Extend character support to 5,000+, lift editing limits, integrate with DeepL (Pro or API), enable formal/informal tone selection, and provide privacy‑friendly device fingerprint rotation.
- chrome-extension
- chrome-extensions
- crack
- deepl
104,105 visible repositories in the index
793–816 of 2,221 · Most stars
Extend character support to 5,000+, lift editing limits, integrate with DeepL (Pro or API), enable formal/informal tone selection, and provide privacy‑friendly device fingerprint rotation.
AgentFlow: In-the-Flow Agentic System Optimization
glTF 2.0 SDK for JavaScript and TypeScript, on Web and Node.js.
High-performance code-intelligence engine for AI agents and IDE, supports 257 languages, multi repositories, based on graph, with access via CLI, MCP Server, and API. AI coding agents teammate - expose only needed information, cutting token usage up to 50x. 100% local. Discord: https://discord.gg/39MFHu3J5d
EPUB to audiobook converter, optimized for Audiobookshelf, WebUI included
An optimized deep prompt tuning strategy comparable to fine-tuning across scales and tasks
A manually tuned font revision of Readerly, with reduced and altered serifs, optimized for digital reading and e-readers. OFL licensed.
IPTV checker tool for Docker && CMD, check your playlist is available
A rate limiter for Starlette and FastAPI
A library for differentiable nonlinear optimization
A pre-execution guard for AI coding agents. It blocks destructive Git and file system commands, plus common attempts to access sensitive files, before a tool call runs. Supports Amp Code, Antigravity CLI, Claude Code, Codex, Cursor, DeepSeek Harness, Devin CLI, GitHub Copilot CLI, Grok Build, Hermes Agent, Kimi Code, OpenClaw, OpenCode, and Pi.
A flexible view for providing a limited rect window into a large data set,just like a two-dimensional RecyclerView. It different from RecyclerView is that it's two-dimensional(just like a Panel) and it pin the itemView of first row and first column in their original location.
Automatic LOD generation + scene optimization
Crane is a FinOps Platform for Cloud Resource Analytics and Economics in Kubernetes clusters. The goal is not only to help users to manage cloud cost easier but also ensure the quality of applications.
LiME (formerly DMD) is a Loadable Kernel Module (LKM), which allows the acquisition of volatile memory from Linux and Linux-based devices, such as those powered by Android. The tool supports acquiring memory either to the file system of the device or over the network. LiME is unique in that it is the first tool that allows full memory captures from Android devices. It also minimizes its interaction between user and kernel space processes during acquisition, which allows it to produce memory captures that are more forensically sound than those of other tools designed for Linux memory acquisition.
The Classiq Library is the largest collection of quantum algorithms and applications. It is the best way to explore quantum computing software. We welcome community contributions to our Library 🙌
Run LLMs on AMD Ryzen™ AI NPUs in minutes; purpose-built and deeply optimized for the AMD NPUs.
Performance Optimizer Observation Platform
A flexible free and unlimited python tool to translate between different languages in a simple way using multiple translators.
Rate limiting library for serverless runtimes
Open Source AI Accelerator Research Platform Standard / 开源推理研究平台
The repository host gives no description.
Virtualized Elastic KV Cache for Dynamic GPU Sharing and Beyond
Ghost in your shell. Ante is a self-contained agent harness with a highly optimized core. It works like Claude Code or Codex, with none of their dependencies or model constraints.