OpenClaw

OpenClaw is an active Spawnfile runtime with a JSON config file and a rich markdown workspace layout. It supports multi-agent operation through native sessions, but Spawnfile v0.1 does not inject its own team router.

Status: Active

Config Shape

OpenClaw uses a JSON configuration file at ~/.openclaw/openclaw.json. The adapter emits a config file that maps Spawnfile execution intent to OpenClaw’s native structure.

Key config areas:

• Agent model selection (agent.model)
• Auth profile configuration
• Session state and model persistence

The short-form runtime: openclaw in a Spawnfile normalizes internally to:

runtime:
  name: openclaw
  options: {}

The long form allows adapter-specific options:

runtime:
  name: openclaw
  options:
    profile: default

Workspace Layout

OpenClaw uses ~/.openclaw/workspace as its workspace root. The adapter places Spawnfile docs into this structure:

Spawnfile Role	OpenClaw File
identity	IDENTITY.md
soul	SOUL.md
system	AGENTS.md
memory	MEMORY.md
heartbeat	HEARTBEAT.md
extras.*	Placed by key name (e.g. USER.md)

Skills are placed under ~/.openclaw/workspace/skills/<skill>/SKILL.md, matching the workspace skill model.

Model Mapping

The adapter maps execution.model.primary to the agent’s default model setting:

# Spawnfile
execution:
  model:
    primary:
      provider: anthropic
      name: claude-sonnet-4-5

Fallback models are mapped only if the runtime path supports them. Auth handling remains runtime-native and adapter-specific.

MCP Handling

OpenClaw supports MCP through an mcporter bridge layer rather than a pure first-class MCP config surface. The adapter compiles logical Spawnfile MCP declarations into OpenClaw’s MCP bridge or plugin-native config.

ACPX runtime paths can inject named MCP server maps, which gives the adapter a target for MCP lowering.

Workspace and Sandbox

• The main session can run on the host
• Non-main sessions can be sandboxed in Docker
• Workspace root is explicit and configurable

The adapter maps workspace.docs, workspace.resources, and execution.sandbox.mode to OpenClaw’s workspace and session sandboxing configuration.

Teams

OpenClaw does not have a native team manifest. What it has:

• Multi-agent sessions
• Agent-to-agent session tools

The adapter lowers Spawnfile team members into runtime-native agents/sessions where possible and reports degradation when native semantics do not preserve Spawnfile representatives, context artifacts, or team networks.

Nested teams and full native team identity are reported as degraded.

Surfaces

OpenClaw has the strongest chat-surface support among the active runtimes. Discord, Telegram, WhatsApp, and Slack are supported with pairing, allowlist, and open access modes. Portable HTTP is not part of the v0.1 alpha surface contract.

Discord

Spawnfile lowers Discord access into OpenClaw’s rich config surface:

• dmPolicy
• groupPolicy
• allowFrom
• guilds
• guilds.*.channels

Mode	Support
pairing	Supported
allowlist	Supported (users, guilds, channels)
open	Supported

Channel allowlists currently require exactly one guild in the Spawnfile lowering.

Telegram

Spawnfile lowers Telegram access into the same rich OpenClaw channel surface:

• dmPolicy
• groupPolicy
• allowFrom
• groups

Mode	Support
pairing	Supported
allowlist	Supported (users, chats)
open	Supported

WhatsApp

Spawnfile lowers WhatsApp access into OpenClaw’s channel surface:

• dmPolicy
• groupPolicy
• allowFrom
• groups

Mode	Support
pairing	Supported
allowlist	Supported (users, groups)
open	Supported

WhatsApp does not have a portable token secret. QR/session auth is runtime-defined.

Slack

Spawnfile lowers Slack access into OpenClaw’s channel surface using socket mode:

• mode: socket
• dmPolicy
• groupPolicy
• allowFrom
• channels

Mode	Support
pairing	Supported
allowlist	Supported (users, channels)
open	Supported

Slack requires both bot_token_secret and app_token_secret.

What The Adapter Emits

For a single agent, the adapter emits:

• An OpenClaw JSON config file
• Workspace markdown files mapped from Spawnfile doc roles
• Skill directories with SKILL.md files
• MCP bridge configuration

For container compilation, the adapter provides container metadata including:

• The standalone base image
• System dependencies
• Config and workspace paths inside the container
• The start command
• Port and environment configuration

Container Notes

• Container output has been verified from the host, not only inside Docker.
• The generated runtime must bind to a host-reachable gateway setting for Docker port publishing to work.
• Compiled output places config and workspace files into final runtime paths at build time. The entrypoint only needs validation and startup.
• Host-side smoke checks use the control UI root path and /healthz.

Example

From the single-agent fixture:

spawnfile_version: "0.1"
kind: agent
name: analyst

runtime: openclaw

execution:
  model:
    primary:
      provider: anthropic
      name: claude-sonnet-4-5
  sandbox:
    mode: workspace

workspace:
  docs:
    identity: IDENTITY.md
    soul: SOUL.md
    system: AGENTS.md
    memory: MEMORY.md
    heartbeat: HEARTBEAT.md
  skills:
    - ref: ./skills/web_search
      requires:
        mcp:
          - web_search

environment:
  mcp_servers:
    - name: web_search
      transport: streamable_http
      url: https://search.mcp.example.com/mcp
      auth:
        secret: SEARCH_API_KEY