moeru-ai

OpenAI Codex provider for xsAI — drop-in adapter to call Codex from the xsAI SDK.

Stream-first agent runtime for building real-time AI agents with token-by-token output.

Framework bindings for xsAI so you can integrate it with React, Vue, Svelte, and other frontend apps.

Speeds up pulling models and datasets from inference runtimes like HuggingFace, Ollama, vLLM, and ModelScope using P2P.

Web-based tool to find and inspect your downloaded HuggingFace models.

Local text-to-speech inference server powered by ONNX Runtime, supports Chatterbox and other TTS models.

Prompt orchestration with the stacks you already know — write LLM prompts as Vue components.

Easy-to-use MCP builder and launcher for all possible MCP servers — Ollama for MCPs.

Yet another memory layer, inspired by cognitive science, designed for AI companion characters. Written in Rust.

WebXR voice call UI that makes AI-powered VRM characters appear to you in mixed reality.

Transformers.js provider for xsAI. Run embeddings, Whisper, and LLMs directly in the browser through the xsAI SDK.

Self-hosted text-to-speech proxy service, all-in-one for multiple TTS providers, OpenAI-compatible API.

Extra-small AI SDK for TypeScript. Minimal, OpenAI- and Ollama-compatible client for building LLM apps without bundling the world.

A self-hosted AI companion inspired by Neuro-sama that can engage in real-time voice chat, play games like Minecraft and Factorio, and interact with your desktop activities. It's designed as a "soul container" for AI waifus and virtual characters that can function as digital companions with gaming capabilities.