evilsocket/pwnagotchi

Health v2 · maintenance only

Flags: no_license

Adoption not part of the score

9189 stars · 1231 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-29, confidence not recorded

Pwnagotchi is an A2C deep reinforcement learning agent built on bettercap that learns from its surrounding WiFi environment to maximize capture of crackable WPA key material (handshakes and PMKIDs). It typically runs on a Raspberry Pi Zero W with an e-ink display, presenting a Tamagotchi-style face while it autonomously sniffs, deauthenticates, and associates to collect PCAP files usable with hashcat.

Use cases

• capture WPA handshakes and PMKIDs for offline cracking with hashcat
• learn reinforcement learning by deploying an AI agent in a real environment
• build a portable WiFi auditing device on a Raspberry Pi Zero W
• automate WiFi reconnaissance and deauthentication attacks
• extend a hacking gadget with a plugin system
• monitor nearby WiFi access points and client stations

When to choose

• you want an autonomous, learning WiFi penetration-testing companion device
• you have compatible hardware (monitor-mode WiFi, ideally Raspberry Pi Zero W)
• you want a fun, hackable platform to learn RL and WiFi security
• you need PCAP handshake captures compatible with hashcat

When to avoid

• you need a compliant, authorized-only enterprise WiFi auditing tool with reporting
• you cannot use monitor-mode WiFi hardware or run on GNU/Linux
• you expect plug-and-play without soldering, flashing SD cards, and configuration
• deauthentication attacks are illegal or unethical in your context

Facets

application · maturity active

machine-learning reinforcement-learning security penetration-testing agent-framework security penetration-testing machine-learning hardware networking python embedded iot wifi wpa-handshake bettercap raspberry-pi a2c hashcat e-ink-display hacking linux

Member repositories

For agents

markdown · JSON · MCP: product_card(name="evilsocket/pwnagotchi")