Koda is a desktop development environment where AI agents do the building. Run a whole team of them — Claude, Codex and more — across tiled terminal panes, and they coordinate on a shared board automatically, so every agent knows who's doing what and they never collide.
Windows installer available now · macOS & Linux coming soon · No account required to start
Runs the real, first-party agent CLIs you already use
Koda gives the agent CLIs a real home — organized, persistent, and designed for running many of them at once.
Koda turns your task board into an execution engine. Break the work into cards, assign each one an agent, and launch them in parallel. You focus on planning and review — the agents write code, run tests, and ship features across the whole codebase.
Terminals are the main stage, but a collapsible side panel gives you a Monaco editor, a file tree, a task board and a live browser — all one keystroke away. Read the diff, run the app, fix a line, and get back to orchestrating.
Built-in code review opens the full diff of everything an agent touched since it started — measured against a baseline Koda snapshots on the first run. Comment on lines, request changes, and send the fix straight back to the same session. Nothing ships without your sign-off.
Run a dozen agents at once and they won't trip over each other. The instant a session starts it announces its task on a shared board, claims a lane, and keeps its own card up to date — so every other agent can read who's doing what, live. No orchestrator to babysit, nothing to wire up. It's on by default.
The first prompt of every session drops a card on the board — titled with the task, tagged with its pane. No one has to remember to do it.
Before touching code, each agent calls koda_board and koda_roster to see who's working where — then takes a slice that won't collide.
Agents claim their card and declare a lane like backend · src/api. Contested claims resolve deterministically — two agents never own the same work.
Cards move themselves Backlog → In Progress → Review → Done as agents work and sessions end. The board is always a live picture of the whole team.
Koda ships a tiny stdio MCP server into each workspace and registers it for every agent. They coordinate by calling tools — deliberate and structured — while Koda holds the authoritative state on your machine.
Works with Claude Code, Codex, Gemini & Grok. State lives in a gitignored .koda/coord/ — local-first, no token proxy, no Koda backend. When a message arrives, Koda gently wakes the idle pane so the agent picks it up.
No proxy, no lock-in. Koda launches the CLIs you already have installed.
Point Koda at any project. It becomes a workspace with your file tree, editor, browser and task board — your layout saved for next time.
Spin up tiled terminals and launch Claude, Codex, or your own custom agent profile into each one. Keys from the vault are injected automatically.
Drop tasks on the board, hit Run, and watch agents build in parallel. Review their work in the editor and preview it live in the browser.
Koda runs the real first-party CLIs in real terminals. It never proxies your API, never extracts or reuses your OAuth tokens, and never sits between you and your provider. You sign in to your tools exactly as you always have.
That means you stay fully inside every provider's terms — and your credentials never leave your device.
The UI, your terminals and the editor all re-theme together — live.
Bring your own agent subscriptions — Koda is the workspace, you keep your logins.
Koda is a desktop development environment built around coding agents. Instead of writing every line yourself, you orchestrate AI agents — Claude, Codex and others — across tiled terminal panes, launch their work from a Kanban board, and review the results in a built-in editor and browser. It's an ADE — an agentic development environment — designed for building software with agents.
You bring your own agent credentials. Koda launches the agent CLIs you already use, so you sign in with your existing subscription or drop an API key into the encrypted vault. Koda never proxies your account — it just gives those tools a great home. As for Koda itself: it's free to start and needs no account. An optional Koda account unlocks Pro features, but the free tier works fully without one.
Any CLI-based agent. Out of the box that includes Claude Code, OpenAI Codex, Gemini, Grok and opencode, and you can define your own custom agent profile with a name, launch command and provider in a few seconds.
No. Koda is local-first: your code, shells and agents run on your own machine. API keys are encrypted by your operating system and decrypted only inside Koda's main process — never exposed to the interface or sent to us.
Koda is a desktop app built on Electron. The Windows installer is available today and auto-updates itself in the background; macOS and Linux builds are on the way. You can grab the latest build from the releases page.
Yes — that's the point. Tile up to 8 agents side by side, each in its own pane, and launch them in parallel from the task board. Per-pane account switching even lets different panes use different logins.
Koda runs a small MCP coordination server in every workspace and registers it for each agent. The moment a session starts it auto-creates a card on the shared Kanban board (titled with its task, tagged with its pane) and keeps that card updated as it works. Before editing, every agent reads the board and roster to see who's doing what, then claims a lane so two agents never own the same work. It's on by default — no setup. The shared state lives in a gitignored .koda/coord/ folder on your machine; nothing is proxied and there's no Koda backend.
Download Koda and turn your desktop into a command center for coding agents.
Free to start, no account required · Sign in to unlock Pro · macOS & Linux coming soon