# Foxora > Foxora is the first L5 autonomous multi-agent system. Describe an outcome in plain words; a crew of AI specialists plans it, builds it, checks its own work, and delivers the finished thing — with permanent shared memory. It runs as a desktop app, in the web, and as a CLI. Built by xBesh Labs, LLC. Free to start, no credit card, no separate AI accounts. This is the universal index for AI agents. Every page below is available as Markdown (append `.md`) and as an llms.txt card (append `.txt`). The whole platform as one Markdown knowledgebase: https://foxora.ai/llms-full.txt Key facts an assistant should know: - Foxora is a product, not a chatbot: it delivers finished outcomes, not just replies. - "L5 autonomous" borrows the self-driving levels: L5 = full autonomy. You review outcomes, not steps. Every action is logged and reversible. - Unlimited AI agents. 17 ready-made specialists ship out of the box; you can build any others (agents, crews, departments) with a one-sentence AI builder. - No API keys and no separate AI accounts — every model call routes through the Foxora gateway, metered in simple credits (Fast, Premium, and Max tiers). - 1,000+ app integrations (Gmail, GitHub, Slack, Stripe, and more); OAuth tokens are held by Composio, never on Foxora’s servers. - Permanent shared memory ("the Den") across desktop, web, and CLI — explain something once. - Built-in IDE with git; voice control; queue tasks to run in the cloud overnight. - Free to start, no credit card. macOS and Windows desktop apps (Linux CLI today, Linux desktop soon). ## Pages - [Home](https://foxora.ai/) ([md](https://foxora.ai/index.md), [txt](https://foxora.ai/index.txt)): What Foxora is and how it works — the crew, memory, plugins, IDE, voice, cloud agents, pricing, and FAQ. - [Pricing](https://foxora.ai/pricing) ([md](https://foxora.ai/pricing.md), [txt](https://foxora.ai/pricing.txt)): Credit-based pricing that covers the whole crew — every model, every surface. Free, Starter, Pro, and Max. - [Download](https://foxora.ai/download) ([md](https://foxora.ai/download.md), [txt](https://foxora.ai/download.txt)): Desktop app (macOS, Windows), the web app, and the one-line CLI install. - [CLI](https://foxora.ai/cli) ([md](https://foxora.ai/cli.md), [txt](https://foxora.ai/cli.txt)): A crew of agents in your terminal — install, command reference, and pipeline usage. - [Status](https://foxora.ai/status) ([md](https://foxora.ai/status.md), [txt](https://foxora.ai/status.txt)): Live status and response times for every Foxora service, from our own monitor. - [About](https://foxora.ai/about) ([md](https://foxora.ai/about.md), [txt](https://foxora.ai/about.txt)): Mission and the company behind Foxora (xBesh Labs, LLC). - [Brand](https://foxora.ai/brand) ([md](https://foxora.ai/brand.md), [txt](https://foxora.ai/brand.txt)): Logo, colors, and typography, with usage guidelines. ## Legal - [Privacy Policy](https://foxora.ai/privacy) ([md](https://foxora.ai/privacy.md), [txt](https://foxora.ai/privacy.txt)): What data Foxora collects, why, how it is protected, and your rights. Data is not used to train models. - [Terms of Service](https://foxora.ai/terms) ([md](https://foxora.ai/terms.md), [txt](https://foxora.ai/terms.txt)): The agreement governing use of the Foxora service, operated by xBesh Labs, LLC. - [Cookie Policy](https://foxora.ai/cookies) ([md](https://foxora.ai/cookies.md), [txt](https://foxora.ai/cookies.txt)): Essential cookies, preferences, analytics, and affiliate tracking. ## Documentation Full docs index: https://docs.foxora.ai/llms.txt · every docs page is available as Markdown (append `.md`). ### Getting Started - [Overview](https://docs.foxora.ai/getting-started/overview) ([md](https://docs.foxora.ai/getting-started/overview.md)): Set up Foxora in the safest order: install the appropriate client, sign in, choose an autonomy default, open a small project, and complete one verified task. - [Introduction to Foxora](https://docs.foxora.ai/getting-started/introduction-to-foxora) ([md](https://docs.foxora.ai/getting-started/introduction-to-foxora.md)): Understand