Use ColabHive with SuperClaw / OpenCode

SuperClaw is Intel's hybrid, local-first agentic AI: it runs agents on the AI PC and keeps sensitive, high-frequency work on-device, while offloading heavy reasoning to a cloud model. ColabHive is a natural fit for that cloud tier — an OpenAI-compatible, Intel-Arc-native inference cloud — so the whole stack stays Intel silicon, edge to cloud.

Because SuperClaw is built on OpenCode, the same setup works for OpenCode, Claude Code, and any OpenAI-compatible agentic client.

Why ColabHive as the cloud tier

• OpenAI-compatible with tool calling. Agents pass their tools; the model returns tool_calls; the agent executes them locally. See Tool Calling.
• Arc-native. The heavy tier runs on Intel Arc GPUs instead of requiring every user to operate a dedicated multi-GPU workstation — elastic and pay-per-use.
• Private lanes for regulated data. Run the cloud tier on your own Arc hardware so data never leaves your perimeter — combined with SuperClaw's local PII handling, you get frontier-class reasoning with full data residency.

Configure ColabHive as the cloud provider

In SuperClaw → Advanced → Model Routing, add a cloud model provider with:

Field	Value
Base URL	https://api.colabhive.com/v1
API key	your ColabHive key (hive_...) — see Authentication
Model	a tool-capable model id, e.g. qwen-2.5-7b-instruct

OpenCode / Claude Code use the same coordinates as an OpenAI-compatible provider:

{
  "provider": {
    "colabhive": {
      "npm": "@ai-sdk/openai-compatible",
      "name": "ColabHive — Intel Arc Cloud",
      "options": {
        "baseURL": "https://api.colabhive.com/v1",
        "apiKey": "{env:COLABHIVE_API_KEY}"
      },
      "models": { "qwen-2.5-7b-instruct": { "name": "Qwen2.5 7B Instruct (ColabHive)" } }
    }
  }
}

Verify the connection:

curl https://api.colabhive.com/v1/chat/completions \
  -H "Authorization: Bearer $COLABHIVE_API_KEY" -H "Content-Type: application/json" \
  -d '{"model":"qwen-2.5-7b-instruct","messages":[{"role":"user","content":"hello"}]}'

Drive the ColabHive platform from your agent (MCP)

Beyond the cloud model, your agent can call ColabHive's platform — fine-tune on proprietary data, run specialists (embeddings, rerank, forecasting), deploy a model as an endpoint — via the Model Context Protocol. This complements the chat model: the model reasons, MCP tools act on the platform.

The MCP server exposes two kinds of tools, and they follow different naming conventions:

• Built-in management tools — snake_case (e.g. list_endpoints, run_inference, list_trainable_models, create_training_run). These are fixed and documented in the MCP tools reference.
• Action tools — one per public endpoint, named by its kebab-case slug (which is the endpoint's endpoint_name, e.g. qwen-2.5-7b-instruct-public, embeddings-public). These are discovered live from the catalog, so the exact set is whatever is public right now.

Notes

• Pick a model whose tool calling is enabled (see Tool Calling).
• For the lowest latency, keep your model warm; cold starts incur a one-time load.
• For data-residency deployments, ask about private lanes so the heavy tier runs on your own Arc nodes.