Hosted cloud coming soon — Orkka Local available today

Your AI dev team,
working on your repos

Connect a GitHub repo and write a task. Named AI agents plan, code, test in a real browser, and open the PR. You approve the plan and merge — from anywhere.

Free & self-hostedRuns on the AI subscriptions you already haveYour code never leaves your machine
OrkkaPowered by
L
N
A
P
A
M
S
S
F
your AI dev team

The Problem

You spot a bug on your phone. You open a note, jot it down, and hope you'll remember to fix it when you're back at your desk. Hours later, you context-switch, set up the environment, find the issue again, and finally start coding. The fix was 10 lines — the process took hours.

Context switchingWaiting for your PCLost bug reports

The Orkka Way

You spot a bug on your phone. You open Orkka, describe it in 30 seconds, attach a screenshot, and submit. Luna refines it, a dev agent plans and codes the fix in an isolated worktree, Scout tests it in a real browser, and a PR opens with a review. You approve and merge — right inside Orkka.

30-second task creationReal browser QAIn-app PR review

Meet your AI development team

Every project gets a persistent team of specialized AI agents. They have names and roles — rename them, tune their instructions, and pick each one's model: Claude, GPT, Gemini, and more.

L

Luna

PM

Refines tasks, asks the right questions, and breaks down requirements into actionable acceptance criteria.

› I've refined your task and identified 3 acceptance criteria.

N

Nova

Full Stack Dev

Handles cross-stack tasks end to end — frontend, backend, and database in a single pass.

› Wired the new endpoint into the dashboard. Tests are green.

A

Archie

Solution Architect

Keeps a living diagram of your system on the architecture board — design reviews, trade-offs, and scalability advice, one chat away.

› Sketched the event flow — want a queue between API and worker?

P

Pixel

Frontend Dev

Builds responsive, pixel-perfect UIs in any frontend stack — React, Vue, Angular, Svelte, or whatever your repo uses.

› Implementing the dashboard with responsive grid layout...

A

Atlas

Backend Dev

Creates APIs, database schemas, and server-side logic. Detects your stack automatically.

› Created REST endpoints with proper auth middleware.

M

Muse

Designer

Creates logos, icons, illustrations, and UI assets. Everything lands in the Design gallery for you to approve or iterate.

› Three logo concepts are ready in the gallery.

S

Scout

QA

Tests your live app in a real browser, validates acceptance criteria, and writes E2E tests before anything ships.

› All 12 test cases passing. Coverage at 94%.

S

Sentinel

Code Reviewer

Reviews PRs, enforces coding standards, and leaves line-level comments on diffs.

› Found 2 issues in the PR. Requesting changes.

F

Forge

DevOps

Handles CI/CD pipelines, Docker builds, Helm charts, and infrastructure as code.

› Docker build succeeded. Deploying to staging...

Ship code in three steps

From a task on your phone to a merged PR — without touching your IDE.

STEP 01

Connect your repo

Install the GitHub App and pick your repositories. Orkka detects the stack and assigns the right agents to each repo — frontend, backend, or full stack.

01
STEP 02

Write a task, approve the plan

Describe the bug or feature — Luna refines it into clear acceptance criteria. A dev agent studies your codebase and drafts a plan in an isolated worktree. Nothing gets coded until you approve.

02
STEP 03

QA, review, merge

Scout tests the change in a real browser and Sentinel reviews the diff before a PR opens. You review it line by line and merge — without leaving Orkka.

03

Watch tasks flow through your pipeline

Every task moves through configurable lanes. Agents hand off the work — you approve the big moments.

Ready
Fix auth redirect loop
High#127L
Luna refining...
Planning
Plan Ready
Developing
Testing
Code Review
Done

See it in action

The dashboard your AI team works in — live board, task threads, in-app PR review, and a living architecture board.

app.orkka.ai/p/my-project
Ready1
Add OAuth flow
Medium#143L
Developing1
Fix auth redirect loop
High#127N
Agent working...
Testing1
Refactor user settings API
Medium#134S
Agent working...
Code Review1
Update billing webhook
Low#119S
Awaiting your review
Orkka

Everything you need to ship faster

Run your AI development team from anywhere — every step happens inside Orkka, on desktop or on your phone.

Realtime Kanban Board

Tasks flow through configurable lanes, updated live as agents plan, code, and test. Skip stages or reorder lanes to match your process.

Agent Task Threads

Every task is a conversation: agent messages, execution plans, questions, and attachments in one place. Approve plans or answer questions from your phone.

In-App PR Review

Review diffs with line-level comments from Sentinel, then approve and merge — without opening GitHub.

Repo Browser

Connect repos via the GitHub App and browse files, branches, and diffs right inside Orkka.

