Showing 2402 open source projects for "zero"

View related business solutions
  • Host LLMs in Production With On-Demand GPUs Icon
    Host LLMs in Production With On-Demand GPUs

    NVIDIA L4 GPUs. 5-second cold starts. Scale to zero when idle.

    Deploy your model, get an endpoint, pay only for compute time. No GPU provisioning or infrastructure management required.
    Start Free
  • Custom VMs From 1 to 96 vCPUs With 99.95% Uptime Icon
    Custom VMs From 1 to 96 vCPUs With 99.95% Uptime

    General-purpose, compute-optimized, or GPU/TPU-accelerated. Built to your exact specs.

    Live migration and automatic failover keep workloads online through maintenance. One free e2-micro VM every month.
    Start Free
  • 1
    MOSS-TTS Family

    MOSS-TTS Family

    MOSS‑TTS Family open‑source speech and sound generation model

    ...The project is designed for complex real-world use cases where a single speech model may not be enough. Its flagship model focuses on stable long speech generation, multilingual and code-switched synthesis, pronunciation control, and zero-shot voice cloning. The broader family also includes dialogue generation, prompt-based voice creation, streaming voice-agent support, and a unified audio tokenizer. It is especially useful for developers building dubbing, podcasts, audiobooks, voice assistants, character voices, and creative audio tools.
    Downloads: 3 This Week
    Last Update:
    See Project
  • 2
    LuxTTS

    LuxTTS

    A high-quality rapid TTS voice cloning model

    ...It implements a lightweight architecture based on ZipVoice and optimized sampling techniques so that it can generate speech at speeds up to roughly 150 times real-time on a single GPU and faster than real-time on CPU, all while producing audio at high fidelity with 48 kHz quality. The project supports zero-shot voice cloning, meaning it can adapt to a reference speaker’s voice with minimal example data, enabling realistic and personalized synthetic speech. Intended for developers, hobbyists, and creators, the repository includes installation instructions, usage examples, and Python APIs that make it feasible to integrate the model in local workflows, web demos, or production systems. ...
    Downloads: 3 This Week
    Last Update:
    See Project
  • 3
    requests-cache

    requests-cache

    Persistent HTTP cache for python requests

    ...Use Cache-Control and other standard HTTP headers, define your own expiration schedule, and keep your cache clutter-free with backends that natively support TTL or any combination of strategies. Works out of the box with zero config, but with a robust set of features for configuring and extending the library to suit your needs.
    Downloads: 3 This Week
    Last Update:
    See Project
  • 4
    Zerocopy

    Zerocopy

    Zerocopy makes zero-cost memory manipulation effortless

    ...It also includes marker traits like KnownLayout, Immutable, and Unaligned to define type characteristics used in conversions. Complementing these traits are conversion macros that perform compile-time checks to ensure size and alignment safety, providing zero runtime overhead for unconditional casts.
    Downloads: 0 This Week
    Last Update:
    See Project
  • Ship Agents Faster Icon
    Ship Agents Faster

    Transform your applications and workflows into powerful agentic systems at global scale.

    Gemini Enterprise Agent Platform lets you rapidly build, scale, govern and optimize production-ready agents grounded in your organization's data. The platform enables developers to build custom or pre-built agents for virtually any use case. New customers get $300 in free credits.
    Start Free
  • 5
    KubeAI

    KubeAI

    Private Open AI on Kubernetes

    Get inferencing running on Kubernetes: LLMs, Embeddings, Speech-to-Text. KubeAI serves an OpenAI compatible HTTP API. Admins can configure ML models by using the Model Kubernetes Custom Resources. KubeAI can be thought of as a Model Operator (See Operator Pattern) that manages vLLM and Ollama servers.
    Downloads: 0 This Week
    Last Update:
    See Project
  • 6
    Moquette Project