the relationship between a task, project, agent, crew, Stage, tools, and local Memory Den before configuring advanced features. - [Installation](https://docs.foxora.ai/getting-started/installation) ([md](https://docs.foxora.ai/getting-started/installation.md)): Install Foxora on Windows or macOS, or set up the CLI and web app on Linux. - [System requirements](https://docs.foxora.ai/getting-started/system-requirements) ([md](https://docs.foxora.ai/getting-started/system-requirements.md)): Check OS version, CPU architecture, memory, disk space, internet access, and platform-specific runtimes before downloading an installer. - [First-run setup](https://docs.foxora.ai/getting-started/first-run-setup) ([md](https://docs.foxora.ai/getting-started/first-run-setup.md)): Finish browser sign-in, select a cautious autonomy default, review local-data permissions, choose a theme, and create the first task. - [Quickstart: complete your first task](https://docs.foxora.ai/getting-started/quickstart-complete-your-first-task) ([md](https://docs.foxora.ai/getting-started/quickstart-complete-your-first-task.md)): Open a small test folder, ask for one clearly measurable change, review the plan and approvals, then verify the changed file or command output. - [Updating Foxora](https://docs.foxora.ai/getting-started/updating-foxora) ([md](https://docs.foxora.ai/getting-started/updating-foxora.md)): Check the installed Desktop or CLI version, save active work, install the signed update, restart the runtime, and verify with a small task. - [Uninstalling and resetting Foxora](https://docs.foxora.ai/getting-started/uninstalling-and-resetting-foxora) ([md](https://docs.foxora.ai/getting-started/uninstalling-and-resetting-foxora.md)): Choose between removing the application, resetting preferences, clearing local tasks and memory, or deleting the account; export local data before destructive actions. ### Foxora Workspace - [Overview](https://docs.foxora.ai/workspace/overview) ([md](https://docs.foxora.ai/workspace/overview.md)): Learn the workspace regions and the rule that the active task controls the conversation, project, crew, autonomy mode, and Stage context. - [Application layout and navigation](https://docs.foxora.ai/workspace/application-layout-and-navigation) ([md](https://docs.foxora.ai/workspace/application-layout-and-navigation.md)): Move between the task rail, conversation, composer, Studio, Settings, and Stage without losing the active task. - [Command Center](https://docs.foxora.ai/workspace/command-center) ([md](https://docs.foxora.ai/workspace/command-center.md)): Open the Command Center with Ctrl+K or Command+K, search tasks and actions, use keyboard navigation, and execute the highlighted result. - [Panels and saved view state](https://docs.foxora.ai/workspace/panels-and-saved-view-state) ([md](https://docs.foxora.ai/workspace/panels-and-saved-view-state.md)): Resize, collapse, and reopen workspace panels; confirm Foxora restores useful layout state without changing task data. - [Keyboard shortcuts](https://docs.foxora.ai/workspace/keyboard-shortcuts) ([md](https://docs.foxora.ai/workspace/keyboard-shortcuts.md)): Open the shortcut reference, learn navigation and composer shortcuts, and resolve conflicts with operating-system or editor bindings. - [Appearance and themes](https://docs.foxora.ai/workspace/appearance-and-themes) ([md](https://docs.foxora.ai/workspace/appearance-and-themes.md)): Choose the color scheme, accent, density, and motion preferences; verify readability in conversation, editor, terminal, and Stage surfaces. ### Tasks - [Overview](https://docs.foxora.ai/sessions/overview) ([md](https://docs.foxora.ai/sessions/overview.md)): Understand what belongs to a task and how it differs from a project, agent, crew, workflow, schedule, and run. - [Starting a task](https://docs.foxora.ai/sessions/starting-a-session) ([md](https://docs.foxora.ai/sessions/starting-a-session.md)): Choose New Task, select a project when file work is required, set the crew and autonomy mode, and send an outcome-focused