Terminal Use
Terminal Use is a deployment and orchestration platform for background AI agents — "Vercel for background agents." It gives agents that need long-lived task state, persistent files at /workspace, and production deployment primitives (versions, rollback, logs, environment secrets) a single runtime model and one deploy flow. Teams write agent code in Python with the AgentServer runtime, ship it with the tu CLI, then call deployed agents from their own app with the Python or TypeScript SDKs (including a Vercel AI SDK provider for streaming chat UIs). The platform is model- and framework- agnostic — run the Claude Agent SDK, Codex SDK, or your own framework inside sandboxed compute with forkable, shareable filesystems. The HTTP API exposes namespaces, projects, agents, branches, versions, tasks, events, messages, state, filesystems, schedules, secrets, API keys, and webhook keys. Terminal Use is a Y Combinator (W26) company founded by Vivek Raja, Filip Balucha, and Stavros Filosidis.
Limited machine-readable signal and partial portal coverage — documentation a human can read, but little a machine or agent can consume without scraping.
API Evangelist profiles Terminal Use the way a machine reads it — 33 machine-readable artifacts across 28 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 — Terminal Use scores 43.8/100 (thin), with a separate agent-readiness read of 80/100 (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 Terminal Use
Each block below is one kind of artifact we hold for Terminal Use. 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 28
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.
Terminal Use Agent APIKeys API
The Agent APIKeys API from Terminal Use — 4 operation(s) for agent apikeys.
Terminal Use Agent Task Tracker API
The Agent Task Tracker API from Terminal Use — 2 operation(s) for agent task tracker.
Terminal Use Agents API
The Agents API from Terminal Use — 7 operation(s) for agents.
Terminal Use API Keys API
The API Keys API from Terminal Use — 3 operation(s) for api keys.
Terminal Use Authentication API
The Authentication API from Terminal Use — 1 operation(s) for authentication.
Terminal Use Branch Events API
The Branch Events API from Terminal Use — 1 operation(s) for branch events.
Terminal Use Branches API
The Branches API from Terminal Use — 10 operation(s) for branches.
Terminal Use Builds API
The Builds API from Terminal Use — 3 operation(s) for builds.
Terminal Use CLI Authentication API
The CLI Authentication API from Terminal Use — 2 operation(s) for cli authentication.
Terminal Use Environments API
The Environments API from Terminal Use — 4 operation(s) for environments.
Terminal Use Events API
The Events API from Terminal Use — 2 operation(s) for events.
Terminal Use Filesystems API
The Filesystems API from Terminal Use — 9 operation(s) for filesystems.
Terminal Use Groups API
The Groups API from Terminal Use — 8 operation(s) for groups.
Terminal Use Logs API
The Logs API from Terminal Use — 3 operation(s) for logs.
Terminal Use Messages v2 API
The Messages v2 API from Terminal Use — 2 operation(s) for messages v2.
Terminal Use Namespaces API
The Namespaces API from Terminal Use — 5 operation(s) for namespaces.
Terminal Use OAuth API
The OAuth API from Terminal Use — 2 operation(s) for oauth.
Terminal Use Organizations API
The Organizations API from Terminal Use — 7 operation(s) for organizations.
Terminal Use Projects API
The Projects API from Terminal Use — 4 operation(s) for projects.
Terminal Use Raw Events API
The Raw Events API from Terminal Use — 1 operation(s) for raw events.
Terminal Use Registry API
The Registry API from Terminal Use — 1 operation(s) for registry.
Terminal Use Schedules API
The Schedules API from Terminal Use — 5 operation(s) for schedules.
Terminal Use Search API
The Search API from Terminal Use — 1 operation(s) for search.
Terminal Use Secrets API
The Secrets API from Terminal Use — 4 operation(s) for secrets.
Terminal Use States API
The States API from Terminal Use — 2 operation(s) for states.
Terminal Use Tasks API
The Tasks API from Terminal Use — 14 operation(s) for tasks.
Terminal Use Version Events API
The Version Events API from Terminal Use — 1 operation(s) for version events.
Terminal Use Versions API
The Versions API from Terminal Use — 6 operation(s) for versions.
Scroll within the panel for all 28 ·
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.
terminal-use-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.
Terminal Use Webhooks
ASYNCAPISecurity Posture 2
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.
Agentic Access 1
An x-agentic-access contract marks which operations are safe for an agent to run on its own and which need a human in the loop. It is the difference between an API an agent can use and one it can use safely.
Recommended x-agentic-access execution contracts for AI agents.
Resources
Every other property we hold for Terminal Use — 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 3
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 7
Pagination, idempotency, versioning, errors, and events
Scroll within the panel for all 7 ·
Build 4
SDKs, sample code, and the tooling you integrate with
Access & Security 2
Authentication, authorization, and security posture
Company 1
The organization behind the API
Other 1
Properties that don't map to a standard resource type
← All providers · Data indexed from github.com/api-evangelist/terminal-use · machine-readable index on apis.io