# Kaitoi

> Kaitoi is a self-extending AI platform for creators and developers. Build hybrid AI workflows in Studio, ship them through Core, and let Penny create capabilities on demand.

Kaitoi Labs builds software that builds itself, on demand. Instead of shipping a fixed list of features, Kaitoi lets you build in Studio, ship through Core, and let Penny turn missing capabilities into working parts of the system.

## Main

- [Kaitoi (home)](https://kaitoi.io/): Your next campaign starts with the last. Turn a brief into a finished ad and a workflow you can use again. AdMuse develops the ideas, Penny adds any tools or functionality you need, and you stay in control of every step.
- [Kaitoi Platform](https://kaitoi.io/platform/): The full platform overview: Studio and Core, Penny building missing tools, supported models and integrations, and reusable production workflows.
- [Kaitoi for media owners](https://kaitoi.io/media-owners/): Creative infrastructure for broadcasters, streaming and CTV platforms, retail media networks and marketplaces with ad businesses. Complete ad campaigns for the advertisers a creative team cannot serve by hand.

## Products

- [Kaitoi Studio](https://kaitoi.io/studio/): A self-extending AI workspace for visual production teams: graph workflows, moodboards, storyboards, timeline, media tools, and Penny in one browser-based workspace.
- [Kaitoi Core](https://kaitoi.io/core/): The programmable platform and public API that powers Kaitoi Studio. Build custom AI-native applications on the same foundation.
- [Kaitoi CLI](https://kaitoi.io/cli/): Brings Kaitoi to your terminal: local operations, runtime recipes, graph execution, Kaitoi Code, and apps powered by Kaitoi Core.

## Free apps

- [Teksto](https://kaitoi.io/teksto/): A free menu-bar dictation app for Mac. Press a shortcut, talk, and get polished text, transcribed and rewritten on the Mac, with optional translation. Apple silicon, macOS 14 or later.
- [C182 Cruise Advisor](https://kaitoi.io/c182/): A free, offline iPhone and iPad app for the Cessna 182T G1000 that reads back manifold pressure, RPM, airspeed, fuel flow and range from the POH tables.

