Back to Eliza

Supabase Edge Functions elizaOS Worker Examples

packages/examples/supabase/README.md

2.0.19.6 KB
Original Source

Supabase Edge Functions elizaOS Worker Examples

Deploy AI chat agents as serverless Supabase Edge Functions. These examples show how to run an elizaOS agent as a stateless worker that processes chat messages via HTTP.

All handlers use the full elizaOS runtime with OpenAI as the LLM provider, providing the same capabilities as the AWS Lambda and chat demo examples.

Architecture

┌──────────────┐     ┌─────────────────┐     ┌────────────────┐
│  Test Client │────▶│  Supabase Edge  │────▶│  Edge Function │
│  (curl/deno) │◀────│  Functions      │◀────│  (elizaOS)     │
└──────────────┘     └─────────────────┘     └────────────────┘
                                                    │
                                                    ▼
                                             ┌────────────────┐
                                             │  OpenAI API    │
                                             └────────────────┘

Supported Languages

LanguageSupport LevelNotes
TypeScript✅ NativeFull Deno runtime support
Rust✅ via WASMCompile to WebAssembly
Python❌ Not supportedSupabase Edge Functions use Deno runtime

Note: Unlike AWS Lambda, Supabase Edge Functions run on the Deno runtime, which only natively supports TypeScript/JavaScript. Python is not supported. Rust can be used via WebAssembly compilation.

Prerequisites

Quick Start

1. Set Environment Variables

Create a .env file in your Supabase project or set secrets:

bash
# Local development
export OPENAI_API_KEY="your-openai-api-key"

# Or set in Supabase Dashboard → Project Settings → Edge Functions → Secrets
supabase secrets set OPENAI_API_KEY=your-openai-api-key

2. Initialize Supabase Project

bash
# If starting fresh
supabase init

# Copy edge functions to your project
cp -r examples/supabase/functions/* supabase/functions/

3. Test Locally First

bash
# Start Supabase local development
supabase start

# Serve edge functions locally
supabase functions serve eliza-chat --env-file .env

# Test with curl (in another terminal)
curl -X POST http://localhost:54321/functions/v1/eliza-chat \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_ANON_KEY" \
  -d '{"message": "Hello, Eliza!"}'

4. Deploy

bash
# Deploy to Supabase
supabase functions deploy eliza-chat

# Set secrets (if not already set)
supabase secrets set OPENAI_API_KEY=your-openai-api-key

5. Test Your Deployment

bash
# Get your project URL from Supabase Dashboard
curl -X POST https://YOUR_PROJECT.supabase.co/functions/v1/eliza-chat \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_ANON_KEY" \
  -d '{"message": "Hello, Eliza!"}'

Project Structure

examples/supabase/
├── README.md                       # This file
├── functions/
│   ├── eliza-chat/                 # TypeScript Edge Function
│   │   ├── index.ts                # Main handler
│   │   ├── lib/
│   │   │   ├── runtime.ts          # elizaOS runtime manager
│   │   │   └── types.ts            # Type definitions
│   │   └── deno.json               # Deno configuration
│   └── eliza-chat-wasm/            # Rust WASM Edge Function
│       ├── index.ts                # Deno wrapper
│       └── wasm/                   # Compiled WASM module
├── rust/                           # Rust source for WASM
│   ├── Cargo.toml
│   └── src/
│       └── lib.rs
├── scripts/
│   ├── build-wasm.sh               # Build Rust to WASM
│   └── test-local.sh               # Local testing script
├── test-client.ts                  # Interactive test client
└── config.toml                     # Supabase config

API Reference

POST /functions/v1/eliza-chat

Send a message to the elizaOS agent.