first request. - [Managing tasks](https://docs.foxora.ai/sessions/managing-sessions) ([md](https://docs.foxora.ai/sessions/managing-sessions.md)): Use the Tasks screen, search, filters, grid or list view, status badges, and Open action to find and resume work. - [Renaming and archiving tasks](https://docs.foxora.ai/sessions/renaming-pinning-and-archiving-sessions) ([md](https://docs.foxora.ai/sessions/renaming-pinning-and-archiving-sessions.md)): Use the task action menu to give work an outcome-based name, archive completed items, and restore them when the work becomes active again. - [Branching from an existing task](https://docs.foxora.ai/sessions/forking-sessions) ([md](https://docs.foxora.ai/sessions/forking-sessions.md)): Create a separate task before trying a substantially different approach so the original transcript and result remain reviewable. - [Checkpoints and task history](https://docs.foxora.ai/sessions/checkpoints-and-session-history) ([md](https://docs.foxora.ai/sessions/checkpoints-and-session-history.md)): Use the transcript and task state to locate important transitions, preserve evidence, and recover only after reviewing what will change. - [Multi-agent tasks](https://docs.foxora.ai/sessions/multi-agent-sessions) ([md](https://docs.foxora.ai/sessions/multi-agent-sessions.md)): Select Vixen, Zenko, or Kyubi Crew, follow delegated agent work, and verify the integrated result delivered by the lead. ### Projects - [Overview](https://docs.foxora.ai/projects/overview) ([md](https://docs.foxora.ai/projects/overview.md)): Understand how projects provide file boundaries and working directories while tasks provide conversational history and task state. - [Creating and opening projects](https://docs.foxora.ai/projects/creating-and-opening-projects) ([md](https://docs.foxora.ai/projects/creating-and-opening-projects.md)): Create a new folder or select an existing one, review the resolved path, attach it to the task, and confirm it becomes active. - [Working with local folders](https://docs.foxora.ai/projects/working-with-local-folders) ([md](https://docs.foxora.ai/projects/working-with-local-folders.md)): Open a local folder, inspect its top-level files, exclude unrelated or sensitive locations, and run a read-only orientation task first. - [Working with Git repositories](https://docs.foxora.ai/projects/working-with-git-repositories) ([md](https://docs.foxora.ai/projects/working-with-git-repositories.md)): Open or clone a repository, check branch and working-tree status, read repository instructions, and avoid mixing unrelated changes. - [Project context and instructions](https://docs.foxora.ai/projects/project-context-and-instructions) ([md](https://docs.foxora.ai/projects/project-context-and-instructions.md)): Add durable project rules such as commands, formatting, architecture, and verification expectations; test that a new task follows them. - [Scratchpads and temporary workspaces](https://docs.foxora.ai/projects/scratchpads-and-temporary-workspaces) ([md](https://docs.foxora.ai/projects/scratchpads-and-temporary-workspaces.md)): Start without a folder for questions or planning, then attach or create a project only when the task needs persistent files. - [Managing and removing projects](https://docs.foxora.ai/projects/managing-and-removing-projects) ([md](https://docs.foxora.ai/projects/managing-and-removing-projects.md)): Change the active project, detach a folder from a task, remove it from recent projects, and distinguish that from deleting files on disk. ### Web App & Cloud - [Overview](https://docs.foxora.ai/web-cloud/overview) ([md](https://docs.foxora.ai/web-cloud/overview.md)): Use Foxora from a browser and understand how cloud tasks, projects, execution, and artifacts differ from the local Desktop runtime. - [Starting a web task](https://docs.foxora.ai/web-cloud/starting-a-web-task) ([md](https://docs.foxora.ai/web-cloud/starting-a-web-task.md)): Create a browser task, choose its crew and autonomy mode, describe a verifiable outcome, and follow work without installing the Desktop app. - [Cloud projects