OpenSpace/openspace/host_skills

Host Skills Integration Guide

This guide covers agent-specific setup for integrating OpenSpace. For installation and general concepts, see the main README.

Pick your agent:

Agent	Setup Guide
nanobot	Setup for nanobot
openclaw	Setup for openclaw
Other agents	Follow the generic setup in the main README

---

Setup for nanobot

1. Copy host skills

cp -r host_skills/skill-discovery/ /path/to/nanobot/nanobot/skills/
cp -r host_skills/delegate-task/ /path/to/nanobot/nanobot/skills/

2. Add MCP server to ~/.nanobot/config.json

{
  "tools": {
    "mcpServers": {
      "openspace": {
        "command": "openspace-mcp",
        "toolTimeout": 1200,
        "env": {
          "OPENSPACE_HOST_SKILL_DIRS": "/path/to/nanobot/nanobot/skills",
          "OPENSPACE_WORKSPACE": "/path/to/OpenSpace",
          "OPENSPACE_API_KEY": "sk-xxx"
        }
      }
    }
  }
}

Tip

LLM credentials are auto-detected from nanobot's providers.* config — no need to set OPENSPACE_LLM_API_KEY.

---

Setup for openclaw

openclaw ships with a built-in skills/openspace/ skill — no need to copy host_skills.

Note

openclaw's built-in skill merges skill-discovery + delegate-task into a single SKILL.md with scenario sub-pages. It uses mcporter call openspace.<tool> syntax. The underlying MCP tools are identical.

1. Register MCP server

openclaw uses mcporter as its MCP runtime:

mcporter config add openspace --command "openspace-mcp"

2. Configure env vars

Set in ~/.openclaw/openclaw.json:

{
  "skills": {
    "entries": {
      "openspace": {
        "env": {
          "OPENSPACE_HOST_SKILL_DIRS": "/path/to/openclaw/skills",
          "OPENSPACE_WORKSPACE": "/path/to/OpenSpace",
          "OPENSPACE_API_KEY": "sk-xxx"
        }
      }
    }
  }
}

Or set as system env vars (e.g. ~/.openclaw/.env).

---

Environment Variables (Agent-Specific)

The three env vars in each agent's setup above are the most important. For the full env var list, config files reference, and advanced settings, see the Configuration Guide in the main README.

What needs OPENSPACE_API_KEY?

Capability	Without API Key	With API Key
execute_task	✅ works (local skills only)	✅ + cloud skill search
search_skills	✅ works (local results only)	✅ + cloud results
fix_skill	✅ works	✅ works
upload_skill	❌ fails	✅ uploads to cloud

All tools default to "all" (local + cloud) and automatically fall back to local-only if no API key is configured. No need to change tool parameters.

---

How It Works

Your Agent (nanobot / openclaw / ...)
  │
  │  MCP protocol (stdio)
  ▼
openspace-mcp              ← 4 tools exposed
  ├── execute_task           ← multi-step grounding agent loop
  ├── search_skills          ← local + cloud skill search
  ├── fix_skill              ← repair a broken SKILL.md
  └── upload_skill           ← push skill to cloud community

The two host skills teach the agent when and how to call these tools:

Skill	MCP Tools	Purpose
skill-discovery	search_skills	Search local + cloud skills → decide: follow it yourself, delegate, or skip
delegate-task	execute_task search_skills fix_skill upload_skill	Delegate tasks, search skills, repair broken skills, upload evolved skills

Skills auto-evolve inside execute_task (FIX / DERIVED / CAPTURED). After every call, your agent reports results to the user via its messaging tool.

Note

For full parameter tables, examples, and decision trees, see each skill's SKILL.md directly.