# Cortex Docs

> Documentation for Cortex Chat, Cortex Code, Cortex Bot, Cortex Design, Cortex Security, and the Cortex CLI.

- [Cortex documentation](https://docs.cortex.foundation/index.md): Guides for every Cortex application: Chat, Code, Bot, the CLI, Design and Security, plus accounts, plans, settings and reference.
- [Quickstart](https://docs.cortex.foundation/getting-started/quickstart.md): Open Cortex in a browser, get a first answer from Chat as a guest, then sign in and open Code, Bot, Design, Security or the CLI.
- [What is Cortex](https://docs.cortex.foundation/getting-started/what-is-cortex.md): One account on cortex.foundation behind Chat, Code, Bot, the CLI, Design and Security, running on the Cortex models.
- [Which product do I need?](https://docs.cortex.foundation/getting-started/choose-a-product.md): A task table that maps what you want to do to the right Cortex application, plus what each one needs before it will open.
- [Accounts and sign-in](https://docs.cortex.foundation/getting-started/accounts.md): Cortex Chat works without an account. One sign-in opens Chat, Code, Bot, Security, the desktop apps and the CLI.
- [Two-factor authentication](https://docs.cortex.foundation/getting-started/two-factor.md): Link an authenticator app to your Cortex account. The second factor confirms data export and account deletion.
- [Plans and quotas](https://docs.cortex.foundation/getting-started/plans.md): Guest, Free, Go, Plus and Pro: the message windows each plan allows, what the app draws as a meter, and how a limit fails.
- [Settings](https://docs.cortex.foundation/getting-started/settings.md): Settings opens as an overlay over Chat, Code or Bot. Seven tabs in two groups, plus a search that looks across all of them.
- [Data and privacy](https://docs.cortex.foundation/getting-started/data-and-privacy.md): Export or delete your Cortex data, set a cookie preference, manage memory, and see what Cortex keeps and for how long
- [Notifications](https://docs.cortex.foundation/getting-started/notifications.md): One notification inbox for Chat, Code and Bot: what Cortex tells you about, what the dot on the bell means, and how rows are marked read
- [Interface language](https://docs.cortex.foundation/getting-started/language.md): The eight languages Cortex is translated into, how to switch, what stays in English, and how the language prefix in the address bar works
- [Ways to run Cortex](https://docs.cortex.foundation/getting-started/downloads.md): Where each Cortex application runs, which ones you can run today, and how each one keeps itself up to date.
- [Cortex desktop app](https://docs.cortex.foundation/getting-started/desktop.md): Install and sign in to the Chat and Code desktop app, run Code on This PC, and let it keep itself up to date.
- [Troubleshooting](https://docs.cortex.foundation/getting-started/troubleshooting.md): The messages Cortex shows when something will not run, what each one means, and what to do, grouped by what you were trying to do
- [Keyboard shortcuts](https://docs.cortex.foundation/getting-started/keyboard-shortcuts.md): The chords the Cortex web app really binds, where each one works, and which surfaces have no shortcuts of their own.
- [Report a bug](https://docs.cortex.foundation/getting-started/report-a-bug.md): File a bug from inside Cortex: where the dialog lives, what to write, screenshot limits, what is sent, and where other reports go.
- [Frequently asked questions](https://docs.cortex.foundation/getting-started/faq.md): Short answers about accounts, plans, quotas, privacy, languages and what is not built yet, each pointing at the page that owns it.
- [Glossary](https://docs.cortex.foundation/getting-started/glossary.md): The Cortex words you meet across this site, in alphabetical order, each with a link to the page that owns it.
