Use gald3r with OpenClaw

OpenClaw — an open-source, self-hosted AI agent gateway oriented around chat channels (Discord / Telegram / Slack / WhatsApp), not an in-editor IDE coding agent. It runs as a gateway process out of a per-user file workspace (default ~/.openclaw/workspace), with config at ~/.openclaw/openclaw.json.

Installing gald3r into an OpenClaw project writes the CRASH overlay this tool actually reads into .openclaw/ — the same task board, bug tracker, and gald3r <verb> CLI every other supported platform gets, wired the way OpenClaw itself expects it. Today that's commands partial, rules native, skills native, hooks not yet wired, MCP native via the gald3r engine's MCP (L2). Cheapest high-parity install: ship gald3r rule prose into AGENTS.md (operating rules) + SOUL.md (hard guardrails) — both load every session — and install gald3r g-skl-*/SKILL.md into the OpenClaw workspace skills/ dir (folder-per-skill is identical to gald3r; each user-invocable skill is automatically a /skill slash command). Re-declare MCP servers via openclaw mcp set.

Once installed, the same .gald3r/TASKS.md task board, bug tracker, and full gald3r <verb> CLI work identically to every other supported platform — OpenClaw is one of 37 platforms gald3r reads and writes today.

Get started

gald3r setup
gald3r platform install openclaw

Related

• OpenClaw technical reference
• Platform Support Matrix — every capability, honestly marked
• All gald3r-supported platforms
• Install gald3r