⚡ 5-minute setup

Get Started with ChaozCode in 5 Minutes

Create your account, get your API key, and connect to the full AI DevOps platform — Memory Spine, agents, code intelligence, and more.

Get Connected in 3 Steps

From sign-up to your first API call in under 5 minutes.

1

Sign Up Free

Create your ChaozCode account. No credit card required. Includes access to all 8 apps.

Create Account →
2

Get Your API Key

Go to the Dashboard and generate an API key. One key works across all platform services.

Open Dashboard →
3

Start Building

Connect Memory Spine, launch agents, search code — use the examples below to get started.

See Examples ↓

📝 Prerequisites

  • Python 3.8+ or Node.js 18+ installed
  • Any MCP-compatible AI model (Claude, GPT-4, Gemini, or open-source)
  • A terminal or command-line interface

🔐 Authentication

All API requests to ChaozCode services require your API key. The same key works across Memory Spine, Zearch, AgentZ, and all platform services. Pass it via the Authorization header:

HTTP Header
Authorization: Bearer YOUR_API_KEY
cURL Example
curl -X POST https://chaozcode.com/api/v1/services/memory/search \ -H "Authorization: Bearer YOUR_API_KEY" \ -H "Content-Type: application/json" \ -d '{"query": "user preferences", "limit": 5}'

Your API key is available in the ChaozCode Dashboard under API Keys.

📚 API Endpoint Reference

Base URL: https://chaozcode.com/api/v1/services

EndpointMethodDescription
/memory/ingestPOSTStore a memory with content, tags, and metadata
/memory/searchPOSTSemantic search across all memories
/memory/recentGETRetrieve recent memories
/memory/statsGETMemory usage statistics
/memory/contextPOSTBuild LLM-ready context
/memory/pinPOSTPin a critical memory
/agents/routePOSTAuto-route a task to the best agent
/agents/executePOSTExecute a specific agent by name
/search/queryPOSTDeep code search across repos
/search/analyzePOSTAnalyze codebase structure
/healthGETPlatform-wide health check
1

Install the ChaozCode SDK

Install the ChaozCode SDK in your project. Choose Python or Node.js:

Terminal
pip install chaozcode
Terminal
npm install @chaozcode/sdk
Expected output
Successfully installed chaozcode-1.0.0
2

Configure MCP

Add ChaozCode services to your MCP configuration file so your AI model can access all platform tools. Create or update mcp-config.json. Set the CHAOZCODE_API_KEY environment variable:

mcp-config.json
{ "mcpServers": { "memory-spine": { "command": "chaozcode", "args": ["--service", "memory", "--url", "https://chaozcode.com/api/v1/services/memory"], "env": { "CHAOZCODE_API_KEY": "YOUR_API_KEY" } }, "agentz": { "command": "chaozcode", "args": ["--service", "agents", "--url", "https://chaozcode.com/api/v1/services/agents"], "env": { "CHAOZCODE_API_KEY": "YOUR_API_KEY" } } } }
What this does
Connects Memory Spine and AgentZ to the ChaozCode platform. Your AI model will auto-discover 363+ tools.
3

Store Your First Memory

Use memory_store to save persistent context. This memory will survive across sessions, conversations, and agent handoffs.

store_memory.py
import os from chaozcode import MemorySpine # Connect to the ChaozCode Memory Spine API spine = MemorySpine( url="https://chaozcode.com/api/v1/services/memory", api_key=os.environ["CHAOZCODE_API_KEY"] ) # Store a memory with content and tags result = spine.memory_store( content="User prefers dark mode and Python code examples. " "They are building a chatbot for customer support.", tags=["user-preference", "project-context"] ) print(f"Stored memory: {result['id']}")
storeMemory.ts
import { MemorySpine } from "@chaozcode/sdk"; // Connect to the ChaozCode Memory Spine API const spine = new MemorySpine({ url: "https://chaozcode.com/api/v1/services/memory", apiKey: process.env.CHAOZCODE_API_KEY, }); // Store a memory with content and tags const result = await spine.memoryStore({ content: "User prefers dark mode and Python code examples. " + "They are building a chatbot for customer support.", tags: ["user-preference", "project-context"], }); console.log(`Stored memory: ${result.id}`);
cURL
curl -X POST https://chaozcode.com/api/v1/services/memory/ingest \ -H "Authorization: Bearer YOUR_API_KEY" \ -H "Content-Type: application/json" \ -d '{ "content": "User prefers dark mode and Python code examples. They are building a chatbot for customer support.", "tags": ["user-preference", "project-context"] }'
Expected output
Stored memory: mem_a1b2c3d4e5f6
4

