Search Results for "latency" - Page 3
Sort By:
Showing 661 open source projects for "latency"
View related business solutions-
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.
-
Paessler - Monitor Your Whole Network in MinutesWaiting weeks for a monitoring rollout isn't an option when infrastructure doesn't stop running. PRTG's auto-discovery scans your network and suggests from over 200 pre-configured sensor types, so you're watching servers, applications and devices within minutes, not after a multi-week deployment. Enterprise-strength monitoring, without the enterprise complexity. Start your free trial today.
-
1
Orpheus TTS
Towards Human-Sounding Speech
...The project ships both pretrained and finetuned English models, as well as a family of multilingual models released as a research preview, and includes data-processing scripts so users can train or finetune their own variants. Inference is provided through a Python package that uses vLLM under the hood for high-throughput, low-latency generation, including streaming examples that show how to generate audio chunks in real time. The maintainers provide Colab notebooks, a standardized prompting format, and one-click deployment via Baseten for production-grade, FP8/FP16 optimized inference with ~200 ms streaming latency. -
2
DeepSpeed
Deep learning optimization library: makes distributed training easy
...Achieve excellent system throughput and efficiently scale to thousands of GPUs 3. 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. ... -
3
Harper
Offline, privacy-first grammar checker
Harper is an offline, privacy-first English grammar checker written primarily in Rust. It analyzes writing locally, avoiding the latency and data exposure associated with cloud-only services. The engine is designed to lint documents in milliseconds while using a small memory footprint. It can run through WebAssembly in browsers and applications or through native command-line and language-server components. Official integrations support editors and tools including Visual Studio Code, Neovim, Helix, Emacs, Zed, and Obsidian. ... -
4
ThingsBoard Message Queue (TBMQ)
Open-source, scalable, and fault-tolerant MQTT broker
TBMQ is a lightweight message broker built to support ThingsBoard's IoT platform, focusing on telemetry data streaming and device communication. It uses Kafka-compatible APIs and is optimized for high-throughput messaging, device scalability, and low-latency delivery. TBMQ is ideal for IoT backends needing MQTT or Kafka-style pub/sub infrastructure. -
Build Data Resilience - Take the Assessment TodayIs 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.
-
5
gemma.cpp
lightweight, standalone C++ inference engine for Google's Gemma models
Gemma.cpp is a C++ implementation for running inference with Gemma models efficiently on CPUs and GPUs. Developed by Google, it allows running large language models (LLMs) like Gemma with minimal hardware, focusing on optimized performance and low latency. Gemma.cpp is intended for developers seeking to deploy LLMs in production environments without needing massive computational resources. -
6
Aerospike Node.js Client
Node.js client for the Aerospike database
Aerospike Node.js Client is the official Node.js driver for Aerospike, a high-performance NoSQL database optimized for real-time applications. It provides low-latency access to key-value stores and supports advanced data structures for AI, financial, and IoT applications. -
7
go-web-framework-benchmark
Go web framework benchmark
...It can add configurable handler delay to simulate business work such as database calls, cache access, disk writes, socket activity, or microservice calls. The benchmark uses wrk and scripts to collect throughput, latency, allocation, concurrency, pipelining, and CPU-bound results. It is useful for developers who want repeatable framework comparisons that better reflect end-to-end web request behavior. -
8
SlateDB
A cloud native embedded storage engine built on object storage
...Leveraging object storage allows SlateDB to provide bottomless storage capacity, high durability, and easy replication. The trade-off is that object storage has a higher latency and higher API cost than local disk. To mitigate high write API costs (PUTs), SlateDB batches writes. Rather than writing every put() call to object storage, MemTables are flushed periodically to object storage as a string-sorted table (SST). The flush interval is configurable. To mitigate write latency, SlateDB provides an async put method. -
9
darktable
darktable is an open source photography workflow application
darktable is an open source photography workflow application and non-destructive raw developer. A virtual lighttable and darkroom for photographers. It manages your digital negatives in a database, lets you view them through a zoomable lighttable and enables you to develop raw images, enhance them and export them on local or remote storage. -
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.