<!-- BEGIN generated: docs -->
## Documentation

- [Documentation](https://kaitoi.io/docs/): Concepts behind Kaitoi projects, graphs and runs, and the Kaitoi Core REST API. Every page is also available as raw markdown at the same URL with a `.md` extension.
- [Choose where to work](https://kaitoi.io/docs/start/overview/): Choose Studio for visual creation, Core for applications and AI clients, or the CLI for local work, then find the right starting point for your task.
- [Your first project](https://kaitoi.io/docs/start/first-project/): Create a small test image, change its pattern, save the editable workflow, and download the result while learning Studio’s basic graph controls.
- [Finding your way around](https://kaitoi.io/docs/start/navigation/): Locate Studio’s main controls, switch views, find nodes and saved work, navigate a graph, and understand the different controls used on a phone.
- [Projects](https://kaitoi.io/docs/concepts/projects/): Understand what a project keeps, how the working autosave differs from a saved project, and how to reopen, copy, and update work safely.
- [Graphs and nodes](https://kaitoi.io/docs/concepts/graphs-and-nodes/): Understand node types and instances, manual and connected inputs, typed pins, branches, and how a graph's dependencies shape a run.
- [Runs](https://kaitoi.io/docs/concepts/runs/): Run the work you need in Studio, understand progress and reused results, stop execution, and keep the outputs that matter.
- [Kaitoi Studio and Kaitoi Open Source](https://kaitoi.io/docs/concepts/studio-and-open-source/): Compare hosted Studio with the planned Kaitoi Open Source distribution: who runs it, which services are included, where data goes, and what you manage yourself.
- [Saving and recovery](https://kaitoi.io/docs/studio/saving-and-recovery/): Save deliberately, read autosave status, reopen the right work, and recover a backup without confusing a local restore with a successful server save.
- [Files and results](https://kaitoi.io/docs/studio/files-and-results/): Inspect current and earlier node outputs, copy useful results to Files, organize personal and team assets, and download copies for use elsewhere.
- [Teams](https://kaitoi.io/docs/studio/teams/): Set up a team, choose its workspace, add members with the right roles, share saved work, and manage a pooled credit balance with weekly spending caps.
- [Working with Penny](https://kaitoi.io/docs/studio/penny/): Build graphs, create custom nodes, and make content with Penny. Choose the right context, manage conversations, and distinguish changes from completed results.
- [Building and editing graphs with Penny](https://kaitoi.io/docs/studio/penny-graphs/): Brief a new workflow, target changes in an existing graph, check inputs and wires, and test the intended output with Penny.
- [Creating custom nodes with Penny](https://kaitoi.io/docs/studio/penny-custom-nodes/): Create a reusable node with Penny. Define its interface, review generated code and warnings, test known cases, and revise it while preserving its contract.
- [Skills](https://kaitoi.io/docs/studio/skills/): Choose the workflows Penny can execute in Lab, configure required plugins, and create or import reusable Skills that produce canvas results.
- [Playbooks](https://kaitoi.io/docs/studio/playbooks/): Give Penny reusable written instructions for a conversation, import a Markdown Playbook, activate it, and maintain a consistent creative method.
- [Creating content in Lab](https://kaitoi.io/docs/studio/lab/): Develop a brief with Penny, give references a clear role, generate with Skills, and take the results into your next stage of work.
- [Nodes](https://kaitoi.io/docs/studio/nodes/): A node is one unit of work with typed pins, its own parameters, its own preview and its own state. Learning to read one is most of learning to read a Kaitoi graph.
- [Building a graph](https://kaitoi.io/docs/studio/graphs/): Add nodes, connect compatible typed pins, run the intended selection, inspect earlier results, and organize reusable parts of a larger workflow.
- [Blocks](https://kaitoi.io/docs/studio/blocks/): Build a processing chain with block previews and parameter controls, inspect its history, and keep the same underlying graph available for editing.
- [Templates and organization](https://kaitoi.io/docs/studio/templates/): Start projects from reusable graphs, save a template, share its link, and organize nodes and projects without confusing their roles.
- [Storyboards](https://kaitoi.io/docs/studio/storyboards/): Plan scenes and shots, organize reference frames, edit their order and duration, and send an intended sequence to Timeline or back to Lab.
