Montevive
Back to home

// Open source

Our open source work

We believe safe AI is built in community. We publish the tools, agents and utilities we use day-to-day so anyone can audit, improve and reuse them.

8
repositories
307
stars
36
forks
montevive/penpot-mcp

Penpot MCP server

#ai#api-integration#cursor
Python22728updated 6mo ago
montevive/autocache

🚀 Autocache - Intelligent Anthropic API Cache Proxy Automatically inject cache-control fields into Claude API requests to reduce costs by up to 90% and latency by up to 85%. Works as a transparent drop-in replacement for popular AI platforms like n8n, Flowise, Make.com, LangChain, and LlamaIndex—no code changes required

#agent#agentic-ai#ai
Go698updated 3mo ago
montevive/go-name-detector

High-performance Go library for PII name detection. 10x faster than Python with embedded 727K names dataset. Production-ready out-of-the-box functionality for privacy compliance and data security.

#data-security#dlp#go
Go50updated 8mo ago
montevive/prompt-injection-demo

Prompt Injection Demo with n8n

#ai-agents#ai-security#cybersecurity
Python20updated 1mo ago
montevive/duffbot

Duffbot: a bot for Top AI tools

#ai#chatbot#gradio
Python20updated 1y ago
montevive/gemma3n-benchmark

Gemma 3n benchmark (CPU vs GPU)

Python10updated 10mo ago
montevive/ai-workshop

AiBirras AI Workshop

Jupyter Notebook10updated 1y ago
montevive/openai-privacy-filter
OpenAI Privacy Filter — Web Demo

A small browser app that runs openai/privacy-filter — OpenAI's bidirectional token classifier for personal data detection — entirely on the user's device. Model weights are downloaded once from the Hugging Face CDN, cached in IndexedDB, and inference runs on the local GPU via WebGPU (with a WASM CPU fallback for browsers without WebGPU). There is no backend. There are no API calls. Your text never leaves the tab it's typed into.

#typescript#webgpu#privacy
TypeScript00updated 15d ago