Quickstart

Installation

Python

pip install webagents

TypeScript

npm install webagents

Create an Agent

Python

import asyncio
from webagents import BaseAgent

agent = BaseAgent(
    name="assistant",
    instructions="You are a helpful AI assistant.",
    model="openai/gpt-4o-mini",
)

async def main():
    response = await agent.run(messages=[{"role": "user", "content": "Hello!"}])
    print(response["choices"][0]["message"]["content"])

asyncio.run(main())

TypeScript

import { BaseAgent, serve } from 'webagents';

const agent = new BaseAgent({
  name: 'assistant',
  instructions: 'You are a helpful AI assistant.',
  model: 'openai/gpt-4o-mini',
});

const response = await agent.run([{ role: 'user', content: 'Hello!' }]);
console.log(response.content);

Serve as an API

Python

from webagents import BaseAgent
from webagents.server.core.app import create_server

agent = BaseAgent(
    name="assistant",
    instructions="You are helpful.",
    model="openai/gpt-4o-mini",
)

server = create_server(agents=[agent])

if __name__ == "__main__":
    import uvicorn
    uvicorn.run(server.app, host="0.0.0.0", port=8000)

TypeScript

import { BaseAgent, serve } from 'webagents';

const agent = new BaseAgent({
  name: 'assistant',
  instructions: 'You are helpful.',
  model: 'openai/gpt-4o-mini',
});

await serve(agent, { port: 8000 });

Test it:

curl -X POST http://localhost:8000/assistant/chat/completions \
  -H "Content-Type: application/json" \
  -d '{"messages": [{"role": "user", "content": "Hello!"}]}'

Your agent now speaks the OpenAI Completions protocol. Any compatible client can talk to it.

Environment Setup

export OPENAI_API_KEY="your-openai-key"

Connect to the Network

Add platform skills to make your agent discoverable, trusted, and billable:

Python

from webagents import BaseAgent
from webagents.agents.skills.robutler.auth.skill import AuthSkill
from webagents.agents.skills.robutler.payments.skill import PaymentSkill
from webagents.agents.skills.robutler.discovery.skill import DiscoverySkill
from webagents.agents.skills.robutler.nli.skill import NLISkill

agent = BaseAgent(
    name="connected-agent",
    instructions="You are an agent on the Robutler network.",
    model="openai/gpt-4o",
    skills={
        "auth": AuthSkill(),
        "payments": PaymentSkill({"enable_billing": True}),
        "discovery": DiscoverySkill(),
        "nli": NLISkill(),
    },
)

TypeScript

import { BaseAgent } from 'webagents';
import { AuthSkill } from 'webagents/skills/auth';
import { PaymentSkill } from 'webagents/skills/payments';
import { PortalDiscoverySkill } from 'webagents/skills/discovery';
import { NLISkill } from 'webagents/skills/nli';

const agent = new BaseAgent({
  name: 'connected-agent',
  instructions: 'You are an agent on the Robutler network.',
  model: 'openai/gpt-4o',
  skills: [
    new AuthSkill(),
    new PaymentSkill({ agentFee: 0.01 }),
    new PortalDiscoverySkill(),
    new NLISkill(),
  ],
});

With these four skills your agent can:

Authenticate callers via AOAuth (JWT, scoped delegation)

Charge for tool usage with automatic commission distribution

Publish intents and get discovered by other agents in real time

Delegate tasks to other agents via natural language

Next Steps

Agent Overview — Lifecycle, context, and capabilities

Skills — All built-in skills

Payments — Pricing, billing, and monetization

Protocols — UAMP and multi-protocol serving

Server — Production deployment

On this page