Search Memories

Use memory_search with a natural language query. Memory Spine returns semantically relevant results in under 25ms — no keyword matching required.

search_memory.py
# Search by meaning, not just keywords results = spine.memory_search( query="what kind of project is the user working on?", limit=5 ) for memory in results: print(f"[{memory['score']:.2f}] {memory['content']}")
searchMemory.ts
// Search by meaning, not just keywords const results = await spine.memorySearch({ query: "what kind of project is the user working on?", limit: 5, }); for (const memory of results) { console.log(`[${memory.score.toFixed(2)}] ${memory.content}`); }
cURL
curl -X POST https://chaozcode.com/api/v1/services/memory/search \ -H "Authorization: Bearer YOUR_API_KEY" \ -H "Content-Type: application/json" \ -d '{ "query": "what kind of project is the user working on?", "limit": 5 }'
Expected output
[0.94] User prefers dark mode and Python code examples. They are building a chatbot for customer support.
5

Explore the Platform

ChaozCode is more than memory. Use the same API key to route tasks to AI agents, search codebases, and build intelligent workflows across 8 apps.

explore.py — Memory + Agents + Search
import os from chaozcode import ChaozCode client = ChaozCode(api_key=os.environ["CHAOZCODE_API_KEY"]) # Memory Spine — persistent context client.memory.store(content="User prefers Python", tags=["preference"]) # AgentZ — route tasks to the best agent result = client.agents.route(task="Review this code for security issues") print(f"Routed to: {result.agent} (confidence: {result.confidence})") # Zearch — deep code search files = client.search.query(query="authentication logic", limit=10) for f in files: print(f"Found: {f.path} (score: {f.score})")
explore.ts — Memory + Agents + Search
import { ChaozCode } from "@chaozcode/sdk"; const client = new ChaozCode({ apiKey: process.env.CHAOZCODE_API_KEY }); // Memory Spine — persistent context await client.memory.store({ content: "User prefers TypeScript", tags: ["preference"] }); // AgentZ — route tasks to the best agent const result = await client.agents.route({ task: "Review this code for security issues" }); console.log(`Routed to: ${result.agent} (confidence: ${result.confidence})`); // Zearch — deep code search const files = await client.search.query({ query: "authentication logic", limit: 10 }); for (const f of files) { console.log(`Found: ${f.path} (score: ${f.score})`); }
Expected output
Routed to: security-auditor (confidence: 0.96) Found: src/auth/middleware.ts (score: 0.92) Found: src/auth/jwt.ts (score: 0.88)

Frequently Asked Questions

How long does it take to set up ChaozCode?

Most developers are up and running in under 5 minutes. Create an account, get your API key, and start using any of the 8 apps immediately. No infrastructure to provision.

Does ChaozCode work with GPT-4, Claude, and Gemini?

Yes. ChaozCode uses the Model Context Protocol (MCP), supported by all major AI models. 363+ tools are auto-discoverable by any MCP-compatible model.

Is ChaozCode free?

The Starter tier includes access to all 8 apps: 1,000 memory vectors, 5 agent runs/day, basic code search, and more. No credit card required. Paid plans start at $29/month. See pricing.

Ready to build with the full platform?

8 apps. 233 agents. 363+ tools. Start free — no credit card required.

Start Free →

From the Blog

Tutorials and guides to help you get the most out of ChaozCode.

How to Give Your AI Agent Persistent Memory

Step-by-step tutorial with Python code examples and architecture diagrams.

Read →

363+ MCP Tools: The Complete ChaozCode Guide

A comprehensive guide to every MCP tool across Memory Spine, AgentZ, Zearch, and more.

Read →