AgentField Documentation

The AI backend. Build, deploy, and govern AI agents like APIs.

Code to API — write a function, get a production endpoint

curl -sSf https://agentfield.ai/get | sh

Fastest way in: one prompt, full backend

After install, type /agentfield in Claude Code — or describe your system in plain English. Stack is live under docker compose in one shot.

Try it →

from agentfield import Agent, AIConfig
from pydantic import BaseModel

app = Agent("demo", ai_config=AIConfig(model="anthropic/claude-sonnet-4-20250514"))

class Decision(BaseModel):
    action: str

@app.reasoner()
async def route(text: str) -> dict:
    out = await app.ai(
        system="Pick one action: summarize | escalate | done.",
        user=text,
        schema=Decision,
    )
    return out.model_dump()

app.run()

// Same idea in TS: Agent + reasoner + app.ai with a schema.
// See Quickstart for the full snippet.

// Same idea in Go: agent package + reasoner + structured AI call.
// See Quickstart for the full snippet.

APIs — decorated functions become HTTP endpoints with discovery and tracing.
Models — 100+ LLMs, structured output (Pydantic / Zod / structs), tool calling.
Multi-agent — app.call, shared memory, async, webhooks, governance (DIDs, policy, audit).

Prompt to production — recommended

Describe the system in one line. Get a production-ready multi-agent backend.

Quickstart — write it yourself

Install, scaffold, run in about a minute with the SDK.

How it works

Primitives + control plane in one pass

Architecture

Request flow: sync, async, cross-agent calls

Build

Agents, intelligence, coordination, execution, governance

Reference

SDKs, REST, CLI, deploy, testing