CLI

Your whole agent stack, from the terminal

almyty ships a suite of small CLIs that share one login: authenticate, drive agents, chat, install skills into your editor, proxy MCP, and run agents on your own machine. Install the umbrella binary, or run any package with npx.

terminal
# one login, shared by every almyty CLI (~/.almyty/credentials.json)
$ npx @almyty/auth login

# or set it in the environment
$ export ALMYTY_TOKEN=ak_live_…

The suite

One credential store, the whole toolchain

Run the umbrella almyty binary, or pull any single package with npx. They all share the same login.

@almyty/cli
almyty

One binary for everything

The umbrella CLI. Installs a single almyty command that delegates to every package below.

almyty
# install once, run anything
$ npm install -g @almyty/cli
$ almyty login
@almyty/auth
almyty-auth

One login, shared everywhere

Browser-based login that mints a long-lived key. Every CLI reads it from ~/.almyty/credentials.json.

almyty-auth
# opens the browser, stores the key
$ npx @almyty/auth login
@almyty/agents
almyty-agents

List, run, and inspect agents

Drive your agents from scripts and CI: list them, run one with input, and read past runs.

almyty-agents
$ npx @almyty/agents list
$ npx @almyty/agents run research-bot
@almyty/chat
almyty-chat

Talk to an agent, in the terminal

An interactive REPL. Stream an autonomous agent step by step without leaving your shell.

almyty-chat
# interactive chat with an agent
$ npx @almyty/chat research-bot
@almyty/skills
almyty-skills

Skills into your AI editor

Install a gateway’s tools as Agent Skills into Claude Code, Cursor, Windsurf and more — or run one directly.

almyty-skills
$ npx @almyty/skills install acme/petstore
$ npx @almyty/skills run acme/petstore/get-pet --id 3
@almyty/mcp-server
almyty-mcp

Bridge a gateway to any MCP client

A local MCP server that proxies your gateway’s tools to any MCP-compatible client.

almyty-mcp
# register with Claude Code
$ claude mcp add petstore -- \
    npx -y @almyty/mcp-server acme/petstore

@almyty/runner

Run agents on your own machine

The runner is a daemon you start on your laptop or server. almyty dispatches work to it over a streaming connection; it executes processes and shell commands locally, while every LLM call still runs through the backend. Your code and local credentials never leave your box.

Its sharpest use: multi-vendor coding-agent orchestration. Every coding CLI is single-vendor — Claude Code on Anthropic, Codex on OpenAI, gemini-cli on Google. A runner lets one almyty workflow drive all of them at once: a planner agent dispatches subtasks to specialist agents, each on a different model, all editing the same codebase in one workspace.
your-laptop
# register this machine with almyty
$ npx @almyty/runner start --name my-laptop

# it appears online in the dashboard; agents can now
# run commands + CLI tools here, in a scoped workspace
$ npx @almyty/runner status

One login, then npx anything

Authenticate once and the whole suite is yours — agents, chat, skills, MCP, and a runner on your own machine.