and workspaces](https://docs.foxora.ai/web-cloud/cloud-projects-and-workspaces) ([md](https://docs.foxora.ai/web-cloud/cloud-projects-and-workspaces.md)): Understand the relationship between a web task, its Foxora Cloud project, and the isolated Daytona-backed workspace used for tool execution. - [Cloud execution and artifacts](https://docs.foxora.ai/web-cloud/cloud-execution-and-artifacts) ([md](https://docs.foxora.ai/web-cloud/cloud-execution-and-artifacts.md)): Follow cloud tool activity in the transcript, inspect generated artifacts in Preview or Code, and verify the final result before reusing it. - [Desktop versus web](https://docs.foxora.ai/web-cloud/desktop-versus-web) ([md](https://docs.foxora.ai/web-cloud/desktop-versus-web.md)): Choose Desktop for direct local files and Stage tools, or the web app for browser-based cloud work; do not assume local projects or task history automatically appear in both. - [Cloud workspace lifecycle](https://docs.foxora.ai/web-cloud/cloud-workspace-lifecycle) ([md](https://docs.foxora.ai/web-cloud/cloud-workspace-lifecycle.md)): Learn how Foxora creates, resumes, stops, and lifecycle-recreates isolated cloud workspaces while preserving the task and project record. - [Troubleshooting cloud workspaces](https://docs.foxora.ai/web-cloud/troubleshooting-cloud-workspaces) ([md](https://docs.foxora.ai/web-cloud/troubleshooting-cloud-workspaces.md)): Recover from cold starts, stale workspace handles, interrupted tool calls, missing artifacts, or project-state problems without deleting useful work. ### Task Composer - [Overview](https://docs.foxora.ai/composer/overview) ([md](https://docs.foxora.ai/composer/overview.md)): Learn how requests, attachments, slash commands, crew selection, autonomy, and follow-up messages combine within one task. - [Sending your first request](https://docs.foxora.ai/composer/sending-your-first-request) ([md](https://docs.foxora.ai/composer/sending-your-first-request.md)): Write one outcome-focused request, include constraints and verification criteria, send it, and review both the answer and performed actions. - [Slash commands](https://docs.foxora.ai/composer/slash-commands) ([md](https://docs.foxora.ai/composer/slash-commands.md)): Type `/` to browse the built-in commands, choose the workflow that matches the task, add arguments, and review the expanded work in the transcript. - [Adding files, images, and attachments](https://docs.foxora.ai/composer/adding-files-images-and-attachments) ([md](https://docs.foxora.ai/composer/adding-files-images-and-attachments.md)): Attach a file or image from the composer, confirm the correct item and size, explain what to inspect, and remove accidental attachments before sending. - [Selecting a crew or processing tier](https://docs.foxora.ai/composer/selecting-a-crew-or-processing-tier) ([md](https://docs.foxora.ai/composer/selecting-a-crew-or-processing-tier.md)): Open the crew picker, choose Fast, Pro, or Max based on complexity and plan access, then verify the selected crew before sending. The Pro crew uses Foxora’s premium processing pool. - [Voice and hands-free conversations](https://docs.foxora.ai/composer/voice-and-hands-free-conversations) ([md](https://docs.foxora.ai/composer/voice-and-hands-free-conversations.md)): Enable microphone access, select input and output devices, dictate a concise request, review the transcription, and stop listening when finished. - [Context and compaction](https://docs.foxora.ai/composer/context-and-compaction) ([md](https://docs.foxora.ai/composer/context-and-compaction.md)): Keep the task focused, ask for a summary before long transitions, inspect compaction notices, and start or fork a task when the objective changes. - [Transcripts and task history](https://docs.foxora.ai/composer/transcripts-and-conversation-history) ([md](https://docs.foxora.ai/composer/transcripts-and-conversation-history.md)): Scroll or search the local transcript, expand tool and agent activity, copy the required evidence, and export before clearing local data. ### Autonomy & Approvals - [Overview](https://docs.foxora.ai/autonomy-approvals/overview) ([md](https://docs.foxora.ai/autonomy-approvals/overview.md)): Understand the four task autonomy modes, their approval boundaries, and the separate `/plan` command. - [Ask Permissions mode](https://docs.foxora.ai/autonomy-approvals/ask-permissions-mode) ([md](https://docs.foxora.ai/autonomy-approvals/ask-permissions-mode.md)): Select Ask Permissions, send a task that needs a file edit or command, inspect the approval details, and approve or decline each action. - [Accept Edits mode](https://docs.foxora.ai/autonomy-approvals/accept-edits-mode) ([md](https://docs.foxora.ai/autonomy-approvals/accept-edits-mode.md)): Allow routine file edits while keeping command and higher-risk actions gated; review diffs frequently during the task. - [Auto mode](https://docs.foxora.ai/autonomy-approvals/auto-mode) ([md](https://docs.foxora.ai/autonomy-approvals/auto-mode.md)): Use Auto for a bounded task with clear constraints, monitor the transcript, and interrupt when Foxora reaches an unexpected decision or external side effect. - [Bypass Permissions mode](https://docs.foxora.ai/autonomy-approvals/bypass-permissions-mode) ([md](https://docs.foxora.ai/autonomy-approvals/bypass-permissions-mode.md)): Confirm the project is trusted and recoverable, select Bypass Permissions, acknowledge the warning, and return to a safer mode immediately afterward. - [Reviewing approval requests](https://docs.foxora.ai/autonomy-approvals/reviewing-approval-requests) ([md](https://docs.foxora.ai/autonomy-approvals/reviewing-approval-requests.md)): Read the action, target, command, working directory, and risk; approve once, decline, or revise the request instead of approving unclear work. - [Changing autonomy during a task](https://docs.foxora.ai/autonomy-approvals/changing-autonomy-during-a-task) ([md](https://docs.foxora.ai/autonomy-approvals/changing-autonomy-during-a-task.md)): Pause or wait for a safe boundary, change the task pill, confirm the new mode in the composer, and continue with an explicit instruction. - [Choosing the appropriate autonomy mode](https://docs.foxora.ai/autonomy-approvals/choosing-the-appropriate-autonomy-mode) ([md](https://docs.foxora.ai/autonomy-approvals/choosing-the-appropriate-autonomy-mode.md)): Classify the task by reversibility, data sensitivity, external impact, and environment; then choose the lowest mode that avoids unnecessary interruptions. ### The Stage - [Overview](https://docs.foxora.ai/stage/overview) ([md](https://docs.foxora.ai/stage/overview.md)): Understand how the Stage follows the active task and switches between plans, artifacts, files, terminal, browser, media, and supporting views. - [Understanding Stage panels](https://docs.foxora.ai/stage/understanding-stage-panels) ([md](https://docs.foxora.ai/stage/understanding-stage-panels.md)): Open a Stage item from the transcript, switch surfaces from the Stage menu, close finished surfaces, resize the panel, and return to the conversation without losing the active surface. - [Plans and live progress](https://docs.foxora.ai/stage/plans-and-live-progress) ([md](https://docs.foxora.ai/stage/plans-and-live-progress.md)): Open the plan checklist, follow active and completed steps, inspect blocked items, and verify the final step against real output. - [Artifacts and generated files](https://docs.foxora.ai/stage/artifacts-and-generated-files) ([md](https://docs.foxora.ai/stage/artifacts-and-generated-files.md)): Open an artifact from the transcript, inspect its rendered and source views, copy or save it, and confirm whether it is also written to the project. - [Images, diagrams, tables, and media](https://docs.foxora.ai/stage/images-diagrams-tables-and-media) ([md](https://docs.foxora.ai/stage/images-diagrams-tables-and-media.md)): Open the generated media surface, zoom or switch representation, check labels and underlying data, and export in the required format. - [Supporting surfaces](https://docs.foxora.ai/stage/supporting-surfaces) ([md](https://docs.foxora.ai/stage/supporting-surfaces.md)): Use process, memory, source-control, terminal, or