agentfield

Open-source control plane that runs AI agents as microservices: write plain Python/Go/TS functions, get REST endpoints with routing, queues, retries, memory and tracing — one laptop to 10k agents.

2,351 374 Go Apache-2.0updated yesterday

agents orchestration

View on GitHub Dispute this mapping →

Curator's take

The 'agents as a backend' play: write plain functions (no DSL, no graph wiring), and the Go control plane turns each into a REST endpoint any service can call — with fan-out to thousands of parallel agents, queues, retries, versioned deploys, observability and identity/audit built in. Reach for it when agents must be production infrastructure callable by frontends, cron jobs and other services — not a chat window. NOT for notebook experiments or a single local agent (a control plane + SDK is real operational commitment), and it won't give you reasoning-pattern libraries — you still design the agent logic it hosts. Its prompt-to-backend flow (/agentfield in Claude Code/Cursor) is a nice on-ramp, but evaluate the runtime, not the demo.

Mapped by ShipWithAI editors · links verified

README.md

AgentField — The AI Backend

Build agents like APIs. Run ten thousand of them like microservices.

One request fans out to thousands of agents. The control plane queues, retries, and traces every branch.

Docs · Quick Start · Python SDK · Go SDK · TypeScript SDK · REST API · Examples · Discord

Now includes Harness Orchestration — multi-turn coding agents with Claude Code, Codex, Gemini CLI, and OpenCode

AgentField is an open-source control plane that lets you build AI agents callable by any service in your stack - frontends, backends, other agents, cron jobs - just like any other API. You write agent logic in Python, Go, or TypeScript. AgentField turns it into production infrastructure: routing, coordination, memory, async execution, and observability. Every function becomes a REST endpoint, and the same code scales from one agent on your laptop to ten thousand in a single workflow: the control plane handles the fan-out, the queues, and the retries.

https://github.com/user-attachments/assets/9fb7b1cf-26de-4b9b-9ba2-917252cc26ec

_{One prompt → a running containerized production ready multi-agent backend. No glue code, start using the agent API!}

Build produc

Continue your stack

What teams reach for next — and why each earns a place beside agentfield. Ranked by curator confidence.

Alternative to See all + compare →

scale-agentex

Scale AI's open agent platform: scaffold agents with a CLI, run them behind the ACP protocol with a dev UI, and graduate from sync chat to durable Temporal-backed long-running workflows.

Why it fitsBoth are open control planes for building and deploying agents as long-running services with routing, queues and durable state. AgentField wraps plain Python/Go/TS functions as microservice agents; Agentex standardizes on the ACP protocol with Temporal underneath and a scaffolding CLI + dev UI.

paperclip

Open-source control plane for running fleets of heterogeneous AI agents as a "company" — bring your own agent, assign goals, org charts, budgets, governance, and an audited ticket system.

Why it fitsBoth are open control planes for fleets of agents, attacking opposite ends: paperclip is the governance layer over agents you already have (BYO agent, goals, org charts, budgets, audited tickets); agentfield is the build-and-run backend where agents are SDK-written microservices with REST endpoints, queues and retries. Govern existing agents → paperclip; build the agent backend itself → agentfield.

LangGraph

Build stateful, multi-actor LLM apps as graphs — durable execution, human-in-the-loop, streaming.

Why it fitsSame job — production multi-agent systems — opposite shape. LangGraph is an in-process library: model your workflow as a stateful graph with durable execution. agentfield is an out-of-process control plane: plain functions become REST microservices and the platform handles fan-out, queues and retries, explicitly rejecting graph wiring. Library and embedded → LangGraph; platform and service-oriented → agentfield.