Persistent Localhost logo

Persistent Localhost

CommunityPopular
davidondrej
persistent-localhost

Manage persistent dev servers, APIs, and other local processes on a port using macOS LaunchAgents. Use when starting, stopping, restarting, inspecting, or troubleshooting local servers that should survive shell exit and restart after crashes.

Overview

Publisherdavidondrej
Repositoryskills
Skill namepersistent-localhost
Stars
4.1K
Forks
599
Bundled files
1
LicenseMIT
Links
Skill sourceRepository
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 1 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by davidondrej on GitHub. Read the source before you install it.

Installation

Install the Persistent Localhost AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/davidondrej/skills.git /tmp/skills
mkdir -p .claude/skills
cp -r /tmp/skills/skills/ops-and-setup/persistent-localhost .claude/skills/persistent-localhost
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Persistent Localhost in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Persistent Localhost on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Persistent Localhost is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Persistent localhost servers (macOS launchd)

One script does everything. Resolve scripts/persistent-localhost.sh relative to this SKILL.md, never from the current directory.

Workflow

  1. Check what already exists:
bash
scripts/persistent-localhost.sh list
  1. Start the server. --name is the handle. --port enables readiness checks and duplicate handling. --dir defaults to the current directory.
bash
scripts/persistent-localhost.sh start --name myproj --port 5111 --cmd "./bin/serve"

The command returns only after the port is listening, or fails with the last 20 log lines. Report the printed URL= to the user.

  1. Inspect, restart, read logs, stop:
bash
scripts/persistent-localhost.sh status myproj
scripts/persistent-localhost.sh restart myproj   # after editing code that has no reloader
scripts/persistent-localhost.sh logs myproj 100
scripts/persistent-localhost.sh stop myproj

Hot reload

Prefer the framework's own reloader in --cmd (flask run --debug, vite, uvicorn --reload, node --watch). If the server has none, add --watch. It wraps the command in watchexec -r on the working directory. Never use both. Requires brew install watchexec.

Rules the script enforces

  • Runs as com.persistent-localhost.<name> in the user gui domain via launchctl bootstrap. Restart uses kickstart -kp, stop uses bootout. No deprecated load, start, stop, no broad pkill.
  • KeepAlive only on crash. A clean exit stays down. Throttle 5s so a syntax error cannot spin.
  • Port already taken by the same app (our own label, or a stray process with the same working directory) is replaced. A different app is left alone and the next free port is used. Read the printed PORT=.
  • The caller's PATH and a PORT variable are passed into the job. Add more with --env KEY=VAL.
  • Logs: ~/Library/Logs/persistent-localhost/<name>.log. State: ~/Library/Application Support/persistent-localhost/<name>.state. Plist: ~/Library/LaunchAgents/.

Fallback

Never start servers with nohup, &, disown, setsid, or run_in_background. If launchctl bootstrap fails, report the failure and stop.

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Persistent Localhost AI skill do?

Manage persistent dev servers, APIs, and other local processes on a port using macOS LaunchAgents. Use when starting, stopping, restarting, inspecting, or troubleshooting local servers that should survive shell exit and restart after crashes.

Why use Persistent Localhost on TypingMind?

Because you install it once and use it with any model. Persistent Localhost is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Persistent Localhost in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/davidondrej/skills/tree/main/skills/ops-and-setup/persistent-localhost. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Persistent Localhost?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Persistent Localhost?

As many as you like. As long as a model supports skills, you can use Persistent Localhost with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Persistent Localhost AI skill free?

Yes. It is published on GitHub by davidondrej under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

Related AI Skills

View all
obra logo

Systematic Debugging

obra
CommunityPopular

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes

25.8K
288.1K
10 files
View
obra logo

Test Driven Development

obra
CommunityPopular

Use when implementing any feature or bugfix, before writing implementation code

25.8K
288.1K
1 files
View
obra logo

Using Git Worktrees

obra
CommunityPopular

Use when starting feature work that needs isolation from current workspace or before executing implementation plans - ensures an isolated workspace exists via native tools or git worktree fallback

25.8K
288.1K
Instructions
View
obra logo

Using Superpowers

obra
CommunityPopular

Use when starting any conversation - establishes how to find and use skills, requiring skill invocation before ANY response including clarifying questions

25.8K
288.1K
5 files
View

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