-
10
WebRTC Camera
Home Assistant custom component for real-time viewing
WebRTC Camera is a Home Assistant custom component for real-time camera viewing with very low latency. It uses go2rtc as its streaming server and can work with many camera sources and protocols. Supported inputs include RTSP, RTMP, HTTP streams, HomeKit cameras, USB cameras, ONVIF-style sources, and other go2rtc-compatible streams. It can output through WebRTC, RTSP, MSE, MP4, or MJPEG depending on browser, codec, and network conditions. -
11
CppServer
Fast and low latency asynchronous socket server & client C++ library
Ultra-fast and low latency asynchronous socket server & client C++ library with support TCP, SSL, UDP, HTTP, HTTPS, WebSocket protocols, and 10K connections problem solution. Cross platform (Linux, MacOS, Windows) Asynchronous communication. Supported CPU scalability designs: IO service per thread, thread pool. Supported transport protocols: TCP, SSL, UDP, UDP multicast. -
12
Ghostty
Ghostty is a fast, feature-rich, and cross-platform terminal emulator
Ghostty is a modern terminal emulator designed to deliver high performance, low latency, and a refined user experience for developers. It is built with a focus on speed and efficiency, leveraging modern rendering techniques to provide smooth text display and responsive interaction. The project emphasizes simplicity while maintaining advanced capabilities expected from professional terminal tools. It integrates with modern development workflows and supports customization for user preferences. ... -
13
Dapper
A simple object mapper for .Net
...Dapper allows you to execute raw SQL queries, map the results to objects, and execute stored procedures, among other things. It is available as a NuGet package. Dapper is lightweight and fast, making it an ideal choice for applications that require low latency and high performance. It is a simple yet powerful object mapping tool for any .NET language, such as C#, that enables developers to quickly and easily map query results from ADO.NET data readers to instances of business objects. It has excellent support for both asynchronous and synchronous database queries and batching multiple queries together into a single call. -
14
Kimi K2.5
Moonshot's most powerful AI model
...Based on a 1T-parameter Mixture-of-Experts (MoE) architecture with 32B activated parameters, it integrates advanced language reasoning with strong visual understanding. K2.5 supports both “Thinking” and “Instant” modes, enabling either deep step-by-step reasoning or low-latency responses depending on the task. Designed for agentic workflows, it features an Agent Swarm mechanism that decomposes complex problems into coordinated sub-agents executing in parallel. With a 256K context length and MoonViT vision encoder, the model excels across reasoning, coding, long-context comprehension, image, and video benchmarks. ... -
15
Hazelcast
Open-source distributed computation and storage platform
Hazelcast is a streaming and memory-first application platform for fast, stateful, data-intensive workloads on-premises, at the edge or as a fully managed cloud service. Hazelcast is a distributed computation and storage platform for consistently low-latency querying, aggregation and stateful computation against event streams and traditional data sources. It allows you to quickly build resource-efficient, real-time applications. You can deploy it at any scale from small edge devices to a large cluster of cloud instances. A cluster of Hazelcast nodes share both the data storage and computational load which can dynamically scale up and down. ... -
16
Langfuse
Open source LLM engineering platform: LLM Observability, metrics, etc.
