Built by agents. Readable by humans.
Your coding agent builds your company’s software on SegmentStream: Claude Code, Codex, Cursor or any other. A workspace is one git repository with typed SDKs for the database, the apps, the data and the company agent, and one deploy runs it. The CLI and MCP give agents the same operations and permissions as people.
curl -fsSL https://segmentstream.com/install.sh | shmacOS and Linux. Then give this prompt to your agent, or point it at /agents.md.
Paste one prompt. Your agent does the rest.
It installs the CLI, signs in, reads the platform’s rules and your workspace’s AGENTS.md, builds what you described and deploys it. Every workspace keeps those instructions current with segmentstream upgrade.
Build our company's software on SegmentStream.1. Install the CLI: curl -fsSL https://segmentstream.com/install.sh | sh2. Sign in with `segmentstream login` (or set SEGMENTSTREAM_API_KEY), then pick our organization: `segmentstream org list`, then `segmentstream org use <organization-id>`.3. Read https://segmentstream.com/agents.md, then the AGENTS.md in the workspace repository, before you write any code.4. Build this: <describe what your team needs>.5. Deploy with `segmentstream deploy` and tell me what changed.The building surface
Four SDKs, one per kind of folder, plus the CLI, and the API and MCP server every app serves. Everything a person can do here, an agent can do with the same calls.
Ontology SDK
@segmentstream/ontology
Entities, actions and roles; REST, OpenAPI and MCP from one model
App SDK
@segmentstream/app
Email-code sign-in, roles, records and warehouse data for Next.js
Pipeline SDK
segmentstream-pipeline (Python)
Connections, ingestion, models, checks and schedules in Python
Agent SDK
@segmentstream/agent
The company agent: ontology tools as the member, in your team’s channels
CLI
segmentstream
Workspaces, deploys, members, jobs and data from the terminal
MCP and API
/mcp and /api/ontology on every app
REST, OpenAPI and MCP on every app, per caller
Your software on top. Five folders underneath.
A workspace is one git repository with five folders. Each folder is a typed building block, and the platform runs each one: the app, the ontology behind it, the pipelines and warehouse, the connections and the company agent. A CRM, a finance tool or a dashboard is what your agent builds from them.
What you build
app/
The app your team opens
ontology/
Postgres, the API and MCP tools
pipeline/
Scheduled pipelines and a warehouse
connections/
A vault for every credential
agent/
An agent runtime with channels
Every workspace starts with all of it running: a deployed app with sign-in, a database under the ontology, a warehouse, a vault and the console.
Your agent writes the business part in the five folders, from typed building blocks, and deploys. You review the change like any other code.
Or our engineers build the first version with you during a pilot, in your own repository.
From zero to a deployed workspace.
A new workspace comes with the starter: an app with sign-in, an ontology, a pipeline and the docs your agent reads. Clone its repository, deploy, and invite your team.
$ curl -fsSL https://segmentstream.com/install.sh | sh$ segmentstream login$ segmentstream org list$ segmentstream org use org_YOUR_ID # an organization ID from the list$ segmentstream workspace create acme --region eu --subdomain acme$ segmentstream workspace WORKSPACE-ID clone acme && cd acme# your coding agent builds what your team needs$ git add -A && git commit -m "First version"$ segmentstream deploy$ segmentstream ontology member invite ada@example.com --role sales$ segmentstream ontology mcp # connect your agent to the appFive folders are the whole workspace.
Each folder owns its dependencies and deploys together with the others. The instructions your agent needs ship in the repository.
acme/├─ AGENTS.md # what your agent reads first├─ .agents/skills/ # ontology, app-auth, app-data, connections, ...├─ app/ # Next.js app: the screens your team opens├─ ontology/ # entities, actions and roles│ └─ index.ts # export default defineOntology({ ... })├─ pipeline/│ ├─ ingestion/ # one asset per file│ ├─ models/ # bronze, silver, gold│ └─ definitions.py # jobs and schedules├─ connections/│ └─ connections.py # the tools you keep├─ agent/ # the company agent└─ docs/What deploy gives you
Deploy the five folders and the platform runs them: the app with sign-in, Postgres under the ontology with its API and MCP tools, pipelines and a warehouse, the connection vault and the company agent. The console shows all of it.
The whole workspace is a git repository you own: the app, the ontology, pipelines, connections, events and the agent. Clone it with git; every push to main deploys that exact commit.

Developer tools, agent-first
Everything a person can do here, an agent can do too.
CLI
Create and link workspaces, deploy, invite members, run and backfill jobs, inspect lineage and query the warehouse, with JSON output for agents and CI.
More →MCP and API
Every app serves its ontology at /mcp and /api/ontology. Agents sign in as the person and see only the tools that person's roles allow.
More →Agent guide
AGENTS.md and docs in every workspace repository: the layout, the platform rules and the commands your agent may run.
Agent skills
Skills for the work agents do most: the ontology, app sign-in, app data, connections, ingestion, models and the agent, versioned in the repository.
Docs that stay current
segmentstream upgrade brings the SDKs, guide, docs and skills up to date with the installed CLI, keeping the edits you made.
Your repository
A private git repository per workspace. Clone it with plain git; a deploy runs one exact commit.
More →What the code looks like
This is the shape of the code in a workspace, from the published SDKs. Your agent writes it; you review it like any other change.
