Search Results for "model-builder" - Page 54
Sort By:
Showing 6997 open source projects for "model-builder"
View related business solutions-
$300 Free Credits for Your Google Cloud ProjectsLaunch your next project with $300 in free Google Cloud credits—no strings attached. Test, build, and deploy without risk. Use your credits across the entire Google Cloud platform to find what works best for your needs. After your credits are used, continue with always-free tier services. Only pay when you're ready to scale. Sign up in minutes and start exploring.
-
Build Agents and Models on One PlatformGemini Enterprise Agent Platform is Google Cloud's comprehensive platform for developers to build, scale, govern, and optimize agents and models. Choose from Google's most advanced models and third-party models like Anthropic's Claude Model Family.
-
1
Nitro Modules
Insanely fast native C++, Swift or Kotlin modules
Nitro is a React Native native-module system for building very fast C++, Swift, and Kotlin modules with statically compiled bindings to JSI. It is designed to reduce runtime overhead by generating type converters ahead of time instead of relying on dynamic lookups. The project consists of the core react-native-nitro-modules library and the optional nitrogen code generator for module authors. Developers define interfaces in TypeScript and implement the native behavior in C++, Swift, Kotlin,... -
2
Microsoft eXecution Container (MXC)
Policy-driven, layered isolation and containment
Microsoft eXecution Containers, or MXC, is a sandboxed code execution system for running untrusted code across Windows, Linux, and macOS. It is designed for model outputs, plugins, tools, and other code that needs controlled execution boundaries. The project provides a unified JSON configuration schema and a TypeScript SDK while supporting multiple containment backends. Its backends include process containers, Windows Sandbox, LXC, Bubblewrap, Seatbelt, microVM-based options, Hyperlight, IsolationSession, and WSL-related containment. ... -
3
DBX
15MB, lightweight, cross-platform database client
...It includes a query editor with syntax highlighting, autocomplete, formatting, diagnostics, saved snippets, query history, and tab restoration. dbx also includes an AI SQL assistant that can generate, explain, optimize, and help fix SQL through compatible model providers. Its main value is combining broad database coverage, a modern query workflow, and lightweight deployment across desktop and self-hosted environments. -
4
Peinture
A general-purpose AI image generation framework that supports HF
Peinture is a sleek, dark-themed web application that brings AI-powered image generation to artists, designers, and casual creators through a modern interface built with React, TypeScript, and Tailwind CSS. Instead of tying users to a single service, Peinture integrates multiple backend providers, including Hugging Face, Gitee AI, Model Scope, and others, so you can switch between models or extend support to custom endpoints — giving you flexibility over where and how your images are generated. It not only generates images from prompts but also includes tools to edit those images after creation, with features like selection tools and reference image support that let you refine artwork in place. ... -
Stop Cyber Threats with VM-Series Next-Gen Firewall on AzureGain integrated visibility across all traffic in a single pass. Deploy Palo Alto Networks VM-Series to determine application identity and content while automating security policy updates via rich APIs.