browser panels to inspect the evidence behind an agent response and take over when needed. ### Terminal - [Overview](https://docs.foxora.ai/terminal/overview) ([md](https://docs.foxora.ai/terminal/overview.md)): Learn how project-scoped terminals, streamed output, approvals, background processes, and exit codes appear in Foxora. - [Running commands](https://docs.foxora.ai/terminal/running-commands) ([md](https://docs.foxora.ai/terminal/running-commands.md)): Open a terminal in the active project, inspect the command and working directory, approve when required, and read stdout, stderr, and exit code. - [Interactive processes](https://docs.foxora.ai/terminal/interactive-processes) ([md](https://docs.foxora.ai/terminal/interactive-processes.md)): Start an interactive command, keep its terminal focused for input, respond to prompts deliberately, and stop it cleanly when finished. - [Managing multiple terminals](https://docs.foxora.ai/terminal/managing-multiple-terminals) ([md](https://docs.foxora.ai/terminal/managing-multiple-terminals.md)): Create separate terminals for independent processes, name or identify each by command, switch without mixing input, and close only completed processes. - [Stopping and restarting processes](https://docs.foxora.ai/terminal/stopping-and-restarting-processes) ([md](https://docs.foxora.ai/terminal/stopping-and-restarting-processes.md)): Send the normal stop signal first, confirm the process exited and released its port, then restart with the same verified configuration. - [Terminal permissions and safety](https://docs.foxora.ai/terminal/terminal-permissions-and-safety) ([md](https://docs.foxora.ai/terminal/terminal-permissions-and-safety.md)): Inspect commands before approval, check path and environment assumptions, avoid untrusted shell interpolation, and use least privilege. ### Files & Editor - [Overview](https://docs.foxora.ai/files-editor/overview) ([md](https://docs.foxora.ai/files-editor/overview.md)): Understand the project tree, editor tabs, dirty state, agent changes, generated files, and the relationship to source control. - [Browsing project files](https://docs.foxora.ai/files-editor/browsing-project-files) ([md](https://docs.foxora.ai/files-editor/browsing-project-files.md)): Expand folders, search for a file, open it in a tab, confirm its path and language, and use symbols or content search to navigate. - [Creating and editing files](https://docs.foxora.ai/files-editor/creating-and-editing-files) ([md](https://docs.foxora.ai/files-editor/creating-and-editing-files.md)): Create a file in the intended folder, enter or request the content, save it, and run the project-specific verification command. - [Reviewing changes](https://docs.foxora.ai/files-editor/reviewing-changes) ([md](https://docs.foxora.ai/files-editor/reviewing-changes.md)): Open changed-file indicators or source control, compare additions and removals, check unexpected files, and request corrections before commit. - [Working with generated files](https://docs.foxora.ai/files-editor/working-with-generated-files) ([md](https://docs.foxora.ai/files-editor/working-with-generated-files.md)): Open the generated output, confirm format and destination, decide whether it belongs in source control, and regenerate rather than hand-edit when appropriate. - [Opening files in external editors](https://docs.foxora.ai/files-editor/opening-files-in-external-editors) ([md](https://docs.foxora.ai/files-editor/opening-files-in-external-editors.md)): Use Open externally or reveal the path, edit with the external application, save, then return to Foxora and confirm the file refreshes. ### Source Control - [Overview](https://docs.foxora.ai/source-control/overview) ([md](https://docs.foxora.ai/source-control/overview.md)): Learn the Git panel workflow from status and diff review through staging, committing, branching, and safe recovery. - [Reviewing Git changes and diffs](https://docs.foxora.ai/source-control/reviewing-git-changes-and-diffs) ([md](https://docs.foxora.ai/source-control/reviewing-git-changes-and-diffs.md)): Open