    Moquette Project

    Java MQTT lightweight broker

    JVM lightweight MQTT broker for the Internet of Things. Simply embeddable in your IoT projects. Moquette aims to be a MQTT compliant broker. The broker supports QoS 0, QoS 1 and QoS 2. Its designed to be evented, uses Netty for the protocol encoding and decoding part.
    Downloads: 0 This Week
    Last Update:
    See Project
  • 7
    Text Generation Web UI

    Text Generation Web UI

    Oobabooga - The definitive Web UI for local AI, with powerful features

    ...Advanced chat features (send images, get audio responses with TTS). Very efficient text streaming. Parameter presets, 8-bit mode. Layers splitting across GPU(s), CPU, and disk. CPU mode, FlexGen, DeepSpeed ZeRO-3, API with streaming and without streaming. LLaMA model, including 4-bit GPTQ. RWKV model, LoRA (loading and training), Softprompts, and extensions.
    Downloads: 114 This Week
    Last Update:
    See Project
  • 8
    amqplib

    amqplib

    AMQP 0-9-1 library and client for Node.JS

    amqplib is a Node.js client library for the Advanced Message Queuing Protocol (AMQP), enabling applications to connect to AMQP brokers like RabbitMQ for messaging functionalities.
    Downloads: 4 This Week
    Last Update:
    See Project
  • 9
    MobileLLM

    MobileLLM

    MobileLLM Optimizing Sub-billion Parameter Language Models

    ...The framework integrates several architectural innovations—SwiGLU activation, deep and thin network design, embedding sharing, and grouped-query attention (GQA)—to achieve a superior trade-off between model size, inference speed, and accuracy. MobileLLM demonstrates remarkable performance, with the 125M and 350M variants outperforming previous state-of-the-art models of the same scale by up to 4.3% on zero-shot commonsense reasoning tasks.
    Downloads: 2 This Week
    Last Update:
    See Project
  • Build Data Resilience - Take the Assessment Today Icon
    Build Data Resilience - Take the Assessment Today

    Can you recover when it matters most? Take this quick assessment to identify gaps and build greater recovery confidence.

    Is your recovery strategy as strong as you think? Take this quick self-assessment to check your recovery readiness and gain tailored insights. In only 2 minutes, you'll learn where you fall on the recovery readiness scale.
    Take the Assessment
  • 10
    The Bitdefender disassembler

    The Bitdefender disassembler

    bddisasm is a fast, lightweight, x86/x64 instruction decoder

    ...It focuses on decoding machine instructions with high precision while providing detailed metadata about each instruction, including operands, access modes, CPU flags, and feature requirements. Unlike many disassemblers, bddisasm is built with zero dynamic memory allocation and no external dependencies, making it extremely portable and suitable for constrained environments such as kernels, hypervisors, and embedded systems. The project also includes a companion component called bdshemu, which provides a minimal instruction emulator capable of analyzing shellcode-like behavior in a controlled environment. ...
    Downloads: 1 This Week
    Last Update:
    See Project
  • 11
    ProxySQL

    ProxySQL

    A high-performance MySQL proxy

    ProxySQL is an open source, high performance, high availability, database protocol-aware proxy for MySQL. It was created due to a lack of high performance open source proxies, and is able to scale millions of connections across hundreds of thousands of backend servers, all while getting the freedom of being open source. ProxySQL provides end-to-end MySQL connection handling, real-time statistics and database traffic inspection. It's got failover detection, rich query rule definitions, and...
    Downloads: 1 This Week
    Last Update:
    See Project
  • 12
    Diom

    Diom

    Components platform for robust services

    ...It provides high-level APIs for service components such as caching, rate limiting, idempotency, queues, and other backend primitives. The project is designed to reduce boilerplate while keeping services robust, predictable, and production-friendly. It runs with zero runtime dependencies and uses its own storage, which makes deployment simpler than stitching together multiple external systems. Diom can operate as a single node or as a highly available cluster, depending on the service requirements. It is useful for backend developers who want reusable infrastructure components with clean APIs and fewer operational moving parts.
    Downloads: 0 This Week
    Last Update:
    See Project
  • 13
    EVE OS

