topic

setup.

Everything we've published on setup across guides, agents, hardware reviews and glossary entries: 11 entries in total.

Guides (1)

  • Setup Wizard (/setup)Gateway · 2026-02-18

    Web-based setup wizard for PocketClaw: choose messaging channel, AI provider, enter credentials, and deploy in 4 steps.

Agents (4)

  • Hermes Agent

    Agent from Nous Research (MIT, Python). Runs shell commands on the host by default, with an approval step for dangerous ones; Docker and cloud sandboxes are options. Works with many LLM providers.

  • NanoClaw

    Small TypeScript agent (MIT) built on Anthropic's Claude Agent SDK. Every agent runs in its own Docker container, on macOS, Linux or Windows through WSL2.

  • IronClaw

    Rust agent from NEAR AI, MIT or Apache-2.0. Untrusted tools run in a WebAssembly sandbox with declared capabilities, and secrets are injected outside them.

  • NitroClaw

    Managed assistant built on OpenClaw, in Telegram and Discord: $20 a month self-serve, or $100 with setup and a monthly call. AI credits included.

Hardware (5)

  • Mac Mini M4 / M4 Pro

    Mac mini M4 and M4 Pro for local LLMs: 16 to 64 GB of unified memory at 120 or 273 GB/s, the two specs that decide which models load and how fast.

  • Old Android phone (Moto E2 et al.)

    The PocketClaw origin story device. €15-30 used. Runs lightweight agents via Termux + proot, with serious caveats.

  • Raspberry Pi Zero 2 W

    €20 SBC with 512 MB RAM. Useful as an edge agent endpoint (sensor reader, tool host) but not a primary agent host.

  • Orange Pi 5 Plus

    Orange Pi 5 Plus: Rockchip RK3588, 4, 8 or 16 GB of LPDDR4/4X and a 6 TOPS NPU. The Raspberry Pi 5's closest competitor for self-hosted AI on ARM.

  • Dell OptiPlex 3070 / 5070 Micro (used)

    €100-180 used Intel mini PC. 8th gen i5, 8-16 GB RAM, NVMe. The cheapest credible mini PC for self-hosted AI.

Glossary (1)

  • llama.cpp :C++ inference engine for LLMs. The runtime under most local-LLM setups, including Ollama.