Native macOS Autonomous Agent

Autonomy by Nature.Privacy by Design.

Pheron Agent is a fully autonomous, hardware-native AI agent for macOS. Built on the Swift 6 UNO architecture, it runs entirely on your Apple Silicon with local MLX inference. Your conversations never touch the cloud. Zero data leaks.

Pheron Agent Interface

Built for Extreme Performance

Pheron Agent is built with native Apple hardware components to achieve speeds unmatched by cloud-based alternatives.

🚀

Titan Engine

On-device MLX inference featuring wired memory pinning, 4-bit KV quantization, rotating cache (up to 131K context), and speculative decoding via custom draft models.

Local Inference
🧠

ANE Intent Classifier

Hardware-accelerated task routing executed directly on the Apple Neural Engine. Routes prompts to tools, weather, chat, or LLM fallback in milliseconds.

Neural Engine
💾

Three-Layer Memory

Structured memory layers: L1 Hot Cache (12 messages), L2 Daily Notes, and L3 DreamBank long-term summaries coupled with Metal-accelerated RAG via custom Metal kernels.

Metal RAG

Energy Profiling

Monitored via `PheronEnergyDaemon` XPC helper utilizing `powermetrics` at 100ms intervals for exact, hardware-level Joule accounting per task execution.

true joule accounting
🔒

Privacy Guard

Rule-based + local LLM PII (Personally Identifiable Information) detection before any external routing, executing PASS, DESENSITIZE, or BLOCK decisions. Direct inquiries regarding security audits can be sent to privacy@pheronagent.com.

Privacy Centric
🛠️

SkillVault

Self-improving procedural memory. The agent writes and patches its own `.skill.md` tool scripts, while a background curator Actor consolidates skills across sessions.

Self-improving

Agent Workflow in Action

Watch Pheron Agent plan and execute a multi-step workflow locally using native macOS integrations.

Merhaba ve nas...
5 hours ago
Qwen 3.5 9B
Ready
$0.0000
* Design elements may vary in the actual application.

Learn the details

Pheron Agent seamlessly integrates with the world's leading AI models and your entire local codebase to accelerate development at scale.

MLX Optimized Local Models

Run cutting-edge AI models natively on Apple Silicon with MLX optimization.

Explore models
MLX Hardware Processing

SkillVault Procedural Memory

Converts past experiences into refined procedural skills, teaching the agent how to solve similar tasks automatically.

Explore SkillVault
SkillVault Visual

System Stability

Experience uninterrupted performance with autonomous self-healing and intelligent hardware-aware protection.

Explore Stability
System Stability Visual

Changelog

1.0.2Jun 3, 2026
Model Hub & VLM Expansion
1.0.1Jun 1, 2026
RAM & UI Fixes
1.0.0Jun 1, 2026
Public Release
See all notable changes

Pheron Agent is your sovereign, on-device AI companion. It runs 100% locally on your Apple Silicon, ensuring absolute privacy while autonomously automating your daily workflows.

Try it for yourself
Pheron Agent