AI-Written Documents

Agents write and maintain project docs with full revision history. Chat with your PM to create or update them.

Design Gallery

Muse turns requests into logos, icons, and illustrations. Approve, reject, or iterate on each asset with one click.

Architecture Board

Archie keeps a living diagram of your system on an interactive board — ask for changes in chat and watch it update.

Notifications & Live Activity

Get notified when an agent replies, a plan needs approval, or a task gets blocked. Everything updates in real time.

Usage-Based Billing

Pay per token with $5 free credits to start. Costs tracked per task, agent, and project — with budget alerts and auto-pause.

Available today — free & self-hosted

Run Orkka on your own machine

Orkka Local is the free, self-hosted edition. The same AI dev team and pipeline — working on your local repos, powered by the AI subscriptions you already have: Claude, Codex (ChatGPT), Gemini, or GitHub Copilot. No credit card, no API keys, no code leaving your machine.

ClaudeCodexGeminiCopilotOllama

How it works

A lightweight Docker core runs the board, API, and database. The Orkka runner — one small binary on your machine — does the real work: it runs your provider's CLI (claude, codex, gemini, or copilot) under your subscription login and manages git worktrees over your local repositories.

Docker — Orkka corelocalhost:3000
├─ postgres · API · UI
SignalR
orkka-local runneryour machine
└─ claude · codex · gemini · copilot · git · your toolchains
  • Runs on your existing AI subscriptions — Claude, ChatGPT, Gemini, or Copilot — no API keys, no per-token billing
  • Your code never leaves your machine
  • Agents build and test with your locally installed toolchains

Quick start

From zero to your AI dev team in three steps.

  1. 1
    Install the prerequisites

    Docker Desktop and the CLI of your favorite provider — Claude Code, Codex, Gemini, or Copilot.

  2. 2
    Log in to your provider

    Agents run on your subscription, exactly like using the CLI yourself.

    $ claude /login
  3. 3
    Start Orkka Local

    Download the orkka-local binary (a single file, no dependencies) and run one command. It pulls the images, starts everything, and opens the app.

    $ orkka-local up
Get started guideFree forever — bring your own AI subscription.
New — built-in terminal

A real terminal, one click away

Pop open a full terminal from anywhere in the app — running directly inside your repository, on your machine. git, npm, dotnet, vim: whatever you have installed just works, colors and all.

  • Opens in your repo’s working copy — no cd, no setup
  • Full PTY: colors, arrow keys, Ctrl+C, even vim and interactive prompts
  • Floats on every page and keeps its session while you navigate
pwsh — my-app
➜ my-app (main) git status
On branch main · working tree clean
➜ my-app (main) npm run build
✓ Compiled successfully in 3.2s
➜ my-app (main) ▍

Private by design

Repos, diffs, and agent output stay on your hardware. The stack binds to 127.0.0.1 only — nothing is exposed to the network.

Your machine, your rules

Agents work in isolated git worktrees and open pull requests you review inside Orkka. Merges land straight into your local repository.

The same pipeline

Board, planning, development, code review, documents, architect — the full Orkka experience, self-hosted.

Pay only for what you use

When hosted Orkka launches: no tiers, no subscriptions. Start with $5 free credits, then pay per token — with models from Anthropic, OpenAI, and Google to choose from.

Hosted — coming soon
Start free
$5 free credits

No credit card required

  • $5 free credits on signup — no credit card required
  • Pay per token after free credits are used
  • 10% Orkka fee covers infrastructure & tooling
  • Monthly invoices via Stripe
  • Set budget limits with alerts at 50%, 80%, 100%
  • Auto-pause agents when budget is reached

Hosted sign-ups open soon.

Token pricing — Claude models

Per 1M tokens, includes 10% Orkka markup

ModelInputOutput
Haiku 4.5$1.10$5.50
Sonnet 4.6$3.30$16.50
Sonnet 5$3.30$16.50
Opus 4.6$5.50$27.50
Opus 4.8$5.50$27.50
Fable 5$11.00$55.00

Also at launch: OpenAI GPT-5.5 and GPT-5.5 Codex, Google Gemini 3 Pro and Flash — same pay-per-token model, rates published when sign-ups open.

Prices shown include the 10% Orkka infrastructure fee. Provider base rates may change.

No BYOK Required

We handle the provider API keys — Anthropic, OpenAI, Google. You focus on building your product.

Real-Time Cost Tracking

See costs per task, per agent, per project. Usage charts and daily spend breakdowns.

Budget Controls

Set monthly limits per project or org-wide. Get alerts before you hit your cap.

Orkka
Hosted version — coming soon

Your AI dev team is ready today

Run Orkka Local free on your own machine right now. The hosted cloud version is coming soon.