Prompt decomposition
Convert a prompt into a mission plan with a target, budget, deadline, and check-ins before the agents start work.
Medley is a Claude Code plugin that turns prompts into coordinated multi-agent mission plans, with structure shown at a URL for research, outreach, operations, and coding.
Medley is a Claude Code plugin that adds a /mission command for turning a single prompt into a coordinated multi-agent plan. Instead of asking one model to do everything in one session, it decomposes the work, assigns steps to agents, and shows the structure at a URL.
The product is built for work that stretches beyond a narrow coding task: research, outreach, docs, hiring, operations, and other company-building work that benefits from parallel execution and human checkpoints. Medley stays inside Claude Code, uses the models you already have access to there, and is described as free on the site.
Convert a prompt into a mission plan with a target, budget, deadline, and check-ins before the agents start work.
Run coordinated work across multiple agents, including parallel steps and explicit handoffs between sub-tasks.
Use different models where they fit, including Claude, GPT, Gemini, Grok, Qwen, DeepSeek, Ollama, and Llama as shown on the site.
See the same task tree, status, and handoffs in the terminal and in a browser URL for the mission board.
Work with adjacent tools and company systems such as GitHub, Slack, Notion, Linear, Jira, Gmail, Google Drive, and more.
Keep missions inside Claude Code rather than moving to a separate dashboard or app.
Break a customer-acquisition goal into research, outreach drafting, lead list building, and review steps so the work can move in parallel instead of one session at a time.
Coordinate coding and non-coding work together when a launch needs copy, research, implementation, and approval gates in one mission.
Run research-heavy work such as finding signal, summarizing sources, or preparing a report with multiple agents working on separate subtasks.
Use Medley for ops work like hiring, calendar coordination, docs, or outreach where the task is less about a single code change and more about a managed sequence of actions.
Keep a project moving over time with a shared mission structure that survives beyond one terminal session and makes handoffs visible.
Medley turns a prompt into a multi-agent mission plan. It defines the target, budget, deadline, and checkpoints, then runs coordinated agents on the steps inside Claude Code.
No. Medley is a Claude Code plugin, so you still work in Claude Code while Medley adds mission planning, multi-agent execution, and a URL for the structure.
No. Medley is free and uses the models you already have access to in Claude Code.
No. Medley asks before sensitive actions such as publishing, sending outbound, spending, or contacting people, and you can grant more autonomy over time.
Medley is local-first and bring-your-own-keys on Mac. The FAQ says missions, keys, and agent conversations stay on your device rather than on Medley’s servers.
Orca is an Agent Development Environment for shipping with coding agents, running multiple CLI agents in parallel across isolated worktrees, with desktop and mobile workflows.
AI Magicx is a unified AI workspace for chat, image, video, voice, music, email and developer tasks, helping teams and creators manage multiple models in one place.
Paper is a design tool that connects canvas, code, and AI agents so teams can create, share, and ship work in one workflow. Includes desktop app and MCP access.
blop is a QA agent that writes browser tests as code in your repo, runs them in CI, clusters repeated failures, and can open PRs to fix broken tests.
RLAMA is a local AI platform for building RAG systems and intelligent agents on macOS, Linux, and Windows, with HTTP API support.
Kastra authorization infrastructure for AI systems checks prompts, tool calls, shell commands, API requests, and browser actions before execution.