the source-control panel, inspect each changed and untracked file, compare line-level edits, and identify the task responsible. - [Staging and committing changes](https://docs.foxora.ai/source-control/staging-and-committing-changes) ([md](https://docs.foxora.ai/source-control/staging-and-committing-changes.md)): Stage only related files or hunks, write an outcome-focused commit message, run verification, and inspect the created commit. - [Branches and worktrees](https://docs.foxora.ai/source-control/branches-and-worktrees) ([md](https://docs.foxora.ai/source-control/branches-and-worktrees.md)): Create or select a branch, use a separate worktree for parallel isolated work, confirm its path, and merge only after validation. - [Resolving conflicts](https://docs.foxora.ai/source-control/resolving-conflicts) ([md](https://docs.foxora.ai/source-control/resolving-conflicts.md)): List conflicted files, understand both sides, edit the resolved result, remove conflict markers, test, stage, and continue the merge or rebase. - [Git safety and recovery](https://docs.foxora.ai/source-control/git-safety-and-recovery) ([md](https://docs.foxora.ai/source-control/git-safety-and-recovery.md)): Inspect reflog, status, branches, and uncommitted work before recovery; prefer a backup branch or stash over destructive reset. ### Browser - [Overview](https://docs.foxora.ai/browser/overview) ([md](https://docs.foxora.ai/browser/overview.md)): Understand managed and existing-browser modes, Stage previews, takeover, authentication boundaries, and consequential web actions. - [Browser setup](https://docs.foxora.ai/browser/browser-setup) ([md](https://docs.foxora.ai/browser/browser-setup.md)): Open Browser settings, select a supported mode, install or authorize the required bridge when prompted, and test with a harmless page. - [Browser operating modes](https://docs.foxora.ai/browser/browser-operating-modes) ([md](https://docs.foxora.ai/browser/browser-operating-modes.md)): Choose isolated managed browsing for clean state or an existing browser context for signed-in work, then verify which profile is active. - [Running browser tasks](https://docs.foxora.ai/browser/running-browser-tasks) ([md](https://docs.foxora.ai/browser/running-browser-tasks.md)): Provide the target site and outcome, let Foxora navigate and inspect, follow actions on the Stage, and verify the final page state. - [Taking over an authenticated session](https://docs.foxora.ai/browser/taking-over-an-authenticated-session) ([md](https://docs.foxora.ai/browser/taking-over-an-authenticated-session.md)): Pause agent control, take over the browser, complete login or sensitive input yourself, then hand control back only after checking the active account. - [Screenshots and visual interaction](https://docs.foxora.ai/browser/screenshots-and-visual-interaction) ([md](https://docs.foxora.ai/browser/screenshots-and-visual-interaction.md)): Capture the relevant viewport, point to or describe the target element, verify Foxora interpreted it correctly, and repeat after layout changes. - [Browser permissions and safety](https://docs.foxora.ai/browser/browser-permissions-and-safety) ([md](https://docs.foxora.ai/browser/browser-permissions-and-safety.md)): Review domain, account, scope, and proposed action before approval; keep purchases, publishing, messaging, and deletion manually gated. ### Computer Use - [Overview](https://docs.foxora.ai/computer-use/overview) ([md](https://docs.foxora.ai/computer-use/overview.md)): Understand observation, pointer and keyboard control, OS permission prompts, takeover, and the limits of desktop automation. - [Controlling desktop applications](https://docs.foxora.ai/computer-use/controlling-desktop-applications) ([md](https://docs.foxora.ai/computer-use/controlling-desktop-applications.md)): Open the target application, arrange the relevant window, state the exact result, monitor each transition, and verify the application’s saved state. - [Keyboard and pointer interaction](https://docs.foxora.ai/computer-use/keyboard-and-pointer-interaction) ([md](https://docs.foxora.ai/computer-use/keyboard-and-pointer-interaction.md)): Provide