Context7
Feeds AI the latest docs for libraries and frameworks before it answers, so code it writes does not use outdated, removed functions.
Description from the maker (original English)
Per-app CPU, efficiency-core and memory control for Apple Silicon Macs, with suggestions and undo.
These three are never merged into one score: opinions, measurements and popularity are different things.
We have not written a plain-language summary for this one yet. Below are the facts we read from the registry.
Pick the AI app you use, then copy the settings.
Which app do you use?
Pick your app above. We remember it, so next time the button says “Install in …”.
Download the maker’s .mcpb file
The link goes to the maker’s own file; we do not host or repackage it. Open the file and Claude Desktop installs it.
Run this in your terminal
Your browser asks to open the app, then the app shows the settings and asks you to confirm. Key values are left empty for you to fill in.
Your browser asks to open the app, then the app shows the settings and asks you to confirm. Key values are left empty for you to fill in.
This one runs on your computer, and ChatGPT can only connect to servers on the internet. Pick another app.
Your choice stays on this device in a cookie; no account needed.
These settings are generated from the maker’s registry entry. If the README says otherwise, follow the README.
Runs on your computer; the tool list appears in your AI app after you install it.
We check information anyone can see; we have not read the code. Checks that do not apply are left out of the count. · Checked Nov 7, 2026
The registry name was verified with the GitHub account IntarsO, which owns the repo
We have not read this repo from GitHub yet
We have not read this repo from GitHub yet
This one runs on your computer; there is no internet endpoint
Runs on your computer and uses local settings instead
Runs on your computer; we can only read tool lists from internet endpoints
Compared with every active server in this category in the registry. Stars count only when the publisher owns the repo.
It passed 1 of 1 applicable basic checks. We have not read the code. Before adding a key or token, see what access the server asks for and use a key with only the permissions you need.
The registry does not list a required key, though some servers ask you to sign in on first use.
It runs on your computer. Your AI app starts it when needed, and data does not pass through the maker’s servers (unless it calls an online service itself).
The GitHub repo last changed –, and the latest version (1.7.1) reached the registry 25 days ago.
Apps that support MCP, such as Claude Desktop, Claude Code, Cursor and VS Code. You also need MCPB on your computer.
In the same category: Context7, Codebase Memory, Exa
Servers in the same category from other makers, sorted by stars.
Reading a card:★ GitHub starsiThree pillars: reviews · checks · usageiUpdated = latest version published to the registryi
Feeds AI the latest docs for libraries and frameworks before it answers, so code it writes does not use outdated, removed functions.
Codebase knowledge graph for AI agents — 162 languages, sub-ms queries, 99% fewer tokens.
Connect AI agents to Exa for web search, content fetching, and multi-step research.
Copied from the maker’s repo as written. PopNx MCP has not reviewed or endorsed it. HTML, images and scripts are removed. Links lead off this site.
AppWrangler
Keep every app on your Mac in check — CPU, efficiency cores and memory, per app.
A free, open-source menu bar app for Apple Silicon Macs.
Helps the app you're using stay fast, even on an 8 GB Mac with lots of apps open.
Free and open source (GPL-2.0), for macOS 13+ on Apple Silicon. It typically uses 1–2% of one core and about 30 MB of memory, and never connects to the network.
brew tap intarso/appwrangler https://github.com/IntarsO/AppWrangler
brew install --cask appwrangler
Or download the zip from Releases. AppWrangler isn't notarized yet, so the first time, right-click it → Open.