- [Timeline and export](https://kaitoi.io/docs/studio/timeline/): Assemble picture and sound on tracks, trim and inspect clips, configure the output, then render a deliverable or export an interchange document.
- [Drawing, masks, and crops](https://kaitoi.io/docs/studio/drawing-tools/): Sketch a visual reference, prepare a mask or crop for an image input, compare results, and keep the original source while you experiment.
- [3D models and scenes](https://kaitoi.io/docs/studio/3d/): Inspect models and splats, compose a scene with a 3D Editor node, choose render outputs, and keep useful models or scene results for later work.
- [Create and publish a Station](https://kaitoi.io/docs/stations/creating/): Choose the graph inputs and results visitors receive, check node compatibility, preview a frozen draft, and make a Station live at a stable link.
- [Using a Station](https://kaitoi.io/docs/stations/using/): Supply Station inputs, read the estimate, run a published tool, download results, and resume supported failed work while understanding its costs.
- [List a Station in the gallery](https://kaitoi.io/docs/stations/gallery/): Submit a Station description and image or video cover, understand review, update a listed card with Send changes, or withdraw the public listing.
- [Research with AdMuse](https://kaitoi.io/docs/integrations/admuse/): Use advertising references to develop a grounded creative direction, then turn that direction into a production workflow.
- [Knowledge bases and RAG](https://kaitoi.io/docs/studio/rag/): Extract and index document content, keep embeddings compatible, retrieve useful source passages, and use them to ground a model’s answer.
- [Providers and models](https://kaitoi.io/docs/integrations/providers/): Choose managed model access, personal provider keys, or local services, and configure the available model list for Penny and your workflows.
- [Connect your accounts](https://kaitoi.io/docs/integrations/connectors/): Authorize external services for workflow nodes, check the account and permissions in use, and reconnect or remove connections when access changes.
- [Add external MCP servers](https://kaitoi.io/docs/integrations/mcp-servers/): Connect Kaitoi to an external MCP tool server, configure authentication, inspect its capabilities, and troubleshoot missing or expired access.
- [Local models and services](https://kaitoi.io/docs/integrations/local-services/): Connect Studio to supported models and services on your hardware, then check the service, runtime, installed recipe, and connection separately.
- [Sharing and embedding](https://kaitoi.io/docs/studio/sharing/): Choose read-only project sharing, optional cloning, template links, or runnable Stations, then manage expiry and access for the intended audience.
- [Community publishing](https://kaitoi.io/docs/studio/community/): Discover shared nodes and templates, inspect their requirements and prices, and prepare your own reusable code and workflows for publication.
- [Quickstart](https://kaitoi.io/docs/core/quickstart/): Get a scoped REST key, discover a node schema, submit one inline graph run, follow its status and events, and recover uncertain submissions safely.
- [Authentication, API keys and scopes](https://kaitoi.io/docs/core/authentication/): Choose a server or browser API key, grant the scopes your integration needs, configure its origin policy, and keep credentials out of public code.
- [Discover nodes and templates](https://kaitoi.io/docs/core/discovery/): Discover current node schemas and owned template endpoints, preserve their identifiers, follow opaque cursors, and build requests from the returned contract.
- [Projects and graph documents](https://kaitoi.io/docs/core/projects-and-graphs/): Discover node schemas, edit a versioned graph document through the public API, and reconcile changes without overwriting another client’s work.
- [Runs, progress and cancellation](https://kaitoi.io/docs/core/runs-and-files/): Submit API runs from saved or inline graphs, observe their lifecycle, cancel work, recover uncertain submissions, and retain the outputs you need.
- [Files and outputs](https://kaitoi.io/docs/core/files-and-outputs/): Reserve and complete uploads, follow signed storage instructions, use stable file IDs in runs, and distinguish temporary download URLs from retained files.
- [Timelines and storyboards](https://kaitoi.io/docs/core/timelines-and-storyboards/): Validate editable timeline and storyboard documents, convert supported shots, manage versioned project media, and distinguish interchange import from rendering.
