Search Results for "z-push"
Sort By:
Showing 67 open source projects for "z-push"
View related business solutions-
Host LLMs in Production With On-Demand GPUsDeploy your model, get an endpoint, pay only for compute time. No GPU provisioning or infrastructure management required.
-
MongoDB Atlas runs apps anywhereMongoDB Atlas gives you the freedom to build and run modern applications anywhere—across AWS, Azure, and Google Cloud. With global availability in over 115 regions, Atlas lets you deploy close to your users, meet compliance needs, and scale with confidence across any geography.
-
1
Z-Image
Image generation model with single-stream diffusion transformer
...The project includes several variants: Z-Image-Turbo, a distilled version optimized for speed and low resource consumption; Z-Image-Base, the full-capacity foundation model; and Z-Image-Edit, fine-tuned for image editing tasks. Despite its compact size, Z-Image produces outputs that closely rival those from much larger models — including strong rendering of bilingual (English and Chinese) text inside images, accurate prompt adherence, and good layout and composition. -
2
GladiaFlow
A desktop app for real-time voice dictation
...Partial and final results arrive in real time, then the app cleans punctuation, capitalization, and duplicate text before pasting the transcript into the active application. Users can choose push-to-talk or toggle activation and configure languages, code switching, vocabulary, and pronunciations. Dictation history, settings, and statistics are stored locally, while audio is not saved by the app. It supports macOS and Windows and uses a compact overlay and system tray controls to stay unobtrusive. -
3
Omnara
Talk to Your AI Agents from Anywhere
Omnara is an open-source agent control platform that empowers developers to turn autonomous AI tools (e.g., Claude Code, Cursor, GitHub Copilot) into collaborative teammates by offering real-time dashboards, push notifications, and remote guidance across terminals, web, and mobile. Omnara transforms your AI agents (Claude Code, Codex CLI, n8n, and more) from silent workers into communicative teammates. Get real-time visibility into what your agents are doing, and respond to their questions instantly from a single dashboard on web and mobile. ... -
4
Gollama
Go manage your Ollama models
Gollama is a macOS and Linux tool for managing Ollama models through an interactive terminal-based interface. It provides a TUI that lets users list, inspect, sort, filter, edit, run, unload, copy, rename, delete, and push models from one place rather than relying entirely on manual command-line workflows. The project is aimed at developers and local AI users who frequently work with multiple Ollama models and want a more efficient operational layer for everyday maintenance. Beyond standard model management, Gollama can display metadata such as size, quantization level, model family, and modification date, which helps users compare models quickly. ... -
Build Securely on Azure with Proven FrameworksMoving to the cloud brings new challenges. How can you manage a larger attack surface while ensuring great network performance? Turn to Fortinet’s Tested Reference Architectures, blueprints for designing and securing cloud environments built by cybersecurity experts. Learn more and explore use cases in this white paper.
-
5
Happy Coder
Mobile and Web client for Codex and Claude Code, with realtime voice
...You can start a coding session locally through the Happy CLI or connect from a phone or browser, allowing developers to inspect, interact with, and guide the AI as it generates, tests, or explains code. The project includes components like a dedicated backend server for encrypted sync, a rich front-end experience across web and native apps, and support for push notifications when your coding agent encounters permission requests or errors. Happy prioritizes security with end-to-end encryption so your code and interactions remain private and auditable. -
6
stable-diffusion.cpp
Diffusion model(SD,Flux,Wan,Qwen Image,Z-Image,...) inference
stable-diffusion.cpp is a lightweight, high-performance implementation of Stable Diffusion and related generative models written entirely in portable C/C++, designed to run on virtually any device without heavy dependencies. It enables text-to-image and image-to-image generation, supports a growing set of models like SD1.x, SD2.x, SDXL, SD-Turbo, Qwen Image, and more, and is continually updated with support for cutting-edge model variants including video and image editing models. The project... -
7
Onlook
The Cursor for Designers • An Open-Source AI-First Design tool
Seamlessly integrate with any website or web app running on React + TailwindCSS, and make live edits directly in the browser DOM. Customize your design, control your codebase, and push changes your changes without compromise. Link Onlook to your React project with just one command. Run this command on your project's root folder to get set up in seconds. Onlook writes reliable code you can trust, exactly where it needs to go. Adjust layouts, change colors, modify text, and more. -
8
Handy STT
A free, open source, and extensible speech-to-text application
Handy is a free, open-source, offline speech-to-text application built for privacy, accessibility, and extensibility. Developed using Tauri (Rust + React/TypeScript), it runs natively across Windows, macOS, and Linux while performing local speech recognition without sending any audio to cloud servers. Handy allows users to start transcription instantly using a configurable keyboard shortcut—press to record, release to transcribe—and automatically pastes the resulting text into any active... -
9
VoiceInk
The best open-source alternative to Superwhisper & Wispr Flow
...Modes apply different models, prompts, context settings, and shortcuts according to the active app or website. A personal dictionary improves recognition of names, technical terms, and recurring phrases, while configurable global shortcuts support toggle and push-to-talk recording. Context-aware tools can use selected text, clipboard content, or visible screen text to improve the final output. The app is written in Swift, supports macOS 14.4 or later, can be installed through Homebrew, and is available under the GPLv3 license. -
Custom VMs From 1 to 96 vCPUs With 99.95% UptimeLive migration and automatic failover keep workloads online through maintenance. One free e2-micro VM every month.
