Skip to main content

Chucky SDK

Chucky provides Claude as a Service - a fully managed infrastructure for deploying AI agents powered by Claude. Build conversational AI applications without managing servers, handling authentication complexity, or worrying about scaling.

The Problem

Building AI features into your product sounds simple: call the API, get a response, show it to users. But once you ship, reality hits:
ChallengeWhat You Need to BuildTime
BillingUsage tracking, budget limits, Stripe metering, usage-based billing2-4 weeks
ExecutionSandboxed environments, file system isolation, process management4-8 weeks
ToolsTool execution routing, browser-to-server communication, error handling2-4 weeks
SessionsPersistence, context management, message history, resume logic1-2 weeks
That’s 9-18 weeks of infrastructure work before you can ship your AI feature.

The Chucky Solution

Chucky handles all of this with one SDK:
// Billing, execution, tools, sessions - all handled.
const client = new ChuckyClient({ token });
const result = await client.prompt('Deploy my code to production');
Built-in per-user billing: JWT tokens carry budgets. Enforcement happens at the edge.
const token = await createToken({
  userId: 'user-123',
  budget: createBudget({
    aiDollars: 5.00,    // User can spend up to $5
    computeHours: 1,    // And 1 hour of compute
    window: 'day',      // Resets daily
  }),
});
When the budget runs out, requests stop. No surprise bills.

Comparison

CapabilityDirect APIChucky
Per-user billingBuild it yourselfBuilt-in
Budget enforcementBuild it yourselfAutomatic
Code executionBuild it yourselfManaged sandbox
File operationsNot availableFull access
Shell commandsNot availableFull access
Browser toolsBuild it yourselfNative support
Local executionBuild it yourselfPossession Mode
Session persistenceBuild it yourselfAutomatic
Multi-turn contextBuild it yourselfAutomatic
Git integrationBuild it yourselfBuilt-in bundles

Who Uses Chucky

Agencies Billing Clients: Deploy once, bill each client automatically. JWT tokens carry per-client budgets. No custom metering code per project. SaaS Teams Adding AI: Add AI features without building infrastructure. Set budgets per subscription tier. Ship in days, not months. Indie Developers: One SDK, one deployment. Focus on your product, not on building AI infrastructure.

Key Features

Simple Integration

One SDK, same API for browser and Node.js. WebSocket-based real-time communication.

Budget Controls

Set per-user AI and compute budgets. Track usage in real-time with automatic limits.

Custom Tools

Define tools that Claude can call. Execute in browser or server context.

Multi-Provider

Use Claude, OpenAI, or 100+ OpenRouter models. Configure behavior with environment variables.

Supported Models

ProviderModelsBest For
AnthropicClaude Opus, Sonnet, HaikuDefault, best quality
OpenAIGPT-5.2, GPT-5, o3, o4Alternative provider
OpenRouter100+ modelsCost optimization, variety
Configure models per-session with environment variables like ANTHROPIC_MODEL and CLAUDE_CODE_SUBAGENT_MODEL.

Next Steps