phil65phil65Communityยท1 Agent Skills Included

llmling-agent

YAML-based multi-agent orchestration and protocol bridging

Configures and runs multiple AI agents from a single YAML file, mixing native, Claude Code, Codex, Goose, and AG-UI agents. Eliminates custom glue code by bridging ACP, AG-UI, OpenCode, MCP, and OpenAI-compatible protocols through one unified interface. Builds sequential or parallel agent teams with delegation, shared storage, analytics, and event triggers for faster multi-agent workflows.
npx skills add phil65/llmling-agent --all -g -y
Available:

Gives the AI agent a full map of the AgentPool architecture, agent types, YAML configuration patterns, and CLI commands so it can run, test, and extend agents correctly.

All Skills in This Repository (1)

Pure Emerald Level Indicators

Frequently Asked Questions

FAQPage Schema
How to install llmling-agent?โ–ผ

Run `npx skills add phil65/llmling-agent --all -g -y` in your terminal to install all skills in this suite globally.

What does AgentPool do?โ–ผ

It lets you define multiple AI agents in one YAML file and expose them through standard protocols like ACP, AG-UI, MCP, and an OpenAI-compatible API, so they can delegate and cooperate without custom glue code.

Can AgentPool combine Claude Code, Codex, and Goose?โ–ผ

Yes. You can mix native PydanticAI agents with Claude Code, Codex, ACP agents like Goose, and AG-UI agents, then coordinate them as sequential chains or parallel teams.

How do I run an agent with AgentPool?โ–ผ

Define the agent in a YAML manifest, then run `agentpool run <agent_name> "prompt"` or start a server with commands like `agentpool serve-acp config.yml` for IDE integration.

Does AgentPool track agent usage and history?โ–ผ

Yes. It includes SQL-based storage providers and observability via Logfire, and you can view analytics with `agentpool history stats`.

Related Repositories in Software Engineering

View All in Software Engineeringโ†’