- [Cortex Chat](https://docs.cortex.foundation/chat/index.md): The conversation product at cortex.foundation: streaming answers, attachments, projects, research, and a map of every Chat page
- [Chat quickstart](https://docs.cortex.foundation/chat/quickstart.md): Send your first message, read the answer, pick a model, attach a file, and keep the thread in a project
- [How Chat works](https://docs.cortex.foundation/chat/how-it-works.md): A turn is one message plus everything Cortex does to answer it: tools, citations, compaction, what is stored, and where the limits sit
- [Conversations](https://docs.cortex.foundation/chat/conversations.md): Start, name, edit, branch, pin, archive, delete and search your Chat threads, and what a temporary chat does differently
- [Models and thinking](https://docs.cortex.foundation/chat/models.md): The two models Cortex Chat offers, what the Preview badge means, why the model is fixed per conversation, and the three thinking levels
- [Attachments and files](https://docs.cortex.foundation/chat/attachments.md): Send a file with a message: what Cortex Chat accepts, the 10 MB ceiling, what text is read out of a document, and where uploads land
- [Streaming and reconnects](https://docs.cortex.foundation/chat/streaming.md): Answers arrive in pieces as they are written, you can stop or steer them, and a dropped connection resumes instead of starting over
- [Voice](https://docs.cortex.foundation/chat/voice.md): Dictate a message with the microphone and hear an answer read back with Listen, including what each control sends and when it is missing
- [Chat canvases](https://docs.cortex.foundation/chat/canvases.md): A document that sits beside a conversation. Cortex drafts into it, you edit it, and it saves itself while you type.
- [Export documents](https://docs.cortex.foundation/chat/document-export.md): What a chat can turn into a file: a deck built from an editable outline, the formats a research report can offer, and a CSV from a table.
- [Projects](https://docs.cortex.foundation/chat/projects.md): A project keeps standing instructions, its chats and its sources together, so every chat inside it starts from the same brief.
- [Library](https://docs.cortex.foundation/chat/library.md): Every file your account holds: what you uploaded, what Chat produced, and what you attached from a connected drive.
- [Sharing files and connected drives](https://docs.cortex.foundation/chat/library-sharing.md): Share a Library file as a Viewer or Editor grant, copy a link, connect a cloud drive, and attach drive items without a second upload.
- [Memory](https://docs.cortex.foundation/chat/memory.md): What Cortex remembers, how to review, edit, delete, export and import it, and how to scope memory to a single project.
- [Planning](https://docs.cortex.foundation/chat/plans.md): The task-list surface in Cortex Chat: start a plan from the Planning page or from a chat, then tick steps off as the work moves.
- [Scheduled tasks](https://docs.cortex.foundation/chat/scheduled-tasks.md): Run a prompt on a cadence inside a conversation you already have, and read the answer in that chat like any other turn.
- [Built-in tools](https://docs.cortex.foundation/chat/tools.md): How a Chat turn reaches past the model: web search and reading, a Python sandbox, memory, stored results, and the tools you add yourself.
- [Deep Research](https://docs.cortex.foundation/chat/deep-research.md): Plan the questions, read live sources, and get a report with numbered citations you can open in a reader and save to Library.
- [Image generation](https://docs.cortex.foundation/chat/image-generation.md): Ask Cortex Chat for a picture, follow the card as it generates, and find the finished image in your Library with its prompt and seed.
- [Origin check](https://docs.cortex.foundation/chat/origin-check.md): Attach a photo or a clip and ask whether it is authentic. Cortex answers with one of three verdicts, or says plainly that the check could not run.
- [Cortex Data](https://docs.cortex.foundation/chat/data.md): Connect a business-metrics source to your account, ask metric questions in a chat, and pin a chart on the thread.
- [Skills in Chat](https://docs.cortex.foundation/chat/skills.md): A skill is a short recipe the model loads when it applies. Some ship with Cortex; the ones you write are scanned before they can be enabled.