| 🪄 Auto mode | On by default. The app you're using runs at full speed. Background apps move to efficiency cores, and only when your Mac is busy do they share the CPU fairly, so everything stays usable. Optionally, when memory runs out, it freezes apps you haven't used for a while, and they resume the moment you switch back. It adapts to what the Mac needs: background work runs free when there's room or you're away, apps are held sooner on battery or when hot, low-priority work like updaters is paused while you need the resources, and it learns which apps you usually use around now (kept on your Mac). |
| 🎛 CPU limit | Cap an app *and all of its helper processes* (Chrome tabs, Electron helpers, Safari web content…) at any share of the CPU. Optionally limit it only while it's in the background. |
| 🍃 Efficiency cores only | Move an app onto the Apple Silicon E-cores, with slower disk and network access. It stays usable while saving battery and heat. |
| 🧠 Memory limit | When an app's memory stays above your limit, get notified, or freeze, quit or force-quit it. (macOS doesn't let one app hard-cap another's memory, so AppWrangler watches and acts.) |
| 🚨 Low-memory protection | When your Mac runs short of memory, automatically freeze or quit apps you've marked as expendable, and resume them afterwards. Free memory now does it on demand. |
| ⏱ Conditions | Make any rule apply only on battery or on the charger, in Low Power Mode, when the Mac is hot, or during set hours and days. |
| 🔥 Runaway alerts | "Chrome Helper has used 150% CPU for 3 minutes" — a card in the panel and a notification with *Limit*, *E-cores* and *Ignore* buttons. |
| 📞 Calls and meetings | When an app records from the microphone, it gets everything it needs until the call ends, and everything else steps back; nothing touching the call is slowed or frozen. Make room for any app for 30 minutes, an hour or three from the menu bar, and mark apps Prioritized or Can wait. |
| ❄️ Freeze, quit, force quit | Suspend any app instantly and resume it later. |
| 📊 Impact | How much CPU time and energy it saved, how often your Mac ran short of memory and how much it swapped, and what AppWrangler itself cost to run. |
| 💡 Suggestions | "Brave uses more than your 8 GB of RAM — here's what to do." Concrete recommendations, each with the reason, the benefit and a one-click fix. appwrangler undo takes changes back. |
| 🤖 AI assistants (MCP) | Ask Claude or OpenAI Codex what's slowing your Mac down and have it fix it, with your OK. Set up with one command: appwrangler mcp install. |
| ⌨️ Command line & links | appwrangler suggest, show Slack, set Slack efficiency_cores=on, stats, prefs… and appwrangler:// links for Shortcuts. |
| 🖥 Desktop widget | CPU, memory, Auto mode, the busiest apps and suggestions on your desktop (macOS 14+), with Pause, Auto and Free memory buttons. |
| 📖 Built-in help | The full manual inside the app, searchable and offline, with a ? next to every setting. |
| AppWrangler | App Tamer | AppPolice | Activity Monitor | |
|---|---|---|---|---|
| Price | Free | $14.95 (15-day trial) | Free | Free (built in) |
| Apple Silicon native | ✅ | ✅ | ❌ (2016, Intel-era) | ✅ |
| Move apps to efficiency cores | ✅ | ✅ | ❌ | ❌ |
| Per-app CPU limit | ✅ | ✅ | ✅ | ❌ |
| Per-app memory limit (notify / freeze / quit) | ✅ | ❌ | ❌ | ❌ |
| Automatic background management | ✅ Auto mode | ✅ | ❌ | ❌ |
| Freeze idle apps when memory runs low | ✅ | ❌ | ❌ | ❌ |
| AI assistants (MCP) / command line | ✅ / ✅ | ❌ / AppleScript | ❌ | ❌ |
| Open source | ✅ GPL-2.0 | ❌ | ✅ GPL-2.0 | ❌ |
| Last updated | 2026 | 2024 (2.8.4); 3.0 in beta | 2016 | with macOS |
App Tamer is a polished, long-standing commercial app, and if you already use it, it does its job well. AppWrangler is for people who want something free and open source with memory handling and AI control. Facts checked in October 2026 against each project's own pages; tell us if something has changed.
./build.sh --install --run.👉 Read the full [Getting Started guide](docs/getting-started.md).
AppWrangler is a fork of [AppPolice](https://github.com/fuyu/AppPolice) by Maksym Stefanchuk (2013–2015), a menu bar app that let you throttle an app's CPU with a slider. That project inspired AppWrangler, and its source is where AppWrangler began.
The original no longer built on modern macOS and its limiter didn't work on Apple Silicon. AppWrangler is a ground-up rewrite (Swift + C) that keeps the idea and adds:
See NOTICE.md and the CHANGELOG for details. AppPolice 1.x limits and AppPolice 2.x rules are imported automatically.
AppWrangler is free and always will be. If it saves your battery or your sanity, you can buy me a coffee ☕. Thank you!
xcode-select --install # Command Line Tools — full Xcode is not required
./build.sh # → build/AppWrangler.app ./test.sh # unit + integration tests ./Tests/e2e/run.sh # end-to-end tests against the built app
Contributions are welcome — see CONTRIBUTING.md and our Code of Conduct. Please report security issues privately as described in SECURITY.md.
AppWrangler is free software, licensed under the GNU General Public License v2 (LICENSE), the same license as AppPolice. Original AppPolice code © 2013–2015 Maksym Stefanchuk; AppWrangler © 2026 AppWrangler contributors.