Specs at a glance
| CPU | Snapdragon 410 / 615 era — ARM Cortex-A53 |
| RAM options | 1 GB (Moto E2) — up to 8 GB on newer used phones |
| Storage | 8–32 GB internal + microSD |
| Power draw | 1–3 W |
| Form factor | fits in a pocket (the original) |
| Local LLM capability | No local LLM |
| Agent score | 3/10 |
| Price point | €15–30 used |
Overview
Repurposing a 2015-era Android phone as an agent host is the project that started PocketClaw. It works, with severe constraints: Termux + proot-distro for a Linux userland, custom Node.js builds because the official binaries don't target old ARMv8, V8 heap tuning for the 1 GB RAM ceiling. The result is a phone that runs a stripped-down Nanobot agent that calls a cloud LLM API. It is a hobbyist project — not a viable production setup. We document the journey under /archive/ for the engineers who'll find it useful.
Best for
- Hobbyist proof-of-concept
- Demonstrations of low-power AI hosting
- Educational projects
Not for
- Anything production
- Browser automation
- Local LLMs (period)
- Multi-user workloads
Compatible self-hosted agents
Tested working on Old Android phone (Moto E2 et al.) (with the caveats from “Best for” / “Not for” above):
See: all pocket AI hardware · edge AI hardware buyer's guide · how we test.