- [Connectors](https://docs.cortex.foundation/chat/plugins.md): Connect an app to Cortex Chat and Cortex Bot, choose where its tools appear, set when Cortex asks before it acts, and disconnect
- [MCP servers](https://docs.cortex.foundation/chat/mcp-servers.md): Attach a Model Context Protocol server over HTTP, sign in when the server asks, see how its tools appear in a chat, and remove it again
- [Page tools](https://docs.cortex.foundation/chat/page-tools.md): Tools a web page offers to Cortex: how they are discovered, and the consent card where you deny, allow once, or always allow each one
- [Sharing and teams](https://docs.cortex.foundation/chat/sharing.md): Cortex Chat is per account: what that means for conversations, projects, plans and files, and how to hand a result to someone today.
- [Chat troubleshooting](https://docs.cortex.foundation/chat/troubleshooting.md): The messages Chat shows when a send, an answer, a file, a document, a limit or a search does not go through, and what to do about each.
- [Cortex Code](https://docs.cortex.foundation/code/index.md): Cortex Code is a coding agent that works in one repository inside an isolated Cloud guest, with a timeline you watch and changes you approve.
- [Code quickstart](https://docs.cortex.foundation/code/quickstart.md): Sign in, connect GitHub, start a Cloud session on a repository, read the timeline and approve your first change.
- [How Code works](https://docs.cortex.foundation/code/how-it-works.md): Cause and effect in a Code turn: where tools run, how a mode locks the toolset, the two approval gates, compaction, and how a turn ends.
- [Code sessions](https://docs.cortex.foundation/code/sessions.md): What a Code session is, how to find and read one, follow-ups, attach and detach, stopping a turn, and what survives when it ends.
- [Ask, Plan, Agent](https://docs.cortex.foundation/code/interactions.md): Ask reads and explains, Plan proposes, Agent edits and runs. The mode locks the tools a turn is built with and applies to the next turn.
- [Permissions and approvals](https://docs.cortex.foundation/code/approvals.md): Commands ask with Allow once, Always allow and Deny. File writes never use that rail: they wait in Changes for a human Approve.
- [Changes and diffs](https://docs.cortex.foundation/code/changes.md): The Changes pane is where a file write waits for a human Approve, and where a proposed diff becomes a landed one.
- [Tickets](https://docs.cortex.foundation/code/tickets.md): A ticket is a unit of asynchronous work with a title, a body and a status. Tickets have no screen in Cortex Code yet.
- [Cloud runtimes](https://docs.cortex.foundation/code/runtimes.md): What a browser Code session runs in: an isolated Cloud guest, how it starts and hibernates, and what happens when there is no capacity.
- [Environments and images](https://docs.cortex.foundation/code/environments.md): Start an environment for a repository, save it as an image so the next session skips the install, then launch, rebuild or delete it.
- [Machines](https://docs.cortex.foundation/code/machines.md): What the Machines page shows: Cloud occupancy and team runners, why your paired desktop machine is not listed, and what to do instead.
- [SSH hosts](https://docs.cortex.foundation/code/ssh-hosts.md): SSH is one of three runtime kinds a Code session can bind. Hosts are registered in the Cortex desktop app, and keys never reach your browser.
- [Code on desktop](https://docs.cortex.foundation/code/desktop.md): What the Cortex desktop app adds to Code: This PC and SSH next to Cloud, its own screens, and the host status it reports.
- [Connect GitHub](https://docs.cortex.foundation/code/github.md): One control, one label, and no token to paste: how Cortex Code reaches your repositories, and what every failure message means.
- [Repositories and branches](https://docs.cortex.foundation/code/repositories.md): Choose the repository and base branch a Code session works on, and understand the isolated worktree and the branches a session may push.
- [Automations](https://docs.cortex.foundation/code/automations.md): Automations are saved instructions for Cortex Code: a trigger, a repository and a prompt. Nothing runs unattended yet, and the page says so.
- [Code notifications](https://docs.cortex.foundation/code/notifications.md): The Notifications inbox: everything Cortex has told you about, newest first, with one row per thing that happened and one button to clear them.
