Directory
Published directory entries matching your search.
This page describes an online car recognition tool that identifies vehicle information from an uploaded car picture, including brand, model, year and color. The page states that users upload a photo and click the "Car Model Recognition" button to use a machine learning model to identify the vehicle online. It is one of many tools listed on the ToolPie site.
Materials for the Hugging Face Diffusion Models Course, a free course on diffusion models. It covers theory, generating images and audio with Diffusers, training and fine-tuning models, and conditional generation. Prerequisites include Python skills and basics in deep learning and PyTorch.
Models.dev is a GitHub repository or organization with source code, releases, documentation, or project resources.
Self-hosted control plane that sits between connected AI clients, model providers, and tools. It applies access rules to users and agents, routes supported model requests through a gateway, checks governed tool calls before execution, and records policy decisions, execution records, and usage in the operator's environment. It deploys a Rust runtime with PostgreSQL on infrastructure the operator controls.
Model Extractor is a video tool for editing, effects, stock footage, animation, 3D, or creator workflows.
UE Viewer, formerly Unreal Model Viewer and also called umodel, is a program for viewing and extracting resources from games made with Unreal Engine. It loads packages from games and can export skeletal, vertex and static meshes, animations, textures and sounds. It is distributed for Windows and Linux.
Arena is a platform that provides leaderboards to compare and benchmark leading frontier AI models across text, image, vision, and other modalities. Its rankings are powered by real user sessions from a global user base, it tracks new model releases, and offers features including live agent sessions, side-by-side model comparison, and user voting for model performance.
Dify is a platform for building agentic workflows on one canvas, covering agents, knowledge pipelines, models and tools. Deployments include Dify Cloud, a VPC or self-hosted setup, and a source-available Community Edition. The platform also supports RAG pipelines with AI model and tool support.
Direct is a chat tool for interacting with multiple frontier AI models. It allows prompting several open source and proprietary large language models in one place, for research, coding, and creative tasks.
Falcon-40B-Instruct is a 40B parameter causal decoder-only model built by TII based on Falcon-40B and finetuned on a mixture of Baize, released under the Apache 2.0 license. It is intended as a ready-to-use chat and instruct model, and the card notes it may not be ideal for further finetuning. The model is trained mostly on English data, and users are advised to take precautions for production use.
Keras.js runs Keras models in the browser with GPU support using WebGL 2, and models can also run in Node.js in CPU mode. Models can be trained in any backend, including TensorFlow and CNTK. The project is no longer active and no longer updated, though the demos still work.
Kilo is an open source AI coding agent for VS Code, JetBrains, CLI, desktop and cloud. It offers access to 500+ models at zero markup, bring-your-own keys, or local models for privacy. Kilo Gateway provides a unified API to access AI models through a single endpoint.
LlamaChat is a free, open-source macOS application for chatting with LLaMA, Alpaca and GPT4All models running locally on a Mac. It can import raw PyTorch model checkpoints or pre-converted .ggml model files. The application is powered by llama.cpp and llama.swift and is not distributed with any model files.
Open-source project that supports deploying, serving, monitoring, or operating AI and machine-learning systems.
Odysseus is a self-hosted AI workspace for running language models on one's own hardware. It offers chat, autonomous agents, tools and MCP connections, model serving, an email assistant, deep research, model comparison and persistent memory. The project is described as local-first and privacy-first, with no telemetry.
Open WebUI is a self-hosted AI interface for running AI on the user's own hardware. It connects to local or cloud models including Ollama, OpenAI, Anthropic, or compatible services, and can be extended with Python. The project offers community-shared prompts, models, tools, and functions, and lists deployment options including on-premises or air-gapped setups. Installation can be done with a pip command.
Pack 3D Models helps edit, convert, generate, search, or organize images and visual assets.
PromptLayer is a prompt management platform for AI engineering teams. It offers prompt versioning, large language model evaluation tools, and AI agent observability via tracing, logs, and regression sets, plus a visual editor for prompt iteration and collaboration.
Rebyte is an execution layer for enterprise agents. It runs agents in the cloud with durable execution, tools such as browsers, files, and compute, and policy controls over models, skills, MCP servers, and network access. Execution traces record model steps, tool calls, errors, tokens, and cost. The Agent API is compatible with the official OpenAI client and is described as model agnostic.
Sketchfab is a platform for publishing, sharing, and discovering 3D content on web, mobile, AR, and VR. It offers a universal 3D/VR viewer that works in all browsers and operating systems without a plugin, and uses compression to deliver models. Users can embed and share 3D models on websites, forums, and social media. The site also offers free 3D models under Creative Commons licenses.
Stanford CS336: Language Modeling from Scratch is the official course website for a Stanford class offered in Spring 2026. The course walks students through the process of developing a language model, including data collection and cleaning for pre-training, transformer model construction, model training, and evaluation before deployment. The site provides logistics, schedule, assignments, and course materials.
The Models Resource supports game modding, engines, custom content, or fan-game development workflows.
tweetopic is a Python library for topic modelling of Tweets and other short texts. Its documentation site provides an API reference and a usage guide covering installation, the Dirichlet Multinomial Mixture Model, the Biterm Topic Model, pipelines, visualization and model persistence.
A guide by cweeper for importing custom 3D models into Minecraft and creating renders in Blender. It lists required tools including Minecraft Java Edition, ObjToSchematic.com, Jmc2Obj, Blender, and the MCprep Blender addon, and covers converting models to Minecraft formats, exporting worlds, and setting up Blender. It notes that a high-end graphics card affects render quality and duration.
