# Dispatch > Dispatch is a desktop app and shared task board for AI coding agents. You give agents tasks, not chats: each task has an owner, a status, the files it may write and a definition of done. Agents such as Claude Code, Codex, Gemini CLI or any MCP agent take tasks from the board, work in their own git worktrees, and land through review and a merge queue. It runs locally on your own machines with your own agent and API key. Current version: 0.45.1. Platforms: macOS (Apple Silicon and Intel) and Linux. Free for up to three people with every feature, commercial use included. ## What Dispatch does - Two views: Overseer, one conversation with the whole project (what needs you comes in on the left, running work goes out on the right), and Tasks, every task grouped by milestone. - Plan in one sentence: the Overseer plans a milestone into tasks and asks for approval; approving starts agents wave by wave, and a blocked task starts the moment its blocker lands. - Any agent through one MCP server: `dispatch init` registers one MCP server in a repo. Tools include task_next, task_save, task_comment, peer_list, msg_send, msg_reply, doc_save, doc_search, doc_read, memory_save and memory_search. - Guardrails: every run works on its own branch in its own worktree; a task declares the files it may write and anything else waits for a person; spend and turn caps per run and per milestone stop work when hit. - Review, then land: diff, reviewer findings and transcript in one place, then a merge queue. - Agent to agent: agents message each other across a team, and agents outside it can hand work over A2A (Agent2Agent) as proposals that become tasks when approved. - Memory: agents save hazards, conventions, decisions and other lessons; the next run starts with them in its prompt. Team memories are reviewed by a person first, and unused ones fade out. - Milestone map: every wait between milestones, the critical path and an ETA, exportable as Mermaid. - In your repo: tasks are markdown in .dispatch/, or SQLite with a git receipt log. ## Common questions ### What is Dispatch? Dispatch is a desktop app and shared task board for AI coding agents. You give agents tasks instead of chats, they work through them on your own machines, and you review and land what they produce. ### Which AI coding agents work with Dispatch? Claude Code and Codex are built in, with live output, turn counts and spend. Gemini CLI, Cursor or any agent that speaks MCP connects through the one MCP server that dispatch init registers in your repo, and any CLI agent can be declared in config. ### How is a task different from a chat with an agent? A task has an owner, a status, the files it may write and a definition of done. It survives the tab closing, so anyone can ask the board where work stands instead of pinging people. ### How does Dispatch stop agents from breaking things? Every run works on its own branch in its own git worktree. A task lists the files it may write and anything else waits for your yes. Spend and turn caps per run and per milestone stop work when hit, and every change goes through review and a merge queue. ### Does my code leave my machine? No. Runs use your machine, your checkout and your own agent and API key. Tasks live in your repo as markdown or SQLite with a git receipt log. ### How much does Dispatch cost? It is free for up to three people with every feature, commercial use included. Teams of four or more need a license key. ### What does Dispatch run on? macOS on Apple Silicon and Intel, installed from a DMG or with brew install --cask wsoule/tap/dispatch. Linux packages are on GitHub. ## Get it - [Download for Mac, Apple Silicon](https://github.com/wsoule/dispatch/releases/latest/download/Dispatch_aarch64.dmg) - [Download for Mac, Intel](https://github.com/wsoule/dispatch/releases/latest/download/Dispatch_x64.dmg) - Homebrew: `brew install --cask wsoule/tap/dispatch` - [Quickstart docs](https://dispatch.foo/docs): download, follow Setup, land a first change. ## Pricing and licensing - Is Dispatch open source? It is open core. The pieces other tools integrate with (the core library, CLI, API client and MCP server) are MIT. The messaging protocol spec is Apache-2.0. The desktop app and daemon are source-available under FSL-1.1, and every release becomes Apache-2.0 two years after it ships. The team features are under the Elastic License 2.0. - Can I use it at work for free? Yes. Up to three people, every feature, commercial use included. - What does the FSL allow? Reading, building, modifying, self-hosting and redistributing the code for any purpose except shipping a competing product or service. - What happens past three people? A fourth invite is refused and says why. On a synced board, anyone past the seats keeps working locally and catches up when seats are added. Nothing is deleted, and an expired key falls back to the free plan instead of locking anyone out. - Does my code go anywhere? No. Runs use your machine, your checkout and your own agent and API key. The license key is checked on your machine with no phone-home. A team can sync over its own git branch instead of the relay. - What if Dispatch goes away? Your tasks are markdown in your repo, or a git receipt log you can copy into any repo to get a working board back. And each release turns Apache-2.0 two years on. ## Pages - [Home](https://dispatch.foo/): what Dispatch is, with a live replica of the app. - [Docs](https://dispatch.foo/docs): quickstart from download to a first landed change. - [Pricing](https://dispatch.foo/pricing): free for up to three, license key for bigger teams. - [Changelog](https://dispatch.foo/changelog): what changed in each release. - [Clips](https://dispatch.foo/clips): short videos filmed in the real app. - [Privacy](https://dispatch.foo/privacy): what the app, site, demo and Claude plugin collect. - [Dispatch Messaging Protocol](https://dispatch.foo/protocol/): the open spec (Apache-2.0) behind agent messaging, with an A2A 1.0 binding. - [A2A envelope extension](https://dispatch.foo/a2a/ext/envelope/v1) - [A2A gate extension](https://dispatch.foo/a2a/ext/gate/v1) - [A2A work extension](https://dispatch.foo/a2a/ext/work/v1) - [Source on GitHub](https://github.com/wsoule/dispatch) ## Recent releases - v0.45.1 (Oct 13, 2026): Memory in Docs. Browse what your agents remember from the Docs page, import Claude notes from a symlinked memory folder, and the Overseer works even when an agent started the daemon first. - v0.45.0 (Oct 13, 2026): Attachments and dispatch tui. Attach files and pasted images to Overseer messages, run Overseer, Tasks and Runs in the terminal with dispatch tui, and answer a task’s planner questions from its rail. - v0.44.1 (Oct 12, 2026): Clearer first steps. Setup notices a signed-out Claude Code, drafted acceptance criteria are kept, and the first land in a new project works. - v0.44.0 (Oct 12, 2026): Guided setup, and Codex can plan. Setup walks you to your first task, and Codex can now draft tasks, plan milestones and run the Overseer, with errors in plain English. - v0.43.0 (Oct 11, 2026): Approving a plan sends agents. An approved Overseer plan starts its agents on its own, and runs work on the current Claude models. - v0.42.0 (Oct 9, 2026): Two views is the whole app. Overseer and Tasks replace the old sidebar layout, and every finished task says plainly how it ended. ## Contact hello@dispatch.foo