, from simple line charts to highly detailed geospatial charts.

DeepSeek R1 is an open-source language model by DeepSeek AI, designed for efficient, high-quality text generation and reasoning tasks. It supports instruction tuning and runs on GPUs with as little as 16GB memory.

LLaMA 4 is a family of open-weight language models by Meta AI, optimized for performance and scalability.

Mistral is a suite of open-weight language models developed by Mistral AI, known for fast inference and strong performance.

Last updated

Was this helpful?