Voyage.ai API Toolbox

Summarize youtube videos with an LLM

A web UI for managing multiple models with llama-server.exe on windows

A simple discord bot that generates images using the Flux Dev model using Fireworks.ai

Chat with local AI models in a simple electron app

A vector search MCP for document retrieval using MongoDB Atlas Vector Search and Voyage AI Context embeddings.

An experiment in AI collaboration and automated research.

Learn 7 things about any topic using an LLM

Generates dense vector embeddings for images using VoyageAI's multimodal embedding model

A simplified version of a MongoDB MCP server for the sample_mflix movies database

Implementation of search on Mongo without Atlas Search or $text. It's terrible.

A simple MCP server tool for calculating approximate sizing for dedicated search nodes on MongoDB Atlas

The site code for catbee.ca written in flask/bootstrap. It just lists my various github projects.

Record your global audio and transcribe with whisper.cpp and llama.cpp

MCP server for querying the sample movies dataset on MongoDB Atlas

Discord bot for summarizing channels when people get out of control and I don't wanna read all that.

Image generation Flask app using Flux models hosted on Fireworks.ai

A conversational UI for chatbots using the llama.cpp server

Natural Language Query for MongoDB Atlas

A pure python vector store with hybrid search and metadata filtering

Run llama.cpp based chatbots on Discord

Downscale your media files to h265 to save space

A local API for using a Mistral 7b LLM to summarize JSON data into semantically rich plain text.

A small service to convert PDF files to Markdown using the Docling library

Create batches of images with the Flux model and the Fireworks.ai API

Zero shot Flappy Bird implementations with various LLM models

Facts are all you need! Blog without writing, blog with just facts.

Create an external brain for your facts, ask questions about it later

A tool for testing RAG functionality with Atlas Vector Search

Another attempt at an LLM driven voice assitant, but with better transcription and better TTS