-
5
ProxyPal
A desktop app that lets you use your AI subscriptions
ProxyPal is a desktop application that lets developers unify and manage multiple AI model subscriptions (such as Claude, ChatGPT, Gemini, and GitHub Copilot) with any coding tool by acting as a local proxy and connection manager. By wrapping a CLI-based proxy API with an intuitive graphical interface, ProxyPal bridges your paid AI services into environments that don’t natively support them, allowing tools like text editors, terminals, and IDE plugins to route requests through a centralized proxy endpoint. ... -
6
The Magic of CSS
A CSS course to turn you into a magician
Magic of CSS is an open source educational project by Adam Schwartz that explores advanced CSS concepts through practical lessons. It is structured as a series of chapters that cover topics like the box model, layouts, positioning, typography, and animations. The repository is designed to go beyond basic CSS tutorials, teaching how to harness the language for complex, responsive, and visually appealing designs. Each lesson is supported by examples and code that demonstrate real-world use cases. The project emphasizes both the technical and creative potential of CSS, showing how small details can greatly improve user experience. ... -
7
Stagehand
An AI web browsing framework focused on simplicity and extensibility
...The goal of Stagehand is to provide a lightweight, configurable framework, without overly complex abstractions, as well as modular support for different models and model providers. It's not going to order you a pizza, but it will help you reliably automate the web. Each Stagehand function takes in an atomic instruction, such as act("click the login button") or extract("find the red shoes"), generates the appropriate Playwright code to accomplish that instruction, and executes it. -
8
DeepSpeed
Deep learning optimization library: makes distributed training easy
...Train/Inference on resource constrained GPU systems 4. Achieve unprecedented low latency and high throughput for inference 5. Achieve extreme compression for an unparalleled inference latency and model size reduction with low costs DeepSpeed offers a confluence of system innovations, that has made large scale DL training effective, and efficient, greatly improved ease of use, and redefined the DL training landscape in terms of scale that is possible. These innovations such as ZeRO, 3D-Parallelism, DeepSpeed-MoE, ZeRO-Infinity, etc. fall under the training pillar. -
9
ChatTTS_colab
One-click deployment (including offline integration package)
...The project also implements multi-speaker or role-based reading, letting users assign different voices to different characters in a script and even use a large language model to generate that script in one step. -
Enterprise-grade ITSM, for every businessFreshservice is an intuitive, AI-powered platform that helps IT, operations, and business teams deliver exceptional service without the usual complexity. Automate repetitive tasks, resolve issues faster, and provide seamless support across the organization. From managing incidents and assets to driving smarter decisions, Freshservice makes it easy to stay efficient and scale with confidence.
-
10
Junie
An AI coding agent by JetBrains that ships code from your terminal
...It allows users to give development tasks in natural language, such as fixing bugs, implementing features, reviewing pull requests, or improving tests. Junie is LLM-agnostic, meaning it can work with different model providers, including JetBrains authentication, Junie API keys, or bring-your-own-key options. The tool integrates with real-world development workflows and can assist across local projects, repositories, and automated GitHub processes. Developers can use Junie through multiple release channels, including stable, EAP, nightly, and experimental builds. ... -
11
Intent UI
Intent UI is a chill set of React components
Intent UI is a modern React component library focused on accessibility, customization, and developer ownership, built on top of React Aria Components and styled with Tailwind CSS. It follows a copy-and-paste philosophy similar to shadcn/ui, allowing developers to directly integrate and modify components within their own codebases instead of relying on rigid dependencies. The library emphasizes accessible design by leveraging ARIA standards and best practices, ensuring that components work... -
12
promptmap2
A security scanner for custom LLM applications
promptmap is an automated security scanner for custom LLM applications that focuses on prompt injection and related attack classes. The project supports both white-box and black-box testing, which means it can either run tests directly against a known model and system prompt configuration or attack an external HTTP endpoint without internal access. Its scanning workflow uses a dual-LLM architecture in which one model acts as the target being tested and another acts as a controller that evaluates whether an attack succeeded. The repository emphasizes broad coverage, including test rules for prompt stealing, jailbreaks, harmful content generation, hate-related outputs, social bias, and distraction attacks. ... -
13
React Native AI
Full stack framework for building cross-platform mobile AI apps
...It supports real-time streaming responses from multiple AI providers and enables developers to build chat interfaces, AI-driven image generation tools, and natural language features within mobile apps. The framework includes backend components such as an Express-based server proxy that handles authentication and API communication with model providers. Developers can also integrate multiple models and services through a unified interface, making it easier to experiment with different AI capabilities. Built-in theming and UI templates allow developers to quickly create polished interfaces for AI chat and generative features. -
14
E2B Cookbook
Examples of using E2B