-
10
TRELLIS.2
Native and Compact Structured Latents for 3D Generation
TRELLIS.2 is a cutting-edge open-source model and codebase for high-fidelity 3D asset generation from 2D images, developed to push forward the state of the art in image-to-3D generation. At its core is a novel sparse voxel structure called O-Voxel that jointly encodes both geometry and surface appearance, enabling reconstruction and generation of complex 3D shapes with arbitrary topology, open surfaces, and physically based rendering (PBR) textures. The system leverages a large 4-billion-parameter architecture combining sparse 3D variational autoencoders with flow-matching transformers to produce fully textured 3D models at resolutions up to 1536³ voxels. ... -
11
Unlimited OCR Works
Welcome the Era of One-shot Long-horizon Parsing
Unlimited-OCR is an OCR and document parsing model project focused on one-shot long-horizon parsing. It is designed to push OCR beyond short, isolated image recognition and into longer document understanding workflows. The project supports single-image parsing as well as multi-page and PDF-style parsing by converting pages into images. It provides inference paths for Hugging Face Transformers, vLLM, and SGLang, which gives users several deployment options. -
12
GLM-5
From Vibe Coding to Agentic Engineering
GLM-5 is a next-generation open-source large language model (LLM) developed by the Z .ai team under the zai-org organization that pushes the boundaries of reasoning, coding, and long-horizon agentic intelligence. Building on earlier GLM series models, GLM-5 dramatically scales the parameter count (to roughly 744 billion) and expands pre-training data to significantly improve performance on complex tasks such as multi-step reasoning, software engineering workflows, and agent orchestration compared to its predecessors like GLM-4.5. ... -
13
HunyuanVideo
HunyuanVideo: A Systematic Framework For Large Video Generation Model
HunyuanVideo is a cutting-edge framework designed for large-scale video generation, leveraging advanced AI techniques to synthesize videos from various inputs. It is implemented in PyTorch, providing pre-trained model weights and inference code for efficient deployment. The framework aims to push the boundaries of video generation quality, incorporating multiple innovative approaches to improve the realism and coherence of the generated content. Release of FP8 model weights to reduce GPU memory usage / improve efficiency. Parallel inference code to speed up sampling, utilities and tests included. -
14
Kimi K2
Kimi K2 is the large language model series developed by Moonshot AI
Kimi K2 is Moonshot AI’s advanced open-source large language model built on a scalable Mixture-of-Experts (MoE) architecture that combines a trillion total parameters with a subset of ~32 billion active parameters to deliver powerful and efficient performance on diverse tasks. It was trained on an enormous corpus of over 15.5 trillion tokens to push frontier capabilities in coding, reasoning, and general agentic tasks while addressing training stability through novel optimizer and architecture design strategies. The model family includes variants like a foundational base model that researchers can fine-tune for specific use cases and an instruct-optimized variant primed for general-purpose chat and agent-style interactions, offering flexibility for both experimentation and deployment. ... -
15
DeepSeek Coder V2
DeepSeek-Coder-V2: Breaking the Barrier of Closed-Source Models
DeepSeek-Coder-V2 is the version-2 iteration of DeepSeek’s code generation models, refining the original DeepSeek-Coder line with improved architecture, training strategies, and benchmark performance. While the V1 models already targeted strong code understanding and generation, V2 appears to push further in both multilingual support and reasoning in code, likely via architectural enhancements or additional training objectives. The repository provides updated model weights, evaluation results on benchmarks (e.g. HumanEval, MultiPL-E, APPS), and new inference/serving scripts. Compared to the original, DeepSeek-Coder-V2 likely incorporates improved context management, caching strategies, or enhanced infilling capabilities. ... -
16
MetaClaw
Just talk to your agent
...It is likely designed for experimentation with next-generation agent systems that combine planning, learning, and execution. Overall, MetaClaw represents a research-driven effort to push the boundaries of intelligent agent coordination and adaptability. -
17
openpilot
Open source driver assistance system