a stable visual target, let Foxora click, type, scroll, or send keys, and stop immediately if focus moves to the wrong control. - [Permission requests](https://docs.foxora.ai/computer-use/permission-requests) ([md](https://docs.foxora.ai/computer-use/permission-requests.md)): Read the genuine operating-system permission prompt, confirm the requested capability and Foxora identity, grant the minimum access, and retest. - [Taking over from Foxora](https://docs.foxora.ai/computer-use/taking-over-from-foxora) ([md](https://docs.foxora.ai/computer-use/taking-over-from-foxora.md)): Interrupt the task, take control at login or sensitive steps, complete the action, place the app in a clear state, and explicitly return control. - [Computer-control safety](https://docs.foxora.ai/computer-use/computer-control-safety) ([md](https://docs.foxora.ai/computer-use/computer-control-safety.md)): Close unrelated sensitive windows, use a test account where possible, keep approvals enabled, monitor the screen, and verify every external side effect. ### Agents - [Overview](https://docs.foxora.ai/agents/overview) ([md](https://docs.foxora.ai/agents/overview.md)): Build reliable specialists by separating an agent’s role, instructions, model, knowledge, skills, and tool permissions. - [Creating an agent with AI](https://docs.foxora.ai/agents/creating-an-agent-with-ai) ([md](https://docs.foxora.ai/agents/creating-an-agent-with-ai.md)): Describe the specialist, its inputs, expected outputs, and boundaries; generate the draft, inspect every field, and save only after correcting assumptions. - [Creating an agent manually](https://docs.foxora.ai/agents/creating-an-agent-manually) ([md](https://docs.foxora.ai/agents/creating-an-agent-manually.md)): Create a blank agent, name its single responsibility, write instructions, select a model, add capabilities, and save a version you can test. - [Agent instructions and configuration](https://docs.foxora.ai/agents/agent-instructions-and-configuration) ([md](https://docs.foxora.ai/agents/agent-instructions-and-configuration.md)): Write the role, procedure, constraints, output format, and escalation rules; keep durable behavior in instructions and task-specific details in the task prompt. - [Specialist roles and delegation](https://docs.foxora.ai/agents/specialist-roles-and-delegation) ([md](https://docs.foxora.ai/agents/specialist-roles-and-delegation.md)): Give each specialist a non-overlapping responsibility, define when it should receive work, and make the expected handoff explicit for crew coordination. - [Testing an agent](https://docs.foxora.ai/agents/testing-an-agent) ([md](https://docs.foxora.ai/agents/testing-an-agent.md)): Prepare a normal case, an ambiguous case, and a permission-sensitive case; run each in a clean task and compare the result with explicit acceptance criteria. - [Editing and managing agents](https://docs.foxora.ai/agents/editing-and-managing-agents) ([md](https://docs.foxora.ai/agents/editing-and-managing-agents.md)): Duplicate before major experiments, edit one behavior at a time, retest dependent crews or bots, and disable or remove definitions that should no longer be selected. - [Agent models and tiers](https://docs.foxora.ai/agents/agent-models-and-tiers) ([md](https://docs.foxora.ai/agents/agent-models-and-tiers.md)): Choose a managed Foxora processing tier or assign a BYOK provider and model to this agent; test quality, latency, and credit or provider usage before wider use. ### Crews - [Overview](https://docs.foxora.ai/crews/overview) ([md](https://docs.foxora.ai/crews/overview.md)): Understand how a lead, specialists, delegation, processing tier, and final synthesis work together in a crew. - [How crews coordinate work](https://docs.foxora.ai/crews/how-crews-coordinate-work) ([md](https://docs.foxora.ai/crews/how-crews-coordinate-work.md)): Trace how the lead interprets a request, assigns bounded subtasks, receives specialist results, resolves conflicts, and produces the final response. - [Creating