Stars
Turso is an in-process SQL database, compatible with SQLite.
AG-UI: the Agent-User Interaction Protocol. Bring Agents into Frontend Applications.
Servo aims to empower developers with a lightweight, high-performance alternative for embedding web technologies in applications.
🤖 A client-first, server-capable, fully type-safe router and full-stack framework for the web (React and more).
Moshi is a speech-text foundation model and full-duplex spoken dialogue framework. It uses Mimi, a state-of-the-art streaming neural audio codec.
A modern animation library for React and JavaScript
Open-source AI agents for penetration testing
A lightweight WebAssembly runtime that is fast, secure, and standards-compliant
🎒 Token-Oriented Object Notation (TOON) – Compact, human-readable, schema-aware JSON for LLM prompts. Spec, benchmarks, TypeScript SDK.
API, CLI, and Web App for analyzing and finding a person's profile in 1000 social media \ websites
🍒 Cherry Studio is a desktop client that supports for multiple LLM providers.
Kilo is the all-in-one agentic engineering platform. Build, ship, and iterate faster with the most popular open source coding agent. #1 on OpenRouter. 750k+ Kilo Coders. 6.1 trillion tokens/month.
A markup-based typesetting system that is powerful and easy to learn.
A Datacenter Scale Distributed Inference Serving Framework
LLM Frontend for Power Users.
⚡ Python-free Rust inference server — OpenAI-API compatible. GGUF + SafeTensors, hot model swap, auto-discovery, single binary. FREE now, FREE forever.
High-performance framework for building interactive multi-agent workflow systems in Rust
Find vulnerabilities, misconfigurations, secrets, SBOM in containers, Kubernetes, code repositories, clouds and more
Mantella is a Skyrim and Fallout 4 mod which allows you to naturally speak to NPCs using Whisper (speech-to-text), LLMs (text generation), and Piper / xVASynth / XTTS (text-to-speech).
A powerful Rust library and CLI tool to unify and orchestrate multiple LLM, Agent and voice backends (OpenAI, Claude, Gemini, Ollama, ElevenLabs...) with a single, extensible API. Build, chain, eva…
High-performance data engine for AI and multimodal workloads. Process images, audio, video, and structured data at any scale
GenAI Agent Framework, the Pydantic way
LLM agents built for control. Designed for real-world use. Deployed in minutes.
A completely customizable framework for building all-in-one drawing whiteboard
GPU cluster manager for optimized AI model deployment