    EVE OS

    EVE is Edge Virtualization Engine

    EVE is an open-source, secure, and container-optimized operating system for edge computing, developed by the LF Edge foundation. It enables enterprises to deploy and manage edge applications on heterogeneous hardware platforms using a zero-trust architecture. EVE supports virtual machines, containers, and unikernels while being hardware-agnostic, making it suitable for industrial gateways, edge clusters, and IoT devices. With its remote provisioning, lifecycle management, and built-in observability tools, EVE brings cloud-like infrastructure capabilities to the edge.
    Downloads: 0 This Week
    Last Update:
    See Project
  • 14
    Paralus

    Paralus

    All-in-one Kubernetes access manager

    Paralus is an open-source, zero-trust access management solution for Kubernetes. It provides secure access to Kubernetes clusters without the need for VPNs, streamlining operations and enhancing security. Paralus can be easily integrated with your pre-existing RBAC configuration and your SSO providers, or Identity Providers (IdP) that support OIDC (OpenID Connect).
    Downloads: 0 This Week
    Last Update:
    See Project
  • 15
    NetBird

    NetBird

    Connect your devices into a secure WireGuard-based overlay network

    NetBird is an open-source solution that builds a WireGuard®-based overlay network enabling seamless, encrypted peer-to-peer connectivity without the complexity of firewall rules, port forwarding, or centralized VPN gateways. It integrates access control features such as SSO and MFA for secure, policy-driven networking. Every machine in the network runs NetBird Agent (or Client) that manages WireGuard. Every agent connects to Management Service that holds network state, manages peer IPs, and...
    Downloads: 68 This Week
    Last Update:
    See Project
  • 16
    StartOS

    StartOS

    Linux server OS optimized for self-hosting

    StartOS is a sovereign, self-hosted operating system built by Start9 Labs to empower individuals with digital independence. Designed to run on personal servers, it provides a privacy-first interface for installing, managing, and running decentralized applications without needing technical expertise. StartOS includes services like Bitcoin nodes, messaging platforms, file hosting, and password managers, all running locally and without third-party control. With a user-friendly UI and strong...
    Downloads: 25 This Week
    Last Update:
    See Project
  • 17
    Realm Swift

    Realm Swift

    Realm is a mobile database: a replacement for Core Data & SQLite

    Realm is a fast, scalable alternative to SQLite with mobile to cloud data sync that makes building real-time, reactive mobile apps easy. Build data-rich apps without draining device resources with Realm's lazy loading and zero-copy architecture. The object-oriented data model lets developers work directly with native objects – no ORMs or DAOs are needed. Real-time mobile to cloud data sync makes it easy to build interactive features that keep data up-to-date across multiple devices, users, and the backend. Accelerate time-to-market with easy to learn, language-native APIs that simplify data access. ...
    Downloads: 31 This Week
    Last Update:
    See Project
  • 18
    Jimp

    Jimp

    An image processing library written entirely in JavaScript for Node

    An image processing library for Node written entirely in JavaScript, with zero native dependencies. If you're using this library with TypeScript the method of importing slightly differs from JavaScript. Instead of using require, you must import it with ES6 default import scheme. If you're using a web bundles (webpack, rollup, parcel) you can benefit from using the module build of jimp. Using the module build will allow your bundler to understand your code better and exclude things you aren't using. ...
    Downloads: 4 This Week
    Last Update:
    See Project
  • 19
    Sōzu