- [Workflow API endpoints](https://kaitoi.io/docs/core/workflow-endpoints/): Publish a template's selected inputs and outputs as an async endpoint, choose its authentication path, and build on earlier results.
- [Errors, retries and version conflicts](https://kaitoi.io/docs/core/errors-and-retries/): Read structured API errors, recover uncertain requests with stable idempotency keys, reconcile version conflicts, and avoid duplicating side effects or spend.
- [Connect an AI client](https://kaitoi.io/docs/core/mcp/): Connect an AI client using your MCP Access URL and scoped authentication, verify its tools, and choose scratch, headless, or attached Studio work.
- [Attach to a live Studio session](https://kaitoi.io/docs/core/mcp-studio/): Opt in on a Studio tab, discover and attach its exact session, use revision-guarded actions, and recover uncertain changes without silently switching graphs.
- [Build and edit graphs and blocks](https://kaitoi.io/docs/core/mcp-workflows/): Discover node schemas, edit the intended graph with revision guards, use grouped block and canvas tools, and keep validation, saving and execution separate.
- [Load and save projects](https://kaitoi.io/docs/core/mcp-projects/): Load and save the headless graph, or save a versioned copy of an attached Studio graph while keeping the original project and unsaved work open.
- [Create and edit custom nodes](https://kaitoi.io/docs/core/mcp-custom-nodes/): Read current node rules and source policy, author controlled packages, guard attached script edits with source hashes, and test behavior separately from saves.
- [Run workflows and approve costs](https://kaitoi.io/docs/core/mcp-execution/): Inspect credit estimates, choose a scratch, headless or attached run, and retain the original execution receipt for safe retries.
- [Results, files and Run Inspector](https://kaitoi.io/docs/core/mcp-results/): Inspect MCP executions, retrieve omitted values by version, open supported Run Inspector results, retain files, and cancel the intended run or relay action.
- [Work with storyboards and timelines](https://kaitoi.io/docs/core/mcp-media/): Read consistent media snapshots, use revision-guarded grouped timeline and storyboard commands, and distinguish editor changes from transfers and rendering.
- [Build applications with Kaitoi](https://kaitoi.io/docs/core/mcp-apps/): Discover callable workflow contracts, generate exact REST request bodies through MCP, choose key placement, and separate application authority from execution.
- [Permissions and troubleshooting](https://kaitoi.io/docs/core/mcp-troubleshooting/): Diagnose missing MCP tools, attachment and revision failures, quote refusals, uncertain actions, omitted results, and unavailable Run Inspector presentation.
- [Writing custom nodes](https://kaitoi.io/docs/core/custom-nodes/): Declare a node's interface with comment directives, implement its run function, and use the supported runtime rather than backend internals.
- [Agents and plugins](https://kaitoi.io/docs/core/agents-and-plugins/): Compose tool-capable nodes, connect compatible plugins, configure their inputs, and keep iterative execution bounded and observable.
- [Node and data reference](https://kaitoi.io/docs/reference/nodes-and-types/): Find an operation’s current schema, read pin names and data types, check its controls and requirements, and use the right value representation.
- [Install and update](https://kaitoi.io/docs/cli/install/): Install Kaitoi CLI on macOS, Windows, or Linux, choose the command for your work, and learn how to check, download, and apply updates.
- [Your first Kaitoi Code session](https://kaitoi.io/docs/cli/code/): Start Kaitoi Code in a project, inspect it in Plan mode, review a small edit in Build mode, and check the result before moving on.
- [Sign-in and configuration](https://kaitoi.io/docs/cli/configuration/): Sign in to Kaitoi CLI, save your Code preferences, find the right settings file, and understand which choices apply to a new session.
- [Files and state on disk](https://kaitoi.io/docs/cli/files-on-disk/): Find Code settings, session logs, audit records, agent worktrees and Crew evidence, and configure project file exclusions.
- [Hosted and local models](https://kaitoi.io/docs/cli/models/): Choose a hosted model or connect your own model server in Kaitoi Code. Learn model selection, local setup, context limits, and where requests go.
- [Local model setup](https://kaitoi.io/docs/cli/local-models/): Set up Ollama, LM Studio or an OpenAI-compatible model server for Kaitoi Code, with no Kaitoi login or Kaitoi inference charge for local-model turns.
