AI Tools
AI tools. Sorted by what actually ships.
SmolAgents
smolagents is a barebones library for building agents that think in code. It enables running powerful AI agents in a few lines of code, with first-class support for CodeAgents that write actions as Python code snippets. The library is model-agnostic (supports any LLM via Hugging Face, LiteLLM, OpenAI, Anthropic, etc.), tool-agnostic (supports MCP, LangChain, Hub Spaces), and modality-agnostic (text, vision, video, audio). It includes a CLI, sandboxed execution (E2B, Docker, Pyodide), and Hub integration for sharing agents.
Mistral.rs
Mistral.rs is a fast, flexible LLM inference engine written in Rust. It supports any Hugging Face model with zero configuration, true multimodality (text, vision, video, audio, speech, image generation, embeddings), full quantization control (ISQ, GGUF, GPTQ, AWQ, HQQ, FP8, BNB), built-in web UI, hardware-aware tuning, and flexible SDKs (Python and Rust). It features agentic capabilities like server-side tool loops, web search, MCP client, and HTTP tool dispatch. Performance optimizations include continuous batching, FlashAttention, PagedAttention, and multi-GPU tensor parallelism.
Janus Pro - Deepseek
Janus-Series is a family of unified multimodal understanding and generation models developed by DeepSeek. It includes Janus, JanusFlow, and Janus-Pro, which integrate autoregressive language models with rectified flow for text-to-image generation and multimodal understanding. The models decouple visual encoding into separate pathways to alleviate conflicts between understanding and generation tasks. Janus-Pro features optimized training, expanded data, and larger model sizes, achieving significant advancements in both understanding and instruction-following for image generation. The models are available on Hugging Face and support both multimodal understanding (image+text input) and text-to-image generation.
Cua AI
Cua provides cloud desktops for AI agents, supporting macOS, Windows, Linux, and Android sandboxes. It enables engineers to boot, configure, snapshot, and fork environments for computer-use agents like Claude Code, Codex, and OpenClaw. Trusted by 50,000+ engineers at companies like Hugging Face, Datadog, Meta, and NVIDIA.
.webp)
Inferless
Inferless is a serverless GPU inference platform that enables users to deploy machine learning models in minutes. It supports deployment from Hugging Face, Git, Docker, or CLI, with automatic scaling from zero to hundreds of GPUs. Features include custom runtimes, writable volumes, automated CI/CD, monitoring, dynamic batching, and private endpoints. It is SOC-2 Type II certified, penetration tested, and regularly scanned for vulnerabilities. Inferless is designed for production workloads, offering zero infrastructure management, pay-per-use pricing, and lightning-fast cold starts.
Hugging Face Spaces
Hugging Face Spaces is a directory and hosting platform for machine learning applications built by the community. It allows users to discover, run, and deploy ML apps across categories like image generation, video generation, text analysis, and more. The platform features a curated list of trending apps, including tools for voice cloning, 3D modeling, and chatbot assistants, all accessible via a web interface.
Yugo
Yugo is an innovative platform designed to simplify the integration of AI functionalities into web services. It automates API documentation analysis, provides personalized AI feature recommendations, and enables one-click integration with major AI platforms like OpenAI and Hugging Face. Yugo reduces development time and complexity, allowing developers and businesses to create AI-enhanced applications with ease.
DimensionX
DimensionX is a Hugging Face Space that generates 3D/4D scenes from a single image using controllable video diffusion. Users upload an image, type a text prompt describing the scene, and pick an orbit direction (left or up). The app creates a short, high-quality video that animates a 3D-like view around the image.