Request:

json
{
  "message": "Hello, how are you?",
  "userId": "optional-user-id",
  "conversationId": "optional-conversation-id"
}

Response:

json
{
  "response": "I'm doing well, thank you for asking!",
  "conversationId": "uuid-for-conversation-tracking",
  "timestamp": "2025-01-10T12:00:00.000Z"
}

Headers:

HeaderRequiredDescription
AuthorizationYesBearer YOUR_ANON_KEY or Bearer YOUR_SERVICE_ROLE_KEY
Content-TypeYesapplication/json

GET /functions/v1/eliza-chat/health

Health check endpoint.

Response:

json
{
  "status": "healthy",
  "runtime": "elizaos-deno",
  "version": "2.0.0-beta.0"
}

Configuration

Environment Variables / Secrets

VariableRequiredDefaultDescription
OPENAI_API_KEYYes-Your OpenAI API key
OPENAI_SMALL_MODELNogpt-5-miniSmall model to use
OPENAI_LARGE_MODELNogpt-5Large model to use
CHARACTER_NAMENoElizaAgent's name
CHARACTER_BIONoA helpful AI assistant.Agent's bio
CHARACTER_SYSTEMNo(default)System prompt

Setting Secrets

bash
# Via CLI
supabase secrets set OPENAI_API_KEY=sk-xxx CHARACTER_NAME=MyAgent

# Via Dashboard
# Project Settings → Edge Functions → Secrets

TypeScript Implementation

The TypeScript implementation uses the Deno runtime natively:

typescript
// functions/eliza-chat/index.ts
import { serve } from "https://deno.land/[email protected]/http/server.ts";
import { handleChat, handleHealth } from "./lib/runtime.ts";

serve(async (req: Request): Promise<Response> => {
  const url = new URL(req.url);

  if (url.pathname.endsWith("/health")) {
    return handleHealth();
  }

  if (req.method === "POST") {
    return await handleChat(req);
  }

  return new Response("Method not allowed", { status: 405 });
});

Rust WASM Implementation

For performance-critical operations, you can use Rust compiled to WebAssembly:

bash
# Build WASM module
cd examples/supabase/rust
wasm-pack build --target web --out-dir ../functions/eliza-chat-wasm/wasm

# Deploy
supabase functions deploy eliza-chat-wasm

Performance

Cold Starts

Supabase Edge Functions typically have faster cold starts than traditional Lambda:

  • Cold start: 50-200ms (vs 2-5s for Lambda)
  • Warm invocation: 5-20ms

Edge Locations

Edge Functions run on Deno Deploy's global edge network, providing low-latency responses worldwide.

Monitoring

Logs

bash
# Stream logs
supabase functions logs eliza-chat --scroll

# Get recent logs
supabase functions logs eliza-chat

Supabase Dashboard

View metrics and logs in:

  • Project → Edge Functions → Select function → Logs

Cost

Supabase Edge Functions pricing (as of 2025):

  • Free tier: 500K invocations/month
  • Pro tier: 2M invocations included, then $2 per 1M
  • No duration-based billing (unlike Lambda)

Comparison with AWS Lambda

FeatureSupabase Edge FunctionsAWS Lambda
RuntimeDeno (TS/JS)Node, Python, Rust, etc.
Cold Start50-200ms2-5s
Global Edge✅ Built-inVia Lambda@Edge
Supabase Integration✅ NativeManual
Python Support
Rust SupportVia WASMNative

Troubleshooting

"Function not found" Error

Ensure the function is deployed:

bash
supabase functions list
supabase functions deploy eliza-chat

"Unauthorized" Error

Check your authorization header:

bash
# Get your anon key from Supabase Dashboard
curl -H "Authorization: Bearer YOUR_ANON_KEY" ...

"OpenAI API key not found"

Set the secret:

bash
supabase secrets set OPENAI_API_KEY=your-key

CORS Issues

The function includes CORS headers by default. For custom domains, update the Access-Control-Allow-Origin header.

Cleanup

bash
# Delete function
supabase functions delete eliza-chat

# Remove secrets
supabase secrets unset OPENAI_API_KEY

See Also