Computer Agents Cloud API
Exact request and response reference for the Agentic Compute Platform API. This surface is generated from the current OpenAPI contract and covers cloud deployments and local appliances across every public service, protocol callback, and documented operator route.
Direct HTTP requests use the canonical https://api.computer-agents.com/v1 base URL. Replace the origin with your appliance domain when running locally. Official SDKs accept either the deployment origin or an already-versioned /v1 URL.
Version and platform-level metadata endpoints
Health and monitoring endpoints
Authenticated API key creation, listing, rotation, and revocation
Authenticated account identity and destructive account-data deletion
Organization tenancy, membership, and governance
Team memberships, invitations, and resource sharing inside a workspace
Organization-scoped policy decisions, delegations, approvals, policy history, and decision audit
Organization OIDC and Microsoft Entra identity connections, group mappings, and SCIM credentials
SCIM 2.0 user and group provisioning for enterprise identity providers
Project management and workspace grouping
Task planning, board workflows, comments, sprints, releases, and task-to-thread execution
Conversation threads and message execution
Agent configuration and management
Reusable prompt templates, versions, and prompt library management
Persistent computer workspaces, runtime configuration, and container lifecycle
File and directory operations on computer and resource workspaces
Uploaded thread and workspace attachments stored in user computer workspaces
Custom user-defined skills with markdown instructions, files, and icons
Versioned Knowledge libraries and published document retrieval for people and agents
Agentic workflow automations composed from triggers, conditions, actions, services, loops, and notes
Durable, reorderable workload queue and manual shelf with capacity-aware release
Time-based automations and recurring or one-time execution schedules
Event-driven automations, webhook triggers, and trigger execution history
Multi-agent workflows with reusable orchestration graphs and orchestration runs
Versioned hidden prompt adaptation sets that can be attached to agents
Versioned evaluation datasets and evaluation runs
Versioned test plans, deterministic test runs, results, evidence, artifacts, and worker leases
Versioned release policies that bind Tests, Evaluations, and Agent Optimization evidence into auditable decisions
Agent-led improvement jobs based on evaluation sets
Durable bounded loops that propose, test, evaluate, assure, and promote exact saved candidates
Strict, content-addressed, saved-only Function and Metronome optimization candidates
Evidence-gated, content-addressed publication and deployment of accepted immutable candidates
Deployable and managed service surfaces exposed under /v1/servers
Always-on managed agent APIs, runtime deployments, logs, and invocation
Managed structured data stores, collections, documents, and analytics
GitHub repository security monitoring, exact-commit scan runs, findings, policy, and audit evidence
Human review and controlled promotion of scientific evidence extracted by Equal Care agents
Voice-agent configuration, sessions, calls, and realtime interaction controls
Local appliance discovery, workspace synchronization, commands, and bridge sessions
User budget, subscription, resource-billing preferences, and workspace inference settings
Cost analytics and thread-level usage breakdowns derived from ACP execution data
Connected mailbox search, reading, and sending for the Email skill
Push notification token registration and device-token management
Content reporting and moderation-report submission history
Administrative operations (requires admin key)