...E2B itself provides secure Linux-based sandboxes that enable AI systems to safely run generated code and interact with real computing resources without compromising the host environment. The cookbook organizes examples across multiple frameworks and model providers, allowing developers to experiment with integrations involving models from OpenAI, Anthropic, and other ecosystems. -
15
MusicGPT
Generate music based on natural language prompts using LLMs
...The application currently integrates with models such as MusicGen and is designed to support additional models transparently in the future. In addition to a command-line interface, the project includes a web-based interface that enables conversational interaction with the AI model. -
16
Slack MCP Server
The most powerful MCP Slack Server with no permission requirements
Slack MCP Server is an open-source server implementation that connects Slack workspaces to AI systems through the Model Context Protocol (MCP). MCP is a standardized protocol that allows large language models and AI agents to securely interact with external tools and data sources such as messaging platforms, databases, or file systems. The slack-mcp-server acts as an intermediary layer that exposes Slack data and messaging functionality to AI clients while enforcing access rules and communication standards. ... -
17
autoresearch
AI agents autonomously run and improve ML experiments overnight
...Designed to run on a single GPU, it keeps the research loop minimal and self-contained to make autonomous experimentation practical. Over time, the agent logs experiments, evaluates improvements, and gradually evolves the model through automated trial-and-error. -
18
handy-ollama
Implement CPU from scratch and play with large model deployments
...A key focus of the project is enabling users to run large models even without GPUs by leveraging optimized CPU-based inference pipelines. The project includes step-by-step guides that walk learners through tasks such as installing Ollama, managing local models, calling model APIs, and building simple AI applications on top of locally hosted models. Through hands-on exercises and practical examples, the tutorial demonstrates how developers can create applications like chat assistants or retrieval systems using locally deployed models. -
19
second-brain-ai-assistant-course
Learn to build your Second Brain AI assistant with LLMs
...Through a series of modules, the project explains how to design data pipelines, build retrieval-augmented generation systems, and implement agent-based reasoning workflows. The course also introduces practical techniques such as dataset generation, model fine-tuning, and deployment strategies for AI applications. Learners build a full system capable of retrieving information from stored resources and generating responses based on that data. -
20
Anthony Fu's Skills
Anthony Fu's curated collection of agent skills
...By offloading detailed task patterns into discrete skill modules, developers can greatly extend what coding agents can do without retraining the underlying language model itself. The project serves as a curated registry of utilities that save time, standardize best practices, and encode expertise across domains, while still being easy to customize or extend. Contributors can add new skills following a common format, meaning the repository grows organically with community-driven capabilities. -
21
Valdi
Cross-platform UI framework that delivers native performance
Valdi is a cross-platform UI framework built to deliver native runtime performance without giving up the fast iteration loop that teams want from higher-level frameworks. You write your UI once in declarative TypeScript (TSX-style components), and Valdi compiles those components directly into platform-native views for iOS, Android, and macOS, instead of relying on web views or a JavaScript bridge. Its design focuses heavily on performance characteristics that matter in real apps, like... -
22
AutoAgent
AutoAgent: Fully-Automated and Zero-Code LLM Agent Framework
...It also describes resource orchestration and iterative self-improvement behaviors, including controlled code generation for building tools and agent capabilities when needed. The project is designed to work with multiple LLM providers and model endpoints, allowing users to choose different backends by setting environment variables and model identifiers. -
23
kMCP
Kubernetes Controller for building, testing and deploying MCP servers
KMCP is a companion toolchain for building, testing, and deploying MCP servers with a workflow that spans local development through Kubernetes production deployments. It includes a CLI for day-to-day development tasks like scaffolding new MCP projects, managing tools, building container images, and running an MCP server locally for validation. For cluster operations, it includes a Kubernetes controller that manages MCP server lifecycles using a dedicated Custom Resource Definition (CRD),... -
24
GLM-TTS
Controllable & emotion-expressive zero-shot TTS
GLM-TTS is an advanced text-to-speech synthesis system built on large language model technologies that focuses on producing high-quality, expressive, and controllable spoken output, including features like emotion modulation and zero-shot voice cloning. It uses a two-stage architecture where a generative LLM first converts text into intermediate speech token sequences and then a Flow-based neural model converts those tokens into natural audio waveforms, enabling rich prosody and voice character even for unseen speakers. ... -
25
Proton Mail Bridge
Proton Mail Bridge application
...It provides a seamless integration layer for users who need offline support, familiar local client workflows, or tighter integration with desktop tools while preserving Proton’s zero-access encryption model. The Bridge app continues running even when its GUI is closed so that mail clients can remain connected and synchronized, and it supports automatic startup and robust credential handling via secure storage.
