api.
Everything we've published on api across guides, agents, hardware reviews and glossary entries — 9 entries in total.
Guides (2)
- Kimi Coding Provider + User-Agent SpoofNetwork · 2026-02-18
Configure Kimi Coding API provider for OpenClaw with correct endpoint, User-Agent spoof, and reasoning mode disabled.
- Dashboard via hijack.js (HTTP Intercept)Gateway · 2026-02-18
Inject custom dashboard and status API endpoints into OpenClaw's HTTP server via hijack.js monkey-patching.
Hardware (3)
- Raspberry Pi 5
The default starting point for pocket AI in 2026. 4–8 GB of LPDDR4X, ARM Cortex-A76, sub-€100, runs Hermes Agent (no browser tool) or Nanobot comfortably.
- Intel NUC 13 / Mini PC
Mini PCs at €300–600 with i5/i7 + 16–32 GB RAM. The sweet spot for self-hosted AI agents that need browser automation and decent local model performance.
- Old Android phone (Moto E2 et al.)
The PocketClaw origin story device. €15–30 used. Genuinely runs lightweight agents via Termux + proot, with serious caveats.
Glossary (4)
- BYOK (Bring Your Own Key) — Pricing pattern where a user supplies their own LLM API keys to a self-hosted or managed agent.
- OpenRouter — LLM API gateway providing a unified interface across Anthropic, OpenAI, Google, Mistral and many open models.
- Local LLM — Language model running on local hardware rather than via cloud API. Llama, Qwen, Mistral local variants.
- Ollama — Local LLM runtime that exposes an OpenAI-compatible API over local model weights.