SGLang is a fast serving framework for large language models and vision language models.

A cross-platform native clipboard GUI manager in pure Rust.

The best free and open-source automated time tracker. Cross-platform, extensible, privacy-focused.

A lightweight operating system abstraction layer for agents.

The functional, composable, and typescript-first AI Agent framework for real-world LLM Apps.

A template rendering engine based on Jinja, generating type-safe Rust code at compile time.

Chorus - AI chat app for Mac

An Automatic Prompt Optimization Framework for Large Language Models

Ready-made tokenizer library for working with GPT and tiktoken

Parsing gigabytes of JSON per second : used by Facebook/Meta Velox, the Node.js runtime, ClickHouse, WatermelonDB, Apache Doris, Milvus, StarRocks

A lightning-fast Zig-powered event loop for Python's asyncio.

Ultra fast asyncio event loop.

Everything you need to know about cross compiling Rust programs!

Minimal CLI coding agent by Mistral

An Open Phone Agent Model & Framework. Unlocking the AI Phone for Everyone

The web framework for inventors

A Claude Code plugin that automatically captures everything Claude does during your coding sessions, compresses it with AI (using Claude's agent-sdk), and injects relevant context back into future …

Tile-Based Runtime for Ultra-Low-Latency LLM Inference

Actix Web is a powerful, pragmatic, and extremely fast web framework for Rust.

Ergonomic and modular web framework built with Tokio, Tower, and Hyper

"Paper2Slides: From Paper to Presentation in One Click"

PaCoRe: Learning to Scale Test-Time Compute with Parallel Coordinated Reasoning

🪞PRIMP (Python Requests IMPersonate). The fastest python HTTP client that can impersonate web browsers

A Rust HTTP server for Python applications

Servo aims to empower developers with a lightweight, high-performance alternative for embedding web technologies in applications.

Paper Debugger is the best overleaf companion

A user-friendly interface built on top of Thinking Machines Tinker API that lets you fine-tune LLMs, chat with your trained model, and deploy to Hugging Face.

基于 Clash (mihomo) 内核的轻量级 macOS 菜单栏客户端。Lightweight macOS Clash (mihomo) menu bar client.