    Sōzu

    Sōzu HTTP reverse proxy, configurable at runtime, fast and safe

    ...There's now a shift in infrastructure to short-lived virtual machines and hundreds of new deployments per day, and the usual tools reach their limits. How do we reconcile a dynamic environment with availability guarantees? How can we get "zero downtime" deployments for critical services? SŌZU is a HTTP reverse proxy built in Rust, that can handle fine-grained configuration changes at runtime without reloads, and is designed to never ever stop. SŌZU receives and handles configuration changes at runtime and updates its internal configuration without restarts. You can update the configuration multiple times per second, and it will take care of lingering connections.
    Downloads: 81 This Week
    Last Update:
    See Project
  • 20
    TabFM

    TabFM

    scikit-learn compatible tabular foundation model

    TabFM is a tabular foundation model from Google Research for zero-shot classification and regression on structured datasets. It is designed to work with mixed numerical and categorical columns without requiring a custom training run for every new table. Instead of fitting model weights to the user’s dataset, TabFM uses in-context learning by reading training examples and test rows together at inference time.
    Downloads: 0 This Week
    Last Update:
    See Project
  • 21
    react-native-fast-tflite

    react-native-fast-tflite

    High-performance TensorFlow Lite library for React Native

    react-native-fast-tflite is a high-performance TensorFlow Lite library for React Native applications. It is built with Nitro Modules and uses the low-level C and C++ TensorFlow Lite core API for direct memory access. The library supports zero-copy ArrayBuffers, which helps reduce overhead when passing model inputs and outputs through React Native. It can load and swap TensorFlow Lite models at runtime, making it useful for apps that run multiple machine learning tasks. The project supports GPU-accelerated delegates such as CoreML, Metal, and OpenGL. It is especially useful for mobile computer vision, on-device inference, and VisionCamera-based workflows that need fast local model execution.
    Downloads: 0 This Week
    Last Update:
    See Project
  • 22
    NodePass

    NodePass

    TCP/UDP tunneling that delivers access across network restrictions

    NodePass is a lightweight enterprise-grade TCP and UDP tunneling solution for handling complex network access scenarios. It uses an all-in-one architecture that separates control and data channels while keeping deployment simple for administrators. The project supports zero-configuration setup, connection pooling, protocol conversion, and tiered TLS encryption. It is designed for DevOps professionals and system administrators who need reliable forwarding across restricted, segmented, or operationally complex networks. NodePass can be used to expose internal services, bridge environments, manage tunnels, and create fast network paths through pre-established connections. ...
    Downloads: 0 This Week
    Last Update:
    See Project
  • 23
    GitNexus

    GitNexus

    Zero-Server Code Intelligence Engine

    GitNexus is a zero-server code intelligence engine that builds an interactive knowledge graph of a codebase entirely within the user’s browser. The tool allows developers to drop in a GitHub repository or ZIP archive and automatically generate a relational map of files, dependencies, and structural relationships. Its core concept centers on precomputed relational intelligence, enabling AI systems to retrieve comprehensive context with minimal queries.
    Downloads: 0 This Week
    Last Update:
    See Project
  • 24
    Anoma

    Anoma

    Reference implementation of Anoma

    ...Unlike traditional account-based or UTXO models, Anoma introduces intents as the fundamental units of interaction, allowing participants to express what they want without specifying how it must be achieved. The protocol is designed with privacy, interoperability, and decentralization at its core, and is built using Rust and zero-knowledge cryptography tools. It aims to serve decentralized finance, identity, and coordination systems in a novel and user-centric way.
    Downloads: 0 This Week
    Last Update:
    See Project
  • 25
    JuliaWorkshop

    JuliaWorkshop

    Intensive Julia workshop that takes you from zero to hero

    ...Nevertheless, it assumes only rudimentary programming familiarity and does explain concepts that go beyond the basics. The goal of the workshop is to take you from zero to hero (regarding Julia): even if you know nothing about Julia, by the end you should be able to use it like a pro. The material has been updated during July-December 2023 to Julia v1.9+ and the corresponding latest stable versions of used packages
    Downloads: 0 This Week
    Last Update:
    See Project