.actions((self) => ({ win: action({ description: "Mark the lead as won.", input: Schema.Struct({ lead: self.ref }), // Requires lead:win: <entity>:<action name>. handler: ({ input }) => Effect.gen(function* () { const lead = yield* self.get(input.lead, { forUpdate: true }); if (lead.status === "won") { return yield* new ActionRejected({ message: "The lead is already won." }); } yield* self.update(lead, { status: "won" }); }), }),}));const { items, nextCursor } = await segmentstream.ontology.lead.find({ where: { status: { in: ["new", "contacted"] } }, orderBy: [{ field: "createdAt", direction: "desc" }], include: { owner: true }, limit: 20,});const { result, validation } = await segmentstream.ontology.lead.actions.changeStatus( { lead: id, status: "contacted" },);@s.model( tier=s.Tier.Gold, partitioning=s.Partitioning.Daily(column="order_date", start_date="2026-01-01"), schema={"order_date": "date", "customer_count": "int64", "total_revenue": "float64"},)def revenue_summary(customer_revenue: ir.Table) -> ir.Table: return customer_revenue.group_by("order_date").aggregate( customer_count=customer_revenue.count(), total_revenue=customer_revenue.revenue.sum(), )// agent/agent/extensions/segmentstream.tsimport { segmentstream } from "@segmentstream/agent/extension";import config from "../../segmentstream.json";export default segmentstream(config);// agent/segmentstream.json{ "channels": { "telegram": { "connection": "telegram", "policy": "smart" } }}What the platform supports
What people, and the coding agents working for them, ask before they move an app here.
Can people open an app's pages without signing in?
Yes. The paths you list in publicPaths in app/src/proxy.ts are open to anyone, such as a landing page or a public form, and each covers the paths under it, so '/' opens the whole app; every other page asks for sign-in. By default only the members you invite sign in, with an email code. The ontology's signUp lets strangers sign up by email, Telegram or WhatsApp with the roles you name. Apps and sign-in
Can visitors of a website talk to the agent without an account?
Yes. Declare guest in the ontology with your website's address, and its visitors chat with the company agent without an account, with only the permissions you give guests, an optional bot check, and daily limits on turns and model spend. Company agent
Can an app use our own domain?
Yes. Every app is online at your-name.segmentstream.app. To serve it at a domain you own, run segmentstream domain connect example.com, publish the DNS records it prints, declare the host in app/domains.json and deploy; HTTPS, sign-in and redirects follow. segmentstream domain buy orders a new domain for the workspace. Your own domain
Which framework does an app use?
Next.js with the App Router, version 16.4.1 or later, and React 19. The app is the app/ folder of the workspace's git repository, and segmentstream deploy builds and hosts it. App SDK
Where does an app keep its data?
In the company database: the entities declared in ontology/, each changed through an action that checks roles and keeps history. Files are stored on records. The app's own file system does not keep anything between requests, so an app writes no data files. Ontology
Where does work that takes minutes run?
In a workflow. It starts on a schedule, after an action changes a record, from a webhook, or from the app, and runs durable steps that are retried on their own, so work that takes minutes, such as writing a report, does not depend on a request staying open. Pipeline jobs are for warehouse data. Workflows
How does code call an AI model such as Claude?
Through AI Gateway: a workflow step calls a model with the AI SDK, and the company agent uses the model you name per role. There is no API key to create or store. Models from OpenAI, Anthropic, Google, xAI, Mistral and others are billed at each provider's list price with no markup. AI Gateway
Where do credentials for other services go?
In connections. A connection to an ad platform, a CRM or any other API authorizes through SegmentStream's approved application or your own, and its calls go through the platform, so the credential never reaches the code, its logs or an agent's context. Values pipeline code needs are named workspace secrets. Connections
How much does it cost?
Usage-based, in US dollars, with no seats: compute at $0.30 per SSU, plus storage, warehouse queries, events and data transfer at published rates, and AI models at list price. New accounts start with $20 of platform usage, with no card needed. Pricing
Can a coding agent check what the platform supports before it builds?
Yes, with the CLI: segmentstream init ./segmentstream-starter writes the workspace starter without signing in or going online, and its AGENTS.md, docs/ and .agents/skills/ describe every part of the platform. An agent in a sandbox that cannot reach segmentstream.com asks the person to allow that domain in the sandbox's network settings. Instructions for coding agents
Your company's software, in a repository you own.
Every workspace owns a private git repository with its folders and their full history. Clone it with plain git, keep a copy on GitHub, take it with you. segmentstream deploy, or a push to main, deploys that exact commit. If a deploy fails, production keeps serving the last good one.
One repository, one workspace
Commit, then deploy
$ segmentstream workspace WORKSPACE-ID clone acme$ cd acme# Your agent edits the folders; you review the diff.$ git add -A && git commit -m "Add contract approvals"$ segmentstream deployThe deploy checks every folder first: the ontology's changes are planned against the live database and tried on a copy, and unsafe changes are refused before anything applies.
Build your company’s own software. Let agents run it.
$ segmentstream workspace create acme --region eu --subdomain acme
▸ Created workspace acme · database, warehouse and a private git repository
$ segmentstream workspace WORKSPACE-ID clone acme && cd acme
▸ your coding agent builds what your team asked for and runs the checks
$ git add -A && git commit -m "First version"
$ segmentstream deploy
▸ app, company agent, API and MCP tools live for your invited members
Our engineers build the first version on your data in two weeks, at a fixed price.
Or build it yourself with your coding agent:
curl -fsSL https://segmentstream.com/install.sh | sh