agentfield
Build and run production multi-agent systems like microservices
All Skills in This Repository (3)
Pure Emerald Level Indicators
Agent-Fieldagentfield
Design and run multi-agent systems with AgentField's control plane.
Agent-Fieldagentfield-use
Discovers and dispatches tasks to installed AgentField agents via the control plane.
Agent-Fieldagentfield-personal
Builds, packages, installs, and registers a personal AI agent on the local AgentField control plane.
Frequently Asked Questions
FAQPage SchemaHow to install AgentField?▼
Run `npx skills add Agent-Field/agentfield --all -g -y` in your terminal to install all skills in this suite globally.
What does AgentField actually do?▼
It is an open-source control plane that turns ordinary Python, Go, or TypeScript functions into production AI agents callable as REST APIs. It handles routing, retries, parallel fan-out, memory, and observability across thousands of agents.
How is AgentField different from LangChain or CrewAI?▼
Those frameworks require you to declare the whole call graph upfront, while AgentField lets the call graph emerge at runtime from the agents' own decisions. Every cross-agent call is routed, traced, and recorded by the control plane.
Does AgentField work with Claude Code and Cursor?▼
Yes. The skills follow the universal SKILL.md standard and work in Claude Code, Codex, Gemini CLI, OpenCode, Cursor, and similar coding agents.
Can I build an agent without deep infrastructure knowledge?▼
Yes. Describe the system in one prompt and the skill scaffolds a working multi-agent backend with a Docker Compose smoke test, no manual queue or broker setup needed.
Related Repositories in Software Engineering
View All in Software Engineering→
openclawopenclaw
Run a personal AI assistant across your devices and chat apps
obrasuperpowers
Gives coding agents a disciplined workflow from idea to merged code
facebookreact
AI agent skills for building, testing, and porting React core