kordless

Claude Desktop Uninstallers

Scripts to fully remove Claude Desktop and all the files it leaves behind, because Anthropic's official uninstaller doesn't.

The Problem

Anthropic shipped a Cowork feature in Claude Desktop that silently spins up a Linux VM on your machine. No warning. No disk space prompt. No way to opt out at install time.

The VM bundle grows to ~10GB and lives in your AppData/Application Support folder. When you uninstall Claude Desktop through the normal method, the VM bundle stays behind. Most users will never find it because it's buried in a hidden system folder.

kordless

Sticky howto-dynamic-simple-tool-proxy
Created: 2025-09-18T19:13:19.306879Z
Last modified: 2025-09-18T19:13:19.306879Z
Last accessed: 2025-09-18T19:20:57.994597Z
URL: app://sticky/howto-dynamic-simple-tool-proxy
Dynamic MCP Proxy (Hot‑Reload) — How‑To

Overview
- Expose a tool via an MCP server that dynamically imports the underlying implementation from a target file.
- Detect file changes via mtime and reload on demand; no server restarts required.

kordless

Repetition Detection Suite

A comprehensive Python library for detecting repetitive text patterns in real-time streams, designed to catch runaway AI generation, infinite loops, and other repetitive content scenarios.

🚀 Quick Start

from repetition_detector import UnifiedRepetitionDetector

# Create detector

kordless

Nanonets OCR Setup Guide

This guide will help you set up and run the Nanonets OCR model locally for PDF processing.

GitHub Gist: https://gist.github.com/kordless/652234bf0b32b02e39cef32c71e03400

Quick Start (Complete Setup)

# 0. Create and activate conda environment first

kordless

import sys
import os
import logging
import requests
import re
import json
from typing import Dict, Any, Optional, List, Tuple
from mcp.server.fastmcp import FastMCP, Context
from urllib.parse import urlparse, urljoin
import asyncio

kordless

"""
Adaptive Connector Framework (ACF)

A self-bootstrapping alternative to MCP that dynamically builds and tests 
connectors based on current needs. The system evolves its own capabilities
through iterative learning and testing.

Key components:
1. Registry - Manages available connectors and their capabilities
2. Connector Builder - Dynamically creates new connectors

kordless

import os
import sys
from dotenv import load_dotenv, set_key
from langchain_openai import ChatOpenAI
from langchain.prompts import ChatPromptTemplate, PromptTemplate
from langchain_core.runnables import RunnableSequence
from langchain.tools import Tool
from langchain.agents import create_react_agent, AgentExecutor
from langchain.schema import HumanMessage
import getpass

kordless

To run the Python script for splitting a PDF into segments of just under 25MB each, you'll need to follow these steps:

Prerequisites

Python Installation: Ensure that Python is installed on your system. If not, you can download and install it from python.org.

PyPDF2 Library: The script uses the PyPDF2 library. You can install it using pip, Python's package installer. If pip is not already installed, it comes bundled with Python 3.4 and later versions.

Installation Steps

Open Terminal or Command Prompt: On Windows, you can open Command Prompt by searching for cmd in the Start menu.

kordless

# tokens from https://cloud.featurebase.com/configuration/api-keys
featurebase_token = "<token>"

# featurebase ($300 free credit on signup)
# https://query.featurebase.com/v2/databases/bc355-t-t-t-362c1416/query/sql (but remove /query/sql)
featurebase_endpoint = "https://query.featurebase.com/v2/databases/<uuid-only-no-query-sql>"

kordless

Example of using OpenAI functions in completions with Python decorators

This example illustrates a way to utilize a function dynamically while querying an OpenAI GPT model. It uses the newly released functions support in the completion endpoints OpenAI provides.

The general concept is based on using a decorator to extract information from a function so it can be presented to the language model for use, and then pass the result of that function back to the completion endpoint for language augmentation.

In general, a wide variety of functions can be swapped in for use by the model. By changing the get_top_stories function, plus the prompt in run_conversation, you should be able to get the model to run your function without changing any of the other code.

Configuration

To use this, create a config.py file and add a variable with your OpenAI token: