Local adapters (Ollama, LM Studio, Faster-Whisper, Piper, LLaVA) for @llmrtc/LLMRTC

Client Node.js modulare per LLM locali (Ollama/Llava)

A Node.js CLI that uses Ollama and LM Studio models (Llava, Gemma, Llama etc.) to intelligently rename files by their contents

A Node.js CLI that uses Ollama and LM Studio models (Llava, Gemma, Llama etc.) to intelligently rename files by their contents

Bidirectional Markdown-PDF converter with AI-powered vision. MD→PDF with beautiful themes, PDF→MD with LLaVA vision model - completely open source and privacy-first

视觉识别 MCP 服务器，支持 Claude (Anthropic)、智谱 (GLM-4V)、Ollama 三大视觉 API

Generate a simple Node.js project structure for running AI models with Replicate's API

Rename images based on the results of some dumb ai bullshit

MCP vision proxy v0.2 — fork-merge of mature vision MCPs. Multi-model fallback, compare_images, cache, CLAUDE.md rules for DeepSeek text in VS Code / Claude Code.

Ollama provider — local LLM text completion, embeddings, and image description via Ollama API

[AI-JSX](https://docs.ai-jsx.com/) components to work with more model providers like [Ollama.ai](https://ollama.ai/) or [Llamafile](https://github.com/Mozilla-Ocho/llamafile)

Node.js module providing inference APIs for large language models, with simple CLI.

N8n nodes for Syrus AI integration

CLI tool for transcribing and summarizing MP4 recordings using Whisper and Ollama

Turn code repos and curated visual repos into contamination-checked training datasets for local fine-tuning.

This is a project dedicated to building a real-life version of GLaDOS.

Ollama local AI provider for floimg - vision and text generation with local models

AI desktop file auto-labeler (OCR + local vision) for screenshots and docs

Pi extension giving vision to DeepSeek

Persistent memory, visual session tracking, and RL trajectory capture for AR/XR — the shared brain for every headset