Openwork
OpenWork is an open-source, enterprise-ready alternative to Claude Cowork — a desktop application and agent runtime, built as a GUI for OpenCode, that lets people work on their local files with AI agents using any of 50+ model providers and their own keys. Teams package skills, MCP servers, plugins, and configs into shareable one-click setups, and administer rollout, SSO, audit, and policy through OpenWork Den, the cloud control plane. The Den API (OpenAPI 3.1, 214 operations) exposes organizations, members, roles, SSO and SCIM provisioning, connectors, capability sources, LLM providers, workers, marketplaces, plugins, and MCP connections, secured by session bearer tokens and organization API keys with an OAuth 2.0 / OIDC authorization server.
Real signal across most facets with visible, nameable gaps — the contract exists but is thin, or the portal is good while governance and commercial terms are absent.
API Evangelist profiles Openwork the way a machine reads it — 43 machine-readable artifacts across 37 APIs, pulled from the provider's own public surface and indexed so a developer, an analyst, or an AI agent can evaluate it against every other provider on the network.
Every provider in the network is reduced to the same set of machine-readable artifacts — OpenAPI contracts, event specifications, GraphQL schemas, runnable collections, pricing and rate-limit signals, security posture, OAuth scopes, and the agent surfaces (MCP servers and skills) that let software drive the API on its own. We profile them because the interface is the part of a company you can actually inspect: it is a truer signal of what a provider does than any marketing page. From those artifacts we compute the Kin Score — Openwork scores 50.8/100 (developing), with a separate agent-readiness read of 61/100 (agent native). The full breakdown is below, followed by every artifact we hold — each card links through to its machine-readable definition on apis.io.
Kin Score
This is the API Evangelist rating — a single, repeatable read computed from the artifacts on this page. Green fill is points earned; the red track is points possible, so every bar shows earned-versus-possible at a glance.
Kin Score
How this is scored →scored 2026-07-27 · rubric v0.5
How we profile Openwork
Each block below is one kind of artifact we hold for Openwork. For each we say what it is and why it earns a place in the profile, then list every one we've indexed — capped at two rows, scroll within the panel for the rest.
APIs 37
Each API is captured as its own OpenAPI definition — every operation, parameter, and response. This is the single most useful machine-readable description of what an API does, and it's what lets us score, lint, mock, and generate against it without asking the provider for anything.
Individual APIs this provider publishes, each with its own machine-readable definition.
Openwork Admin API
Administrative reporting routes.
Openwork API Keys API
Organization API key management routes.
Openwork Auth API
The Auth API from Openwork — 11 operation(s) for auth.
Openwork Authentication API
The Authentication API from Openwork — 19 operation(s) for authentication.
Openwork Bootstrap API
Agent-first provisional workspace setup routes.
Openwork Capability Sources API
The Capability Sources API from Openwork — 25 operation(s) for capability sources.
Openwork Config Objects API
The Config Objects API from Openwork — 12 operation(s) for config objects.
Openwork Connectors API
The Connectors API from Openwork — 21 operation(s) for connectors.
Openwork Desktop Policies API
The Desktop Policies API from Openwork — 2 operation(s) for desktop policies.
Openwork Dev API
The Dev API from Openwork — 2 operation(s) for dev.
Openwork Diagnostics API
The Diagnostics API from Openwork — 2 operation(s) for diagnostics.
Openwork GitHub API
The GitHub API from Openwork — 11 operation(s) for github.
Openwork Inference API
The Inference API from Openwork — 1 operation(s) for inference.
Openwork Invitations API
Invitation preview, acceptance, creation, and cancellation routes.
Openwork LLM Providers API
Organization LLM provider catalog, configuration, and access routes.
Openwork Marketplaces API
The Marketplaces API from Openwork — 9 operation(s) for marketplaces.
Openwork Mcp API
The Mcp API from Openwork — 3 operation(s) for mcp.
Openwork Members API
Organization member management routes.
Openwork Memory API
The Memory API from Openwork — 3 operation(s) for memory.
Openwork Organizations API
Top-level organization creation and context routes.
Openwork Plugins API
The Plugins API from Openwork — 10 operation(s) for plugins.
Openwork Register API
The Register API from Openwork — 1 operation(s) for register.
Openwork Resources API
The Resources API from Openwork — 1 operation(s) for resources.
Openwork Roles API
Organization custom role management routes.
Openwork SCIM API
Organization SCIM connector management routes.
Openwork Skill Hubs API
Organization skill hub management and access routes.
Openwork Skills API
Organization skill authoring and sharing routes.
Openwork SSO API
Organization single sign-on connector management routes.
Openwork System API
Service health and operational routes.
Openwork Teams API
Organization team management routes.
Openwork Telemetry API
Telemetry event ingestion and adoption analytics.
Openwork Users API
Current user and membership routes.
Openwork Webhooks API
The Webhooks API from Openwork — 2 operation(s) for webhooks.
Openwork .well Known API
The .well Known API from Openwork — 8 operation(s) for .well known.
Openwork Worker Activity API
Worker heartbeat and activity reporting routes.
Openwork Worker Runtime API
Worker runtime inspection and upgrade routes.
Openwork Workers API
Worker lifecycle, billing, and runtime routes.
Scroll within the panel for all 37 ·
MCP Servers 1
Model Context Protocol servers expose these APIs directly to AI agents. We profile them because agent-native access is the fastest-growing way this provider's capabilities actually get used.
Model Context Protocol servers that expose these APIs to AI agents.
openwork-mcp.yml
MCP SERVEREvent Specifications 1
Not every API is request/response. AsyncAPI describes the event-driven and streaming side — the webhooks and channels — so the asynchronous half of the interface is documented the same way the synchronous half is.
AsyncAPI definitions for this provider's event-driven and streaming APIs.
Openwork Webhooks
ASYNCAPISecurity Posture 3
Authentication, domain security, vulnerability disclosure, and trust-center signals — the evidence that a provider takes security seriously enough to document it. We profile it because you can't govern what you can't see.
Authentication, domain security, vulnerability disclosure, and trust-center signals.
Scopes 1
OAuth scopes are the vocabulary of least-privilege access. Profiling them shows exactly what an integration — or an agent acting on a user's behalf — is allowed to do.
OAuth scopes governing access to this provider's APIs.
Resources
Every other property we hold for Openwork — documentation, portals, status pages, policies, and corporate surface — grouped by the job it does, following the integrator's arc from getting started to running in production.
Get Started 1
Portal, sign-up, and the first successful call
Documentation 2
Reference material describing how the API behaves
Agent Surfaces 4
MCP servers, agent skills, and machine-readable catalogs
Design & Contract 6
Pagination, idempotency, versioning, errors, and events
Build 4
SDKs, sample code, and the tooling you integrate with
Access & Security 5
Authentication, authorization, and security posture
Operate 2
Status, limits, changes, and where to get help
Commercial 3
Pricing, plans, and the legal terms of use
Company 1
The organization behind the API
Other 2
Properties that don't map to a standard resource type
← All providers · Data indexed from github.com/api-evangelist/openwork · machine-readable index on apis.io