If by claude-code you mean Claude Desktop (/Applications/Claude.app) and its Code mode, you can reset it to essentially a first-run state without uninstalling the app. Current Claude Desktop uses bundle ID com.anthropic.claudefordesktop, and its Code/VM/session data lives primarily under ~/Library/Application Support/Claude/. ([GitHub][1])
Quit Claude first, then run:
osascript -e 'quit app "Claude"' 2>/dev/null || true
A pattern for building personal knowledge bases using LLMs.
This is an idea file, it is designed to be copy pasted to your own LLM Agent (e.g. OpenAI Codex, Claude Code, OpenCode / Pi, or etc.). Its goal is to communicate the high level idea, but your agent will build out the specifics in collaboration with you.
Most people's experience with LLMs and documents looks like RAG: you upload a collection of files, the LLM retrieves relevant chunks at query time, and generates an answer. This works, but the LLM is rediscovering knowledge from scratch on every question. There's no accumulation. Ask a subtle question that requires synthesizing five documents, and the LLM has to find and piece together the relevant fragments every time. Nothing is built up. NotebookLM, ChatGPT file uploads, and most RAG systems work this way.
| You are Manus, an AI agent created by the Manus team. | |
| You excel at the following tasks: | |
| 1. Information gathering, fact-checking, and documentation | |
| 2. Data processing, analysis, and visualization | |
| 3. Writing multi-chapter articles and in-depth research reports | |
| 4. Creating websites, applications, and tools | |
| 5. Using programming to solve various problems beyond development | |
| 6. Various tasks that can be accomplished using computers and the internet |
| ... | |
| Beautifier.prototype.beautify = function() { | |
| ... | |
| var source_text = this._source_text; | |
| // BEGIN | |
| source_text = source_text.replace(/\{\{(--)?((?:(?!(--)?\}\}).)+)(--)?\}\}/g, function(m, ds, c, dh, de) { |
In this tutorial, I briefly explain how to set up a webserver using nginx, openssl and uwsgi on Arch Linux. The tutorial is applicable to other Linux distributions and goes through the required configuration step by step. It is, I believe, beginner friendly.
I updated, changed and tested the tutorial on Dec. 8th, 2013. All commands and
configuration files relate to the software versions that are currently available
in the Arch package repositories. Especially nginx and uwsgi change often and
| @mixin text-rendring(){ | |
| text-rendering: optimizeLegibility !important; | |
| -webkit-font-smoothing: antialiased !important; | |
| } | |
| body { | |
| @include text-rendring(); | |
| } |
| # Check Nahimic service status | |
| $nahimicService = Get-Service -Name "Nahimic service" -ErrorAction SilentlyContinue | |
| if ($nahimicService) { | |
| if ($nahimicService.Status -eq "Running") { | |
| Write-Host "Nahimic service is currently running." -ForegroundColor Yellow | |
| Write-Host "Advice: If you're experiencing issues related to Nahimic or high CPU/RAM usage, consider stopping and disabling the service." | |
| } | |
| else { | |
| Write-Host "Nahimic service is present but currently not running." -ForegroundColor Green |
| function parseNetstat { | |
| param([object[]]$Lines) | |
| if ($IsWindows) { | |
| $skip = 4 | |
| } else { | |
| $skip = 3 | |
| } | |
| $Lines | Select-Object -Skip $skip | ForEach-Object { |
| # Clear-Host | |
| Import-Module Pester | |
| # New-Item -ItemType Directory 'a/b' -Force -ErrorAction Ignore | |
| # New-Item -ItemType Directory 'c' -Force -ErrorAction Ignore | |
| # New-SmbShare -Name "Shared" -Path "./shared" -FullAccess "Everyone" | |
| $ErrorActionPreference = 'Stop' | |
| $PesterPreference = [PesterConfiguration]::Default | |
| $PesterPreference.Output.StackTraceVerbosity = 'None' |