Hobby
Single agent in production
- 1 agent · 100 builds/mo
- *.theo.app subdomain · 1 team member
- 1 month of Starter included on signup
You design how the agent thinks. The memory, knowledge, guardrails, observability, and scale around it are a whole AI platform — Theo runs it all. Live in ~7s.
Open-source primitives · Managed or self-hosted · Any LLM
$ npx create-theokit my-app
The agent was the goal.The infrastructure became the work.
Every layer of today's cloud was designed for web apps — request in, response out, stateless, a human on the other end. An agent is none of those things. It remembers, retrieves, decides, and acts.
Read the manifestoAny model · no lock-in
OpenAI, Anthropic, Google, Mistral, Llama, Ollama — 28 providers, swap anytime without rewriting your agent.
Apache-2.0 · TypeScript-first · open-core
The complete runtime
Define an agent, give it tools, and ship the whole loop in a few lines of TypeScript.
1import { Agent, defineTool } from "@theokit/sdk";2import { z } from "zod";4const refund = defineTool({5 name: "refund_order",6 description: "Refund an order by id",7 inputSchema: z.object({ orderId: z.string() }),8 handler: async ({ orderId }) => {9 await billing.refund(orderId);10 return `Refunded ${orderId}`;11 },12});14const agent = await Agent.create({15 model: "claude-sonnet-4-6",16 tools: [refund],17});19const run = await agent.send("Refund order #8814");
one agent · every capability in orbit
No orchestration framework to wire up — Agent.create gives it tools, agent.send runs it.
What your user sees
One conversation. Your user gets clean answers — you get memory, retrieval, real actions and guardrails, in one runtime.
Simple for them. The whole stack for you — one runtime, not five vendors.
How it works
From npx create-theokit to a live URL to production — one workflow.
Scaffold a working agent — memory, search and chat UI, built in.
Push to TheoCloud. Live URL in minutes, rollback in seconds.
Switch models, watch every call, keep state — without a redeploy.
Commercial · Early access
Built on Postgres — embeddings, vector search, generation, ranking and natural-language queries as SQL functions. One database for your data and your AI — no ETL to a separate vector store. The data layer under TheoCloud, also sold on its own.
Everything, one database
The full AI surface — embeddings to natural-language queries — in the database your ORM already speaks.
Indexes
Search
AI in SQL
Postgres-native
One database for your data, your vectors, and your AI — no glue, no second system.
Pricing
Start free, upgrade when an agent is doing real work. Every tier uses your own AI provider keys — Theo never sees your prompt.
Single agent in production
Early production agent
Sustained user traffic
Teams · multiple agents
An agent is one deployed agent app — its own URL, sessions, and memory. 1 build = one deploy: each `theo deploy` you run, or each push that triggers an auto-deploy. Memory and search limits are per month — full quotas in the plan matrix.
The runtime for AI Native Companies
Hobby is free forever. Your code, your keys, your data.
No card required. Cancel anytime on paid tiers.
$ npx create-theokit my-app