openinsurance

Open Insurance AI · HiTheo

theo

One API key. Ten intelligent engines. Theo routes every prompt to the perfect model, automatically.

10

Engines

<1ms

Fast-Path

Failover

1

API Key

The multi-model problem

You're building with AI. You shouldn't need a PhD in prompt engineering and 7 vendor relationships to ship.

7 API KEYS

Every provider has its own SDK, auth, billing dashboard, and rate limits. You're managing 7 relationships just to cover your use cases.

NO ROUTING

You're hardcoding model selection. One for code, another for chat, another for images — all manual, all fragile.

FRAGMENTED BILLING

4 billing dashboards. 4 invoices. No unified view of what you're spending or which requests cost the most.

VENDOR LOCK-IN

Built your whole app on one provider's SDK. Now they raise prices 40% and you're rewriting everything.

Theo solves all four ↓

How it works

Every request flows through six stages. Your prompt in, the perfect engine out, automatically.

YOUR PROMPT
CLASSIFY
LOAD SKILLS
ROUTE TO ENGINE
AGENT LOOP
RESPONSE
<1ms fast-path<500ms first token3-provider failover100% transparent

Intelligent routing

Intent classification in <1ms. The right model for every request, every time.

Theo Fastfast

Sub-200ms chat, classification, translation

Theo Thinkthink

Deep reasoning, structured planning, analysis

Theo Codecode

128K output, production-quality code generation

Theo Imageimage

Photorealistic and artistic image generation

Theo Videovideo

5–15s video clips from text or image

Theo Researchresearch

Multi-step web research with citations

Theo Roastroast

Unfiltered humor and creative writing

Why Theo's routing is different

INTENT-FIRST, NOT KEYWORD-FIRST

Regex fast-path classifies obvious intents in <1ms. Ambiguous prompts fall through to an LLM classifier that understands context — no keyword matching required.

AUTOMATIC COST OPTIMIZATION

Simple questions route to Theo Fast. Complex reasoning routes to Theo Think. You save significantly on routine queries without any configuration.

<1ms REGEX FAST-PATH

Server-side keyword matching runs before the LLM classifier. If patterns match with high confidence, classification completes in under 1ms with zero model calls.

3-PROVIDER FAILOVER CHAIN

Redis-backed circuit breaker routes through three independent provider tiers. Each engine also has a per-mode fallback. Your users never see downtime.

What developers build

Real scenarios. Real code. See what Theo makes possible.

AI-POWERED SAAS CHATBOT

Ship an intelligent chatbot in your SaaS product. Theo picks the right model per message — fast responses for simple questions, deep reasoning for complex ones.

MULTI-MODEL CONTENT PIPELINE

Generate blog posts, images, and social media cards from a single prompt. Theo chains the right modes: Code for copy, Image for visuals, Fast for meta tags.

CUSTOMER SUPPORT WITH MEMORY

Build support that remembers. Theo persists user context across sessions and channels — your customer never repeats themselves.

INTERNAL TOOLS & CODE GEN

Let your team generate dashboards, scripts, and data pipelines with natural language. Theo Code writes production-ready code with 128K output tokens.

MULTI-CHANNEL BOT

One brain, every channel. Deploy the same AI assistant to Telegram, WhatsApp, and your web app. Same memory, same skills, same routing.

Three lines to ship

npm install @hitheo/sdk — then pick your use case.

Open Source · TypeScript · Full Docs

your-app.ts
import { Theo } from "@hitheo/sdk";

const theo = new Theo({ apiKey: "theo_sk_..." });

const res = await theo.complete({
  prompt: "Explain quantum computing simply",
  mode: "auto",  // → routes to Theo Fast
});

console.log(res.text);
console.log(res.model);   // "theo-fast"
console.log(res.cost);    // "$0.0003"

Executable Visual Intelligence

Build an E.V.I.

Your persona. Your skills. Theo's engine under the hood.

Your Persona

Replace Theo's personality with your own brand. Your users never see Theo — they see your AI.

Your Skills + Tools

Install marketplace skills for domain expertise. Pass inline tools for your product's actions.

Theo's Engine

Multi-model routing, intent classification, agent loop, memory, billing, caching — all handled.

Before & After

✗ Without Theo — 40+ lines

manual-orchestration.ts
const model = pickModel(prompt);
const tools = resolveTools(user);
const system = buildPrompt(persona, skills);
const res = await llmProvider.complete({ model, ... });
const toolResults = await executeTools(res);
const final = await llmProvider.complete({ ... });
await debitCredits(user, res.usage);
await logAudit(user, res);

✓ With Theo E.V.I. — 5 lines

evi-example.ts
import { Theo } from "@hitheo/sdk";

const theo = new Theo({ apiKey: process.env.THEO_KEY });

const evi = theo.evi({
  persona: "You are Eva, AcmeCorp's AI...",
  skills: ["insurance-quoting"],
  tools: [lookupCustomer, updatePolicy],
});

const res = await evi.complete({ prompt: "..." });

One API call. Everything handled.

Skill Store

An app store for AI capabilities. Install domain skills that give Theo specialized knowledge — or build and publish your own.

Insurance

Insurance Quoting

by hitheo

Compare rates across 5+ carriers in real-time.

1.2k installsInstall

Developer

Code Review

by hitheo

Analyze PRs for security and architecture anti-patterns.

3.4k installsInstall

Research

Deep Research

by hitheo

Multi-step web research with source synthesis.

2.8k installsInstall

Data

Data Extraction

by community

OCR + structured extraction from PDFs and images.

890 installsInstall

Content

Content Writer

by community

Blog posts, emails, social copy — adapted to your brand voice.

1.6k installsInstall

Custom

Custom Skill

by you

Define custom tools, knowledge bases, and workflows.

installsInstall

Build Your Own

my-skill.ts
import { defineSkill } from "@hitheo/sdk";

export default defineSkill({
  name: "inventory-check",
  description: "Real-time inventory lookup",
  tools: [checkStock, reorderAlert],
  knowledge: ["./product-catalog/*.json"],
});

// npx theo publish

Earn from your skills

Publish skills to the store. Other developers install and use them. You earn credits for every API call that activates your skill.

Works everywhere

Channel-agnostic core. Same brain, same memory, same skills — every channel. Open-source adapters. npm install and you're live.

Web AppTelegramWhatsAppREST APICustom

Bring Your Stack

Next.jsExpressFastifyVercelCloudflare WorkersAWS LambdaSupabaseBunDenoNode.js

Why Theo?

You could wire up multiple AI providers yourself. Here's what that looks like vs. Theo.

✗ Without Theo — 47 lines

without-theo.ts
const model = pickModel(prompt);
const tools = resolveTools(user);
const system = buildPrompt(persona, skills);
const res = await llmProvider.complete({ model, ... });
const toolResults = await executeTools(res);
const final = await llmProvider.complete({ ... });
await debitCredits(user, res.usage);
await logAudit(user, res);

✓ With Theo — 5 lines

with-theo.ts
import { Theo } from "@hitheo/sdk";

const theo = new Theo({ apiKey: "theo_sk_..." });

const res = await theo.complete({
  prompt: "Your prompt here",
  mode: "auto",
});
theo

Get started today

One API key. Every model. Automatic routing, failover, and billing. Ship your AI product faster.