Find trending repositories by name or description.
基于 DeepSeek Harness 插件机制构建的远程访问方案，通过低延迟、端到端加密的 P2P 网络，支持使用 PC、移动端 和 Web 随时访问本地设备上的DSH 、CodeX、Cursor、Claude Code等工作区。 (Built on DeepSeek Harness plugins, this low-latency, end-to-end encrypted P2P solution lets PC, mobile, and web clients access local DSH, Codex, Cursor, and Claude Code workspaces.)
The most customisable and low-latency cross platform/shell prompt renderer
Mumble is an open-source, low-latency, high quality voice chat software.
Bidirectional and low-latency communication for every platform
Nornicdb is a distributed low-latency, Graph+Vector, Temporal MVCC with all sub-ms HNSW search, graph traversal, and writes. Using Neo4j Bolt/Cypher and qdrant's gRPC means you can switch with no changes while adding intelligent features like schemas, managed embeddings, reranking+llm, GPU accel, Auto-TLP, Policy-based Memory Decay, and MCP server.
Low-latency local speech-to-speech voice assistant with Ming-3.0-audio-tiny on AMD and Nvidia GPUs. Easy setup on Windows and Linux
An open-source Android Active Noise Cancellation (ANC) engine. Leveraging low-latency DSP to neutralize environmental hums and help you reclaim your quiet.
Petal: low-latency, multi-window screensharing for macOS and Windows. Every shared window becomes a real native window on every participant's desktop.
Apache Pinot: a real-time analytics database for low-latency SQL and vector search, serving user-facing and agent-facing applications
Low-latency machine code generation
PKShortVideo is a high-performance iOS short video engine optimized for chat interfaces. Built on top of AVFoundation and a hardware-accelerated legacy GPUImage/OpenGL ES path, it delivers low-latency recording and silky-smooth video playback with minimal resource overhead.
Ultra-low-latency asynchronous C++17 logging and metrics library for performance-critical applications
Lightweight low-latency RTSP client library for Android
Low-latency hardware-accelerated WebRTC video streaming and remote control for Raspberry Pi & NVIDIA Jetson
A robust, efficient, low-latency speech-to-text library with advanced voice activity detection, wake word activation and instant transcription.
Infinity is a high-throughput, low-latency serving engine for text-embeddings, reranking models, clip, clap and colpali
ASIO driver development for Windows
Secure Low-Latency Interactive Messaging
ArcticInference: vLLM plugin for high-throughput, low-latency inference
A high-performance, thread-safe limit order book implementation written in Rust. This project provides a comprehensive order matching engine designed for low-latency trading systems, with a focus on concurrent access patterns and lock-free data structures.
Low-latency AI engine for mobile devices & wearables
Native CarPlay Ultra & Android Auto head unit for Linux and macOS, built in Rust + Slint. Multi-session wired + wireless, zero-copy hardware video, low-latency audio.
Tile-Based Runtime for Ultra-Low-Latency LLM Inference
Apollo-derived Linux game-streaming host with low-latency virtual displays via Hermes-KMS (zero-copy DRM/KMS), with EVDI still supported. Moonlight/Artemis/Hestia compatible. Official Discord https://discord.gg/M5dYFuhjqP
Direct connection engine for Interactive Brokers in Rust. No Java Gateway required. Ultra-low-latency orders and market data. Rust + Python (PyO3).
Universal algorithmic trading bot and multi-broker execution framework. Automated trading bot for Pocket Option, Quotex, Polymarket, Robinhood, MT5, Forex, Delta Exchange, and Crypto markets. Features unified WebSocket/REST API connectors, cross-platform order routing, and low-latency strategy execution.
Cross-platform desktop app for interactive full-band music notation — built-in VST hosting, amp modeling (NAM), and low-latency audio I/O
Software-only version of the USBridge ecosystem for secure, low-latency remote desktop control and peer-to-peer networking.
A high-performance ASCII video rendering engine featuring real-time WebSocket binary streaming and an isolated compiler for serverless static generation. Built for low-latency 30 FPS playback on HTML5 Canvas.
DeepSeek V4 Pro: Advanced AI desktop app. Features: 1.6T MoE architecture, 1M token context window, Engram memory. Pro coding agent, Think Mode (High/Max), repo-level reasoning, complex bug fixing. Real-time web search, local API key storage, cross-file analysis, low-latency streaming interface.