openpilot is an open-source driver assistance system designed to improve upon the existing driver assistance of most modern cars today. openpilot gives you Tesla Autopilot-like functionality with functions like Adaptive Cruise Control (ACC), Automated Lane Centering (ALC), Forward Collision Warning (FCW) and Lane Departure Warning (LDW). All these with just a push of a button. openpilot also includes a camera-based driver monitoring feature that alerts distracted and asleep drivers while it is engaged. openpilot supports over 85 car makes and models of various years, and the list of supported vehicles continues to grow, including community-supported cars and features. Thousands of drivers have trusted openpilot and have rediscovered the joy of driving again with openpilot. ... -
18
Ant Design X
Experimental Ant Design extensions for advanced UI patterns
...It often includes higher-level abstractions and enhanced UI capabilities that are not yet part of the stable design system. It reflects ongoing innovation, with features that may evolve rapidly based on feedback and real-world usage. Overall, it is intended for developers who want to push the boundaries of Ant Design and explore cutting-edge UI solutions. -
19
Polyglot
Cross-platform AI language practice app
Polyglot is a cross platform AI language practice application that runs as a desktop app and also offers a web version. It is built around conversational large language models and Azure based text to speech services, turning them into an interactive environment for speaking practice in multiple languages. Users can define custom AI personas, choose languages, and configure their own OpenAI and Azure keys so they retain control over which backends they use. The app supports speech recognition... -
20
FLUX.2
Official inference repo for FLUX.2 models
...The model offers both text-to-image generation and powerful image editing, including editing of multiple reference images, with fidelity, consistency, and realism that push the limits of what open-source generative models have achieved. It supports high-resolution output (up to ~4 megapixels), which allows for photography-quality images, detailed product shots, infographics or UI mockups rather than just low-resolution drafts. FLUX.2 is built with a modern architecture (a flow-matching transformer + a revamped VAE + a strong vision-language encoder), enabling strong prompt adherence, correct rendering of text/typography in images, reliable lighting, layout, and physical realism, and consistent style/character/product identity across multiple generations or edits. -
21
Roomote
Your own cloud coding agent
...Users can assign work from Slack, Teams, Telegram, Discord, or its web interface. Each task runs in an isolated sandbox where the agent clones the repository, edits code, runs tests, and can capture screenshots. It can then push a branch and open a pull request with the resulting diff and preview information. Roomote supports multiple source-control platforms, model providers, and sandbox backends. It can be self-hosted or deployed as a managed instance, giving teams control over their infrastructure and credentials. -
22
OpenLess
AI-polished text appears at your cursor in any app
OpenLess is an open-source voice input application for macOS and Windows that turns spoken ideas into polished text at the current cursor position. Users press a global hotkey, speak naturally, and release the key to receive cleaned-up text inside apps such as ChatGPT, Claude, Cursor, Notion, email clients, or chat boxes. Unlike basic dictation tools, it is designed to restructure loose speech into more useful writing, especially AI prompts with clearer context and constraints. The app... -
23
Xianyu Intelligent Monitor Bot
AI tool for real-time monitoring and analysis of Goofish listings
ai-goofish-monitor is an open source automation tool designed to monitor listings on the Goofish second-hand marketplace and analyze them using artificial intelligence. It combines browser automation with AI-based analysis to automatically search, collect, and evaluate newly posted items that match a user’s purchase criteria. It uses Playwright to simulate real user interactions with the marketplace, allowing the system to retrieve product data and track updates in near real time.... -
24
SageMaker Training Toolkit
Train machine learning models within Docker containers
Train machine learning models within a Docker container using Amazon SageMaker. Amazon SageMaker is a fully managed service for data science and machine learning (ML) workflows. You can use Amazon SageMaker to simplify the process of building, training, and deploying ML models. To train a model, you can include your training script and dependencies in a Docker container that runs your training code. A container provides an effectively isolated environment, ensuring a consistent runtime and... -
25
H2O LLM Studio
Framework and no-code GUI for fine-tuning LLMs
...First, upload your dataset and then start training your model. Start by creating an experiment. You can then monitor and manage your experiment, compare experiments, or push the model to Hugging Face to share it with the community.
