Questions & objections
Common questions about how Medley works — and honest answers to the concerns founders raise before they delegate real work to their agents.
Product basics
- What does /mission actually do?
- You give Medley a prompt — like "get my first 10 customers." /mission turns it into a full multi-agent plan: the target, the budget, the deadline, and what to check with you first. Then it runs a coordinated team of agents on the steps.
- Do I need to know how to code?
- No. Medley is built for delegating business work — research, outreach, reporting, hiring, and ops. You describe outcomes; your agents carry out the steps.
- Which agents can Medley run as workers?
- Claude Code, Codex, Cursor, OpenCode, Kimi, and Pi. Medley routes each task in a mission to one of them, and auto-discovers whichever you already have installed and signed in — any subset works. OpenCode adds your own provider or a local model through Ollama or LM Studio, Kimi runs Moonshot’s models on an API key with no CLI to install, and Pi runs on whatever provider you configured in Pi itself.
- Can I use Medley with Codex instead of Claude Code?
- Yes. The same plugin installs on the Codex CLI (0.142.0 or newer) with codex plugin marketplace add https://github.com/Spine-AI/medley and codex plugin add medley@medley. Codex plugins cannot add slash commands, so there you start a mission with the $medley:mission skill instead of /mission.
- How many agents can I run at once?
- Medley is built for parallel missions across multiple agents and projects. The attention queue scales with your fleet — you see only what needs you.
- How do you prevent agents from conflicting?
- Medley decomposes work with explicit dependencies and scopes context per step — so parallel agents work on separate sub-tasks with clear handoffs.
Privacy & control
- Does Medley act without my permission?
- No. Agents run inside the guardrails you set, and Medley asks before anything sensitive — publishing, sending outbound, spending, or contacting people. You grant more autonomy at your own pace.
- Where does my data live?
- On your Mac. Medley is local-first and bring-your-own-keys — your missions, keys, and agent conversations stay on your device, not on our servers.
Comparisons & objections
- Is Medley a replacement for Claude Code?
- No. Medley is a plugin for Claude Code and Codex. You still work in your own harness — Medley adds mission planning, multi-agent execution, and a URL to see the structure.
- Does Medley replace my terminal?
- No. You stay in Claude Code or Codex. Medley is a plugin that adds missions — planning, multi-agent coordination, and a URL for the structure.
- How is this different from a project dashboard?
- A dashboard shows status. Mission control also routes work to agents, enforces sign-off gates, and keeps mission context alive across sessions — so agents can act, not just report.
- How is this different from CI/CD or Zapier?
- Those tools run deterministic scripts. Multi-agent workflows involve LLM agents making judgment calls, producing variable outputs, and needing human review. Medley orchestrates that kind of work.
- What does it cost?
- Medley is free. It uses the models you already have access to in Claude Code or Codex. Install the plugin and start a mission.
Install /mission in three commands.
Add the Medley plugin to Claude Code or Codex, start a mission, and get a coordinated team on the work — with a URL to watch the structure.
Install MedleyI