Embedded deployment
Expose the same Agent through an independent menu entry and an optional Context-aware floating assistant. Both share the enterprise-system Cookie identity; only the floating interface needs the strict page-change bridge.
Choose the deployment shape, then wire providers.
AtlasClaw supports two practical shapes: embedding access to one AI assistant into an Enterprise System, or running as a standalone multi-user AI agent layer above multiple enterprise systems.
Modes
Embedded and standalone.
Standalone deployment
Best when the enterprise needs one SSO-backed multi-user AI agent entry point above multiple systems.
Configuration basics
The runtime is anchored around providers_root.
{
"providers_root": "../atlasclaw-providers/providers",
"service_providers": {
"jira": {
"cloud": {
"base_url": "https://company.atlassian.net",
"token": "${JIRA_API_TOKEN}"
}
},
"smartcmp": {
"prod": {
"base_url": "https://cmp.corp.com/platform-api",
"cookie": "${CMP_COOKIE}"
}
}
}
} Operational notes
Preserve governance boundaries.
- Use `providers_root` to load provider folders from the external providers repository.
- Keep secrets in environment variables, not committed JSON.
- Embedded access uses the enterprise-system Cookie identity. Independent menu access only needs an Enterprise System route; the floating interface additionally sends normalized path, nonce, and generation.
- Keep Context resolution and object actions inside AtlasClaw and Providers rather than sending business DTOs or calling Agent and Tool APIs from Enterprise System code.
- Use webhook mode for fire-and-forget system-to-system invocation with constrained Skills.
- Keep target-platform auth and audit in the provider and the downstream platform.