- [Usage](https://docs.cortex.foundation/code/usage.md): Read the Usage page: recorded cost and billable actions over a 7, 30 or 90 day window, the breakdowns, and what the ledger can honestly tell you.
- [Code settings](https://docs.cortex.foundation/code/settings.md): Code settings holds model defaults for your workspace. Everything else about a session is chosen when you start it, not saved here.
- [Code integrations](https://docs.cortex.foundation/code/integrations.md): The Integrations page: connected apps, repositories, MCP servers and API keys, and the important limit on what a Code session can actually reach.
- [Code in the terminal](https://docs.cortex.foundation/code/cli.md): The Cortex CLI drives the same Code sessions from a shell: what carries across, how the words map, and which CLI pages answer the rest.
- [Pull-request review](https://docs.cortex.foundation/code/security.md): Cortex Security reads a pull request instead of writing one. Where it sits inside Code, how to reach it, and which tab documents it.
- [Code troubleshooting](https://docs.cortex.foundation/code/troubleshooting.md): What Cortex Code tells you when something is wrong, what each message actually means, and which page owns the fix.
- [Cortex Bot](https://docs.cortex.foundation/bot/index.md): A bot with its own computer: it browses, clicks and works on a desktop you can watch, and asks before anything consequential
- [Bot quickstart](https://docs.cortex.foundation/bot/quickstart.md): Sign in, create your first bot, open its computer, give it a task, and approve its first consequential step
- [How Bot works](https://docs.cortex.foundation/bot/how-it-works.md): The bot turn in user terms: no round limit, a 15-minute deadline, a stuck guard, approvals, wake cues, and what actually reaches you
- [Create a bot](https://docs.cortex.foundation/bot/create-a-bot.md): Every field on the New bot form: name, look and face, description, label, notifications, skills and connected apps, then settings and delete
- [Talking to a bot](https://docs.cortex.foundation/bot/conversations.md): Direct messages with a bot: what a thread shows, the questions it asks you, outbound drafts, in-thread search, and what its status word means.
- [Computer](https://docs.cortex.foundation/bot/computer.md): The Computer rail: start and wake a bot's desktop, watch it live, take control, record a session, and understand hibernation.
- [Bot tools](https://docs.cortex.foundation/bot/tools.md): The catalog a bot receives: files and shell, the desktop verbs, browser and web, memory and skills, messaging, tasks, other bots, and your connected apps.
- [Approvals and tool policy](https://docs.cortex.foundation/bot/approvals.md): Allow, Deny and Always: how a bot parks a consequential step, which tools always ask, and the rules and tiers that decide before you are asked.
- [Bot memory](https://docs.cortex.foundation/bot/memory.md): The profile, log and notes a bot keeps between turns, how to add and delete an entry, and how it differs from Chat memory
- [Bot skills](https://docs.cortex.foundation/bot/skills.md): Recipes a bot may follow: the catalog, the scan that gates every skill, enabling one on a bot, running it, and what a skill does not grant
- [Routines](https://docs.cortex.foundation/bot/routines.md): Recurring work on one bot: create a routine, the local weekday schedule, pause and resume, the run record, and sharing a schedule
- [Tasks and subagents](https://docs.cortex.foundation/bot/tasks.md): The nested subagents a bot dispatches inside a turn: the kinds, background results, the one desktop worker rule, limits, cancelling, and bot-to-bot messages
- [Connected apps and secrets](https://docs.cortex.foundation/bot/plugins.md): Assign a connected app to one bot, how its tools ask before they act, the sealed vault behind a secret request, and the MCP servers a bot receives
- [Inbox](https://docs.cortex.foundation/bot/inbox.md): Everything that needs you across every bot you own: the Working, Pending, Inbox and All filters, what each row can be, and read state
- [Channels](https://docs.cortex.foundation/bot/rooms.md): Group threads for the bots you own: create a channel, add members, address one bot with an at-mention, and what rooms would have added
- [Share a bot](https://docs.cortex.foundation/bot/sharing.md): Invite someone to a bot by email, what the independent copy carries and what it never does, accept a share, and share a routine
- [Teach from a demonstration](https://docs.cortex.foundation/bot/teach.md): Show a bot a job on its own computer, read the draft skill it writes from what you did, then save it, schedule it, or record it again
- [Bot desktop app](https://docs.cortex.foundation/bot/desktop.md): Sign in to the Cortex Bot desktop app, work its Inbox, Routines and Plugins rail, grant Background computer, and update it.
