agents

The open client for AI coding agents. Run Claude, Codex, Gemini, Cursor — same interface, on your machine.

$ curl -fsSL agents-cli.sh | sh

Or npm install -g @phnx-labs/agents-cli — also available as ag.

Chain agents in a pipeline

$ agents run claude "Find auth vulnerabilities in src/" \
    | agents run codex  "Fix the issues Claude found" \
    | agents run gemini "Write regression tests for the fixes"

Unix pipe composition across different models. Each agent resolves to the project-pinned version, with the right skills and MCP servers already synced. Chain by strength, swap one for another, script them in CI — the interface stays the same.

Pin versions per project

# .agents-version
claude 2.1.113
codex  0.116.0

cd into the project and every agents call resolves to those versions automatically. Like .nvmrc, but for AI. Nobody else does this.

Install skills, MCP servers, and commands once

$ agents skills add gh:yourname/python-expert
$ agents install mcp:com.notion/mcp
$ agents commands add gh:yourname/commands

Skills, MCP servers, slash commands, hooks, permissions — installed once, synced to every active agent version. No more claude mcp add then codex mcp add then editing Gemini's config file by hand.

One config repo, every harness

$ tree ~/.agents
~/.agents/
├── commands/      # slash commands
├── skills/        # reusable knowledge packs
├── mcp/           # MCP server definitions
├── hooks/         # lifecycle hooks
├── memory/        # agent instructions (AGENTS.md)
└── permissions/

~/.agents/ is the canonical config source. Write your commands as markdown, your rules as AGENTS.md, your hooks as scripts — and agents-cli syncs them into each harness's native format: markdown for Claude and Gemini, TOML for Codex, .cursorrules for Cursor. One repo, every agent in sync. Fork it and push your own via agents push.

Why

You use multiple coding agents and their configs drift
You want a skill, MCP server, or slash command installed everywhere at once
You want to pin agent versions per project like .nvmrc
You want to chain agents in scripts, CI, or cron jobs
You want it open, local, and yours — not a cloud SaaS

Supported agents

Claude Code · Codex · Gemini · Cursor · OpenCode · OpenClaw · Copilot · Amp · Kiro · Goose · Roo

Install

# via curl
$ curl -fsSL agents-cli.sh | sh

# via bun
$ bun install -g @phnx-labs/agents-cli

# via npm
$ npm install -g @phnx-labs/agents-cli

Part of the open stack for AI coding agents. Cloud runner coming.