Sign in

Repository Index

132,241 visible repositories in the index

Tags: All Tags
Tags

A repository shows when it has any selected Tag.

Filters (1)

Filters

Clear all filters

1,561–1,584 of 1,756 · Most stars

Private, provider-neutral context compression for LLMs. Reversibly compress schemas and logs inside your perimeter with zero third-party calls.

  • cli
  • compression
  • context-window
  • cost-reduction

whatRust — a lightweight, open-source WhatsApp Web desktop client built with Rust + Tauri. A low-RAM alternative to the official WhatsApp Desktop for Linux, Windows, and macOS.

  • cross-platform
  • desktop-app
  • electron-alternative
  • lightweight

The mod manager and modding toolkit for Dota 2: 1,600+ mods from the D2PFX catalog in one click, an item builder with a live 3D preview, and a Workshop for effects, the HUD, colours and the map. Windows and Linux, no account, no telemetry. [email protected]

  • dota2
  • dota2-mods
  • mod-manager
  • mods

Self-hosted artifact repository manager written in Rust. Hosts, proxies and groups 30+ formats: Docker/OCI, Maven, npm, PyPI, Cargo, Go, Helm, NuGet, Hugging Face, Terraform and more. PostgreSQL for metadata, blob stores on disk or S3. An open-source alternative to Nexus and Artifactory.

  • air-gapped
  • artifact-registry
  • artifactory-alternative
  • cargo-registry

Free offline AI voice studio for Windows — text-to-speech with cloned and built-in voices, and speech recognition with speakers. Russian done right. 100% local, one native .exe, zero Python.

  • asr
  • local-ai
  • offline
  • portable

Local-first, privacy-focused open-source banking app for macOS and iOS (FinTS/HBCI, PSD2, SEPA) built with Rust, SwiftUI & SQLCipher

Cross-platform UI framework for Rust: declarative Rust UI with signals and React-like components (rsx!, hooks), or compiled XAML; a complete control library, data binding, themes for five design languages and GPU rendering, on desktop, mobile and the web.

Pure-Rust inference engine for Qwen GGUF models (Qwen3 to Qwen3.8, dense and MoE up to 770B+). CUDA and Vulkan (NVIDIA, AMD), hybrid CPU+GPU experts, MTP speculative decoding, OpenAI and Anthropic compatible server. Up to ~1.7x llama.cpp decode on a 12 GB RTX 3060.

Local-first web & document ingestion engine in Rust — HTTP/browser capture, layout-aware PDF/Office/OCR parsing, persistent sync, verifiable data graphs, and evidence-grounded AI context.