Langfuse is a logging and analytics tool for large language model (LLM) applications, providing insights into usage, performance, and troubleshooting. -
17
LiteRT-LM
LiteRT-LM is Google's production-ready inference framework
...It supports CPU execution across major platforms and adds GPU or NPU acceleration where available. LiteRT-LM is especially relevant for developers building private, low-latency AI features on phones, laptops, Raspberry Pi-style devices, and other edge hardware. Its goal is to make modern language models usable in local applications with a consistent deployment stack. -
18
CFnew
Cloudflare Workers-based proxy deployment project
...It supports multiple proxy protocols and lets users manage paths, preferred IPs, and output formats through a more convenient interface. The project stores configuration through Cloudflare KV, which allows changes to take effect without redeploying the worker each time. It includes latency testing tools and automated format detection so different clients can receive compatible subscription output. cfnew is designed for users who need a flexible Cloudflare-backed node configuration system rather than a simple static link generator. Because it deals with proxy infrastructure, it should be used only in lawful environments and according to applicable service terms. -
19
8mb.local
Ffree local self hosted video compressor webui
8mb.local is a lightweight, self-hosted local network status dashboard and utilities hub designed to help users monitor devices and services connected to their home or small business network. The platform presents a simple yet informative web dashboard that dynamically updates with device statuses, IP addresses, and latency information, giving users a centralized view of network health without complex dashboards. It also includes basic tools such as ping monitoring, service reachability checks, and port scanning, enabling users to diagnose connection issues quickly and without external services. The emphasis is on minimalism and performance, so it runs efficiently on low-power devices like Raspberry Pis or small containers, making it ideal for home labs or edge deployments. 8mb.local can also notify users of offline devices or connection drops through configurable alerts, helping preempt outages before they become serious. -
20
Open Vision Agents by Stream
Build Vision Agents quickly with any model or video provider
...It focuses on combining video understanding models, such as YOLO and Roboflow based detectors, with real time large language models like OpenAI Realtime and Gemini Live to create interactive experiences. The framework uses Stream’s ultra low latency edge network so agents can join sessions quickly and maintain very low audio and video latency while processing frames and generating responses. Developers work with an agent abstraction that connects video edge providers, LLMs, and processors into pipelines, making it easier to orchestrate tasks like object detection, pose estimation, and conversational guidance. ... -
21
Pathway
Python ETL framework for stream processing, real-time analytics, LLM
Pathway is an open-source framework designed for building real-time data applications using reactive and declarative paradigms. It enables seamless integration of live data streams and structured data into analytical pipelines with minimal latency. Pathway is especially well-suited for scenarios like financial analytics, IoT, fraud detection, and logistics, where high-velocity and continuously changing data is the norm. Unlike traditional batch processing frameworks, Pathway continuously updates the results of your data logic as new events arrive, functioning more like a database that reacts in real-time. ... -
22
Moonshine Voice
Fast and accurate automatic speech recognition (ASR) for edge devices
...The project is designed to enable real-time voice applications such as live transcription, voice commands, and embedded speech interfaces without requiring heavy cloud infrastructure. Its architecture emphasizes low latency and flexible input handling, allowing audio streams of varying durations rather than relying on fixed processing windows. Moonshine supports multiple platforms including mobile, desktop, and embedded systems, and provides example projects to accelerate integration into real-world products. The toolkit also includes specialized model variants, including monolingual options that improve accuracy for specific languages. ... -
23
edgetunnel
edgetunnel 2.0 VLESS/Trojan
...It provides a streamlined way to host proxy endpoints without managing a full server stack, instead leveraging the edge network of Cloudflare for distribution and potential performance. Because it runs at the edge, latency can be minimized and deployment complexity simplified; users supply configuration variables (host, port, UUID, path) and the script handles mapping to technical protocols and subscription formatting. -
24
RunAnywhere
Production ready toolkit to run AI locally
...The toolkit allows developers to integrate language models, speech recognition, and voice synthesis capabilities into mobile or desktop applications while keeping all computation local. By running models entirely on device, the platform eliminates network latency and protects user data because information does not leave the device. The SDK supports popular open-source models such as Llama, Mistral, and Qwen, enabling developers to build AI-powered features such as chat interfaces and voice assistants with minimal external dependencies. It also includes integrated pipelines that combine speech-to-text, large language models, and text-to-speech into a complete conversational system. -
25
Napkin Math
Techniques and numbers for estimating system's performance
...It collects practical numbers, benchmark-style measurements, and mental models that help engineers make fast back-of-the-envelope calculations. The project is useful for questions like how much memory throughput matters, how long storage operations may take, what network latency to expect, or how expensive logging could become at high request volume. It treats these values as rounded numbers for reasoning rather than exact performance guarantees. The repository is especially useful for system design interviews, architecture planning, capacity estimation, and infrastructure cost discussions. It encourages engineers to practice estimation as a skill so they can reason about systems before building or benchmarking them.
