agent directory

CLI coding agents

A CLI coding agent is an AI pair programmer that runs in your terminal: you describe the work, it edits files and runs commands. This directory covers what each agent is, who makes it, what it costs, and which models it runs, so you can pick the right one before you pick a terminal.

Facts checked against each vendor's own docs. Updated November 16, 2026.

Anthropic

Claude Code

Anthropic's agentic coding tool: a terminal agent that also ships as IDE extensions, a desktop app, and a web surface, all on one engine.

proprietaryincluded in Claude Pro ($20/mo), Max ($100/mo), and Ultra ($200/mo), or pay per token with an API key
about this agent
OpenAI

Codex

OpenAI's open-source terminal coding agent, part of the wider Codex product spanning CLI, IDE, cloud, and web.

Apache 2.0included in ChatGPT plans from Free to Pro (from $100/mo), or pay per token with an API key
about this agent
Google

Antigravity CLI

Google's terminal agent (agy), sharing one agent harness with the Antigravity desktop app and replacing Gemini CLI for free and Google AI plan accounts.

proprietaryworks on free Google accounts; Gemini 4 Argon needs a Google AI Pro or Ultra plan
about this agent
Moonshot AI

Kimi Code

Moonshot AI's open-source terminal coding agent, bundled with Kimi memberships and built around the Kimi model family.

MITbundled into Kimi memberships from about $19/mo, or API pay-per-token
about this agent
Anomaly

opencode

An open-source AI coding agent that runs in the terminal, a desktop app, or on your phone, with free models included and any model provider you bring.

MITfree, with free models included; bring your own provider or subscription, pay per token via the optional Console, or subscribe to opencode Go from $10/month
about this agent
Agentic AI Foundation

goose

An open-source AI agent for code and automation, created at Block and now stewarded by the Linux Foundation's Agentic AI Foundation.

Apache 2.0free; bring your own provider keys or reuse existing Claude, ChatGPT, or Gemini subscriptions
about this agent
GitHub

GitHub Copilot CLI

GitHub's agentic coding assistant for the terminal, with native access to repos, issues, and pull requests.

proprietaryincluded in every Copilot plan, from Free to Max ($100/mo) and Business and Enterprise seats
about this agent
Aider AI

Aider

The original open-source terminal pair programmer: it edits code in your local git repo with almost any LLM, including local models.

Apache 2.0free and open source; model usage is billed by the LLM provider you connect
about this agent
AWS

Kiro

AWS's terminal coding agent and successor to Amazon Q Developer CLI, with credit-based Kiro pricing.

proprietaryfree tier with 50 credits/mo; paid plans $20 to $200/mo
about this agent
Meta

Muse Code

Meta's coding agent for the terminal and CI, built for Meta's Muse models.

proprietarysubscriptions from $5 to $200/mo, or pay-per-token API billing
about this agent

how to choose

how to choose a CLI coding agent

start from the subscription you already pay for

Most CLI coding agents come bundled with a chat subscription. Claude Code is included in Claude Pro, Max, and Ultra, Codex is included in ChatGPT plans down to the free tier, GitHub Copilot CLI ships with every Copilot plan, and Kiro has a free tier with 50 credits a month. If you already pay one of these vendors, their agent is the cheapest place to start.

open source and local models

Codex, opencode, goose, Aider, and Kimi Code publish their source. For models, opencode, goose, and Aider connect to almost any provider, local models through Ollama included, and Codex runs local open-source models through Ollama or LM Studio. GitHub Copilot CLI is not open source, but it also runs local models through Ollama. If your code can't leave your hardware, these are the candidates.

one model family or a switchboard

Claude Code and Muse Code are built around their vendor's own models. GitHub Copilot CLI, Kiro, and Antigravity CLI take the opposite bet: a model picker that spans more than one family, so one subscription covers several. Copilot CLI offers Claude, GPT, Gemini, and xAI models, Kiro offers Claude, GPT, Grok, and open-weight models, and Antigravity CLI offers Gemini plus Claude on paid plans.

in crystl

which agent for which job in crystl

Every agent here runs in crystl. These groupings are claims about crystl fit, not model quality: which host surfaces are wired and tested for each agent.

running the lead shard

The agent that owns a long task needs the full surface: approval cards, ask-user questions, transcript history, and resume after a restart.

  • Claude Codethe reference integration — every surface tested
  • Codexfull parity on cards, transcripts, and resume

fanning out workers

Workers run gated: tool calls raise approval cards, and the lead waits on their turn reports instead of polling screens.

  • Claude Codecards and turn ends fully wired
  • Codexcards and turn ends fully wired
  • opencodecards via an injected plugin; a missed answer falls back to its own prompt
  • goosecards in its default auto mode only
  • Kimi Codecards can deny but not pre-approve
  • GitHub Copilot CLIcards for the tools it gates itself; an allow-all session drops them

quests and multi-agent chat

A quest party needs transcripts crystl can read back and prompts it can deliver mid-session.

open and local models

Provider-agnostic agents point at whatever endpoint you configure, so open models can take the jobs they are good at.

  • opencodeopen source, bring any provider
  • gooseopen source, bring any provider
  • Aideropen source, provider-prefixed model ids, local models included
  • Claude Coderuns against a configured model endpoint too
  • Codexruns against a configured model endpoint too

Compatibility is descriptive

This catalog explains the host surfaces crystl has tested. Your local Crystl installation remains the source of truth for what runs, which hooks are installed, and how each agent is launched.

view catalog JSON