- [Bot troubleshooting](https://docs.cortex.foundation/bot/troubleshooting.md): What each Bot message means and what to do: the desktop stream, parked steps, missing tools, turns that stop early, routines, and error codes
- [Cortex CLI](https://docs.cortex.foundation/cli/index.md): Cortex Code in the terminal: an interactive session view, one-shot runs, headless runs for scripts, and every page of the CLI documentation
- [Install the CLI](https://docs.cortex.foundation/cli/install.md): Install Cortex CLI on macOS, Linux or Windows, pin a version or a channel, keep it current with cortex upgrade, and uninstall it cleanly
- [Sign in to the CLI](https://docs.cortex.foundation/cli/sign-in.md): Sign in to Cortex CLI from a browser, with a device code, through single sign-on, or with an API key for unattended runs
- [CLI quickstart](https://docs.cortex.foundation/cli/quickstart.md): From nothing installed to a finished first turn in a project: install, sign in, start a session, write AGENTS.md, and choose an autonomy level
- [The TUI](https://docs.cortex.foundation/cli/tui.md): What is on screen when you run cortex: the timeline, the composer and its chips, the footer hints, the panels, and the alternate screen
- [Modes and permissions](https://docs.cortex.foundation/cli/modes-and-permissions.md): The four composer modes, the approval prompt, the sandbox, the permission table, and the reasoning-effort options
- [Plan and Spec modes](https://docs.cortex.foundation/cli/plan-mode.md): Have Cortex work out what it would do before anything changes: Plan mode, Spec mode, and what a structured plan contains
- [CLI sessions](https://docs.cortex.foundation/cli/sessions.md): Every interactive run is a session written to disk: list, resume, rewind, fork, export, import, share, protect and clean up
- [Goals](https://docs.cortex.foundation/cli/goal.md): Attach a long-horizon objective to a CLI session with /goal: it survives compaction and resume, carries a turn budget, and completes on evidence
- [Slash commands](https://docs.cortex.foundation/cli/slash-commands.md): Every built-in command you can type after / in the Cortex CLI composer, grouped by purpose, plus aliases and your own project commands
- [CLI keyboard shortcuts](https://docs.cortex.foundation/cli/keyboard.md): The key bindings in the Cortex CLI, grouped by where they apply: global, the composer, a running turn, the approval prompt, and the dialogs
- [Tools the agent uses](https://docs.cortex.foundation/cli/tools.md): The tools a CLI agent can call: reading, searching, editing, shell, language server, web, delegation, and how each call passes the sandbox and approval gates
- [Cloud, This PC, and SSH](https://docs.cortex.foundation/cli/hosts.md): Where a CLI session runs its tools: Cortex Cloud by default, with This PC and SSH as opt-in hosts that fail closed
- [Editor integration](https://docs.cortex.foundation/cli/editor.md): What exists today: the CLI in your editor's terminal, and an Agent Client Protocol server over stdio. There is no packaged extension.
- [Headless and one-shot runs](https://docs.cortex.foundation/cli/headless.md): cortex exec for scripts and automation, cortex run for a single streamed answer: autonomy levels, output formats, limits and exit codes
- [CI cookbook](https://docs.cortex.foundation/cli/ci.md): Run the CLI in a pipeline: pick a command, pass the secret through the environment, set the autonomy level, and fail the job on the exit code
- [Configuration](https://docs.cortex.foundation/cli/configuration.md): How Cortex CLI reads config.toml, the keys you can set, named profiles, and which layer wins when two files disagree.