- [Costs and budgets](https://kaitoi.io/docs/cli/prices/): Read Code usage, set a credit or step limit, and distinguish model spending, tool charges, external engines, and the limits of a running budget.
- [Plan, Build and Crew modes](https://kaitoi.io/docs/cli/modes/): Choose Plan for inspection, Build for approved changes, or Crew for durable delivery with its own reviewed authority and bounds on delegated work.
- [Permissions and the sandbox](https://kaitoi.io/docs/cli/permissions-and-sandbox/): How Kaitoi Code asks before it acts. Trusting a folder, approval cards with diffs, rules you save per project, auto-approve, and the sandbox around commands.
- [Files, attachments and edits](https://kaitoi.io/docs/cli/files-and-edits/): Give Code the right files and images, use line-specific mentions, review edits, and understand the boundary between workspace access and attachments.
- [Commands and background processes](https://kaitoi.io/docs/cli/commands-and-processes/): Enable model command tools, inspect sandbox and approval details, use your own shell command, and track or stop the background processes Code owns.
- [Sessions, history and context](https://kaitoi.io/docs/cli/sessions/): Resume or fork a conversation, inspect context pressure, compact long sessions, export useful records, and distinguish a fresh session from file recovery.
- [Checkpoints, undo and rewind](https://kaitoi.io/docs/cli/checkpoints/): Recover from an unwanted Code exchange, choose whether files or conversation should go back, and understand skipped files, redo, and checkpoint limits.
- [Web research and media generation](https://kaitoi.io/docs/cli/web-and-media/): Research with cited public sources, prepare a media brief, review a generation quote, and recover an existing result when downloading or saving fails.
- [Kaitoi projects, graphs and custom nodes](https://kaitoi.io/docs/cli/kaitoi-workflows/): Build Kaitoi workflows from Code, inspect real node schemas, distinguish inline runs from saved projects, and validate custom nodes before installation.
- [Keyboard shortcuts and slash commands](https://kaitoi.io/docs/cli/shortcuts/): Find Code's keyboard shortcuts and command families, distinguish steering from queueing, and understand how Escape behaves at a prompt or approval card.
- [Extensions overview](https://kaitoi.io/docs/cli/mcp-skills-and-commands/): Extend Kaitoi Code with MCP servers, skills in SKILL.md folders, your own slash commands and hooks, each under your control.
- [MCP servers](https://kaitoi.io/docs/cli/mcp-servers/): Add external tools to Code, resolve user and project server settings, approve the launch, sign in when required, and set separate per-tool grants.
- [Skills and project commands](https://kaitoi.io/docs/cli/skills-and-commands/): Package reusable instructions as a skill, add a project slash command, understand discovery precedence, and keep prompt expansion separate from execution.
- [Hooks](https://kaitoi.io/docs/cli/hooks/): Run reviewed automation at Code events, configure hook matching and timeouts, and distinguish blocking decisions from context and after-the-fact feedback.
- [Project instructions and memory](https://kaitoi.io/docs/cli/instructions-and-memory/): Put durable project guidance where Code can load it, understand parent and nested instruction scope, and keep bounded project memory concise and current.
- [Subagents and background agents](https://kaitoi.io/docs/cli/subagents/): Delegate a bounded task, choose a role and lifetime, monitor background agents, and distinguish shared-workspace work from worktree isolation and Crew.
- [Claude Code and Codex engines](https://kaitoi.io/docs/cli/engines/): Assign subagent roles to Kaitoi, local, Claude Code, or Codex engines, understand credential and billing boundaries, and review the engine's start grant.
- [Your first Crew run](https://kaitoi.io/docs/cli/crew/): Define a bounded coding task for Crew, choose its engines and verification commands, and review workspace preparation, checkout mirroring, and budgets.
- [Monitor, steer and resume runs](https://kaitoi.io/docs/cli/crew-controls/): Follow the correct Crew run, distinguish pause, interrupt, cancel, and continuation, and use fresh state versions when controlling a durable run.
- [Worktrees, verification and results](https://kaitoi.io/docs/cli/crew-results/): Inspect a Crew candidate and its evidence, understand guarded checkout mirroring, and keep saved work, verified completion, integration, and release distinct.
- [Crew command reference](https://kaitoi.io/docs/cli/crew-reference/): Look up Crew commands, run flags, spending limits, continuation grants and recorded phases before starting or recovering a coding run.
