# evilsocket/pwnagotchi

(⌐■_■) - Deep Reinforcement Learning instrumenting bettercap for WiFi pwning.

Repository: https://github.com/evilsocket/pwnagotchi
Canonical: https://ross.abutalabs.com/products/pwnagotchi
Homepage: https://pwnagotchi.ai/
Language: Python
License: NOASSERTION
License Family: other
Topics: ai, deep-reinforcement-learning, wpa-psk, handshakes, bettercap, deep-learning, deep-neural-network
Last push: 2026-08-19T09:02:11+00:00

## Health v2 (maintenance only)
Score: 67/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 98, release rhythm 8, longevity 100
- inputs: {"age_days": 2540, "days_push": 14, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 9189, forks 1231 (observed 2026-08-28T04:10:28.805177+00:00)

## What it is
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
- artifact type: application
- maturity: active
- function: machine-learning, reinforcement-learning, security, penetration-testing, agent-framework
- domain: security, penetration-testing, machine-learning, hardware, networking
- platform: python, embedded, iot
- tags: wifi, wpa-handshake, bettercap, raspberry-pi, a2c, hashcat, e-ink-display, hacking, linux

## Member repositories
- evilsocket/pwnagotchi (main) score 67

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:10:28.805177+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T17:23:20.011957+00:00, confidence not recorded.
  - readme: https://github.com/evilsocket/pwnagotchi (fetched 2026-08-28T04:10:28.805177+00:00, sha e4a5d9cb246c)
  - homepage: https://pwnagotchi.ai/ (fetched 2026-08-29T08:23:19.753384+00:00, sha 7c26993ddf14)
  - site_page: https://pwnagotchi.ai/installation (fetched 2026-08-29T08:23:19.762556+00:00, sha 25c2ed73066c)
  - site_page: https://pwnagotchi.ai/faq (fetched 2026-08-29T08:23:19.765085+00:00, sha d04a54517d7b)
- Data as of 2026-08-30T08:39:29.467469+00:00.