- [Environment variables](https://docs.cortex.foundation/cli/environment-variables.md): The CORTEX_* variables Cortex CLI reads, what each one overrides, and where variables sit between config files and flags.
- [Data locations](https://docs.cortex.foundation/cli/data-locations.md): Where Cortex CLI keeps config, sessions, agents, skills, plugins, caches and logs on each platform, and how to reclaim the space.
- [Permission policy](https://docs.cortex.foundation/cli/policy.md): Set allow, ask and deny rules for tools and commands in Cortex CLI, restrict the sandbox, and understand a managed organization policy.
- [MCP servers in the CLI](https://docs.cortex.foundation/cli/mcp.md): Connect Model Context Protocol servers to the CLI: the three transports, tokens, tool names, permissions, and the server panel
- [Skills in the CLI](https://docs.cortex.foundation/cli/skills.md): Teach the CLI a procedure once: what a skill file contains, where the CLI looks for it, how the agent loads it, and how to gate one
- [Agents and subagents](https://docs.cortex.foundation/cli/agents.md): Named configurations for how the CLI behaves, the tool categories they grant, and the subagents the main agent delegates to
- [Hooks](https://docs.cortex.foundation/cli/hooks.md): How a hook reaches a CLI session: the plugin manifest block, the events that fire, the order they run in, and why a hook can deny but never approve
- [CLI plugins](https://docs.cortex.foundation/cli/plugins.md): Install, review, trust and build Cortex CLI plugins: the plugin commands, the manifest, manifest hooks, and the limits a plugin cannot cross.
- [Themes](https://docs.cortex.foundation/cli/themes.md): The four built-in CLI themes, the picker with live preview, and the configuration keys that control colour and the rest of the display.
- [Command reference](https://docs.cortex.foundation/cli/reference.md): The supported cortex command surface: global options, run and exec, sessions, auth, bounty, agents, MCP, plugins, config, utilities and maintenance.
- [CLI troubleshooting](https://docs.cortex.foundation/cli/troubleshooting.md): Start with six commands, then work through the messages: service unavailable, hosts that refuse, an agent that will not edit, MCP, timeouts and quotas.
- [Cortex Design](https://docs.cortex.foundation/design/index.md): Boards of frames and notes, hosted from a Chat thread or a Code session and edited in the Cortex Design desktop app.
- [Design quickstart](https://docs.cortex.foundation/design/quickstart.md): Open the Cortex Design app, create your first canvas, generate options, pick one, save a version and export it.
- [Design canvases](https://docs.cortex.foundation/design/canvases.md): What a design canvas holds, the thread that hosts it, the canvases rail, the Designs gallery, renaming, deleting and the 200-canvas cap.
- [Generate and edit](https://docs.cortex.foundation/design/editor.md): The Cortex Design editor: generate options as lettered frames, pick one, ask for a change, choose a model, and retry an option that failed.
- [Versions](https://docs.cortex.foundation/design/versions.md): Every save of a design canvas is a numbered version you can view, restore, or compare from the Versions rail in the Design desktop app.
- [Design library](https://docs.cortex.foundation/design/library.md): The account-level set of components, pages, and tokens you reuse across every design canvas, and how it differs from the Chat Library.
- [Export a design](https://docs.cortex.foundation/design/export.md): Take a frame, a selection, or a whole canvas out of Cortex Design as a PNG rendered on your machine or as the canvas document in JSON.
- [Bot jobs](https://docs.cortex.foundation/design/bot-jobs.md): What the Bot jobs surface in Cortex Design is meant for, why handing a design to a Cortex Bot is not available yet, and what to do instead.
- [Design connectors](https://docs.cortex.foundation/design/plugins.md): The Plugins page in the Cortex Design window: browsing the connector catalogue, connecting an app, and reconnecting one whose access expired.
