Aguacatech is a local AI agent, disk reclaimer, and privacy sentinel for macOS. Talk to a model running on your own Mac. Reclaim every gigabyte. See every permission and outbound connection. Nothing leaves your machine.
Snapshot top processes, memory pressure, crashes, and launchd churn → get a plain-English answer from your local model.
Every feature runs against a model on your Mac. No SaaS dependency.
Buy a license key, paste it in Settings. No sign-up, no email gate.
Pay once per tier. Optional subscription if you prefer.
SwiftUI + AppKit. No Electron, no web wrapper. macOS 14+.
Aguacatech replaces three subscriptions with one app you own forever. Talk to a local model, reclaim your disk, and see every privacy decision macOS made for you.
Streaming chat backed by a local LLM. Tool-calling, screenshots, vision, voice. The agent reads files, drives apps, runs your Shortcuts, with an approval gate before every write.
The cleanup tools CleanMyMac wishes it had. TreeMap of every byte. Smart Uninstaller with orphan-leftover detection. 30+ GB Xcode caches in one click.
Replace Little Snitch plus a clipboard manager plus that Mic-Drop menu bar app you keep meaning to install. Sentinel watches every grant and every outbound socket.
Real screenshots from the latest build, no marketing mockups. Swipe, click the dots, or use ← → to walk through.
CPU, memory pressure, disk, battery, and network in one snapshot. Polls every 1.5s. Hit Diagnose to ask your local model 'why is this slow?' and get a plain-English answer.
Every destructive tool, write_file, run_applescript, every MCP write, pauses the agent and shows you the diff before it runs. Allow once, allow always, or deny.
Aguacatech is a Model Context Protocol client. Add GitHub, Postgres, Slack, or any of dozens of MCP servers, their tools join the agent's registry instantly.
Memory pressure chart with proper thresholds. Per-core CPU bars. Per-process network. Top processes. Live, native, snappy. Click the bandwidth card to drill into per-process flows.
Remove an app and review every leftover preference, cache, container, launch agent, and Dock entry, by confidence score. Save a reinstall manifest to restore preferences later.
Permission Inspector audits every TCC grant on your Mac in a single grid. Connection Log keeps 7 days of outbound flows. Find what shouldn't be there, ask the LLM "is this normal?", and revoke.
The model runs on your Mac. Permissions are read from TCC.db on disk. Connection samples come from lsof. Disk scans use du. Nothing is uploaded. Anywhere.
Free is generous and stays free. Each paid tier is sold once or yearly, your choice. Buy one tier or bundle them.
Bundle everything, $129 one-time · or $69/yr. Get the bundle
What you'd be wondering. If anything's missing, email us.
Yes. Aguacatech is a thin client that talks to whatever OpenAI-compatible endpoint you point it at. The default is LM Studio at http://localhost:1234/v1. You can also use Ollama or any compatible runtime. There's no cloud fallback, if your local server is off, the agent doesn't run.
Only the requests you send to your configured LLM endpoint. If that endpoint is local (the default), nothing leaves the machine. Aguacatech has zero telemetry, no analytics, no accounts. Your conversations, logs, scan results, and license key all live in ~/Library/Application Support/aguacatech.
After purchase, you receive a license key by email within 24 hours. Paste it into Settings → License. The key activates the matching tier locally, it is not validated against a remote server, ever. You can use the same key on every Mac you own.
The marketing site is. The app itself ships as a notarized DMG. We'll open more components over time, especially MCP-related infrastructure.
Some people prefer to buy once and own it. Some people prefer lower-friction yearly payments and continuous updates. You pick. One-time licenses include 12 months of updates by default; subscriptions include updates for as long as they're active.
14-day no-questions refund window. Email us within 14 days of purchase and we'll process it through PayPal.
macOS 14 Sonoma or newer. Apple Silicon or Intel. Recommended: 16 GB RAM if you plan to run a 7B-class local model alongside; 32+ GB for larger models. About 200 MB of disk for the app itself.