- [VS Code extension](https://kaitoi.io/docs/cli/vscode/): Connect the VS Code chat view to your installed Kaitoi CLI, add selected code as context, and handle workspace trust, permissions, diffs, and cancellation.
- [Connect other editors with ACP](https://kaitoi.io/docs/cli/acp/): Configure an ACP editor to launch Kaitoi Code over standard input and output, resume saved sessions, and handle authentication, context, and permissions.
- [Headless runs and JSON events](https://kaitoi.io/docs/cli/headless/): Run one Code turn from a prompt or standard input, constrain workspace authority and cost, and consume JSON events without confusing them with session SSE.
- [Local session HTTP API](https://kaitoi.io/docs/cli/session-api/): Start a loopback Code server, create trusted sessions, submit messages, follow resumable events, and answer permissions using the local session API.
- [Python SDK](https://kaitoi.io/docs/cli/python-sdk/): Connect Python to a running local Code server, iterate one turn or follow a session, answer specific permissions, and cancel work with the correct lifecycle.
- [GitHub Actions](https://kaitoi.io/docs/cli/github-actions/): Configure a bounded GitHub integration, understand comment triggers and runner authority, and distinguish a dry run from remote comments, pushes, and PRs.
- [Connect local services](https://kaitoi.io/docs/cli/connect/): Bring a local Runtime or model service into Kaitoi through a tunnel, distinguish service health from readiness, and stop the resources you actually started.
- [Install and run recipes](https://kaitoi.io/docs/cli/recipes/): Find recipes, inspect requirements, install and run them with declared inputs, and connect their outputs to Studio while keeping local and cloud files distinct.
- [Create recipes](https://kaitoi.io/docs/cli/create-recipes/): Define a recipe with YAML and a companion script, map inputs to command arguments, collect declared outputs, and distinguish generation from verified execution.
- [Runtime API](https://kaitoi.io/docs/cli/runtime-api/): Submit local recipe jobs, poll their status, upload inputs and retrieve outputs, and distinguish Runtime's short-lived job store from Code's session API.
- [Troubleshooting](https://kaitoi.io/docs/cli/troubleshooting/): Find the failing layer in a Kaitoi CLI workflow, collect diagnostics, and recover models, permissions, extensions, processes, and Crew without losing work.
- [Plans and availability](https://kaitoi.io/docs/reference/plans/): Check personal and team plan access, included credits, seats and current offers, then diagnose the other requirements behind unavailable features.
- [Credits and costs](https://kaitoi.io/docs/reference/credits/): Read estimates and actual charges, understand available and held balances, and find project and account spending records.
- [Privacy and permissions](https://kaitoi.io/docs/reference/privacy-and-permissions/): Understand which owner, provider, recipient, or connected tool receives workflow data, and manage sharing, permissions, and access deliberately.
- [Troubleshooting](https://kaitoi.io/docs/reference/troubleshooting/): Identify whether a failure belongs to inputs, execution, provider access, files, saving, or an external client before retrying.
- [Versions and updates](https://kaitoi.io/docs/reference/versions-and-updates/): Distinguish application, project, Station, node-package, and local-tool versions when checking compatibility, updating work, or reporting problems.
<!-- END generated: docs -->

## Company

- [About Kaitoi Labs](https://kaitoi.io/about/): Kaitoi Labs builds technology that expands human creativity, combining artificial intelligence, filmmaking, visual effects, systems design, and product design.
- [FAQ](https://kaitoi.io/faq/): Frequently asked questions about Kaitoi, the AI-native orchestration platform for creative professionals.
- [News](https://kaitoi.io/blog/): Product announcements, release notes and writing from the team building Kaitoi. Feed at https://kaitoi.io/rss.xml.
- [Careers](https://kaitoi.io/careers/): Careers at Kaitoi Labs. We are not hiring right now; the page keeps our most recent roles for reference.
- [Press](https://kaitoi.io/press/): Press resources for Kaitoi Labs: a fact sheet, boilerplate, leadership bios, logos to download, announcements and the press contact, press@kaitoi.io.
- [Contact](https://kaitoi.io/contact/): Ask about Kaitoi products, support, billing, privacy, or partnerships.

## Legal

- [Privacy Policy](https://kaitoi.io/privacy/)
- [Terms of Service](https://kaitoi.io/terms/)