- [Design desktop app](https://docs.cortex.foundation/design/desktop.md): The Cortex Design window: its sidebar, the Designs gallery, light and dark, offline states, and the download that is not published yet.
- [Design settings](https://docs.cortex.foundation/design/settings.md): The Settings panes inside the Cortex Design window: General, Models, and Data and privacy, and which rows are not switched on yet.
- [Design troubleshooting](https://docs.cortex.foundation/design/troubleshooting.md): What a Cortex Design refusal means: signed out, a canvas that is not available, the canvas cap, a save that clashed, an option that did not finish.
- [Cortex Security](https://docs.cortex.foundation/security/index.md): GitHub pull-request review that reads the change in the repository, posts a check run, and never turns a failed review green
- [Security quickstart](https://docs.cortex.foundation/security/quickstart.md): Install the Cortex Security GitHub App on a repository, open a pull request, and read the check run and summary comment it posts
- [How a review works](https://docs.cortex.foundation/security/how-a-review-works.md): The stages a review moves through, the second pass that checks every finding, and why the verdict is arithmetic rather than an opinion
- [Checks and comments](https://docs.cortex.foundation/security/checks.md): The Cortex Security check run and its three conclusions, the summary comment, what an inline finding contains, and how to ask for another look
- [Review policy](https://docs.cortex.foundation/security/review-policy.md): The settings that decide when Cortex Security reviews a pull request, what it reports, how hard a finding lands, and why approval stays with a person
- [Repository scans](https://docs.cortex.foundation/security/scans.md): Run an on-demand or weekly scan of a repository you own, read its findings, dismiss one, hand a patch to Cortex Code, or export the scan
- [Cortex Agent runs](https://docs.cortex.foundation/security/agent.md): How Cortex Agent gathers evidence by running a change in an isolated runtime, what a run page shows, and why a run is never a pass
- [Installation and repositories](https://docs.cortex.foundation/security/repositories.md): The Cortex Security GitHub App: what it asks for, which repositories it reviews, Security mode, and the four ways to stop reviews
- [Security troubleshooting](https://docs.cortex.foundation/security/troubleshooting.md): What to check when no check run appears, a review reads Not reviewed, comments are missing, a finding looks wrong, or a scan will not start
- [Errors](https://docs.cortex.foundation/reference/errors.md): Every Cortex failure is an RFC 9457 problem document. Branch on code, quote the reference id, and know which fields are safe to show.
- [Problem catalog](https://docs.cortex.foundation/problems/index.md): Every Cortex error code, its HTTP status, whether retrying helps, and the page that explains it.
- [validation_failed](https://docs.cortex.foundation/problems/validation_failed.md): Validation failed. HTTP 422.
- [bad_request](https://docs.cortex.foundation/problems/bad_request.md): Bad request. HTTP 400.
- [idempotency_key_reuse](https://docs.cortex.foundation/problems/idempotency_key_reuse.md): Idempotency key reused with a different body. HTTP 400.
- [payload_too_large](https://docs.cortex.foundation/problems/payload_too_large.md): Payload too large. HTTP 413.
- [unsupported_media_type](https://docs.cortex.foundation/problems/unsupported_media_type.md): Unsupported media type. HTTP 415.
- [unauthenticated](https://docs.cortex.foundation/problems/unauthenticated.md): Authentication required. HTTP 401.
- [invalid_credential](https://docs.cortex.foundation/problems/invalid_credential.md): Credential is invalid or expired. HTTP 401.
- [forbidden](https://docs.cortex.foundation/problems/forbidden.md): Not permitted. HTTP 403.
- [entitlement_required](https://docs.cortex.foundation/problems/entitlement_required.md): Your plan does not include this. HTTP 403.
- [not_found](https://docs.cortex.foundation/problems/not_found.md): Not found. HTTP 404.
- [conflict](https://docs.cortex.foundation/problems/conflict.md): Conflict. HTTP 409.
- [gone](https://docs.cortex.foundation/problems/gone.md): No longer available. HTTP 410.
- [invalid_state](https://docs.cortex.foundation/problems/invalid_state.md): Not allowed in the current state. HTTP 422.
- [quota_exceeded](https://docs.cortex.foundation/problems/quota_exceeded.md): Plan limit reached. HTTP 429.
- [rate_limited](https://docs.cortex.foundation/problems/rate_limited.md): Too many requests. HTTP 429.
- [concurrency_limit_reached](https://docs.cortex.foundation/problems/concurrency_limit_reached.md): Too many runs at once. HTTP 429.
- [safety_intervention](https://docs.cortex.foundation/problems/safety_intervention.md): We want to make sure you are safe. HTTP 403.
- [content_policy](https://docs.cortex.foundation/problems/content_policy.md): Blocked by content policy. HTTP 403.
- [jurisdiction_restricted](https://docs.cortex.foundation/problems/jurisdiction_restricted.md): Not available in your region. HTTP 403.
- [internal](https://docs.cortex.foundation/problems/internal.md): Something went wrong on our side. HTTP 500.
- [upstream_failure](https://docs.cortex.foundation/problems/upstream_failure.md): An upstream service failed. HTTP 502.
- [upstream_timeout](https://docs.cortex.foundation/problems/upstream_timeout.md): An upstream service timed out. HTTP 504.
- [service_unavailable](https://docs.cortex.foundation/problems/service_unavailable.md): Temporarily unavailable. HTTP 503.
- [no_capacity](https://docs.cortex.foundation/problems/no_capacity.md): No capacity for this model right now. HTTP 503.
- [Models](https://docs.cortex.foundation/reference/models.md): The models Cortex publishes today, what Preview means, the context and output budgets, and which model a conversation runs on.
- [Limits and quotas](https://docs.cortex.foundation/reference/limits.md): Every user-facing limit in one place: the message windows per plan, storage, images, exports, projects, file size and timeouts.
- [Security and privacy](https://docs.cortex.foundation/reference/security-and-privacy.md): What Cortex stores and never stores, what stays on your device, how consent works across the products, and how export, deletion and retention behave
- [System status](https://docs.cortex.foundation/reference/status.md): Live availability for Cortex Web, API, Chat, Code and Bot: what the status page reports, what to do during an incident, and how maintenance appears
- [Platform API](https://docs.cortex.foundation/reference/platform-api.md): Cortex has no public inference API today: no endpoints, no SDKs, no API keys. What the Platform API is not, and what to use instead
- [Cortex Bounty](https://docs.cortex.foundation/bounty/index.md): The Cortex Bounty Challenge: pair a mining hotkey, file a report from Chat, and read every verdict on a public log
- [Pair a hotkey](https://docs.cortex.foundation/bounty/pair-a-hotkey.md): Accept the Cortex Bounty terms and link an SS58 mining hotkey to your Cortex account by signing the payload the CLI prints
- [File a report](https://docs.cortex.foundation/bounty/report.md): Mark a Chat conversation as a bounty-miner session, file a report with the Chat report tool, and see what the report carries
- [Verdicts and scoring](https://docs.cortex.foundation/bounty/scoring.md): The four Cortex Bounty statuses, the gates a verdict has to clear before it is published, and what can never become a valid row
- [Transparency API](https://docs.cortex.foundation/bounty/public-api.md): Four unauthenticated endpoints that publish every adjudicated Cortex Bounty report, with windows, paging, and how to read a zero
- [Changelog](https://docs.cortex.foundation/changelog.md): What shipped in Cortex Chat, Code, Bot, Design, Security, and the CLI, dated, with a link to the surface it changed.

## Optional

- [System status](https://status.cortex.foundation)
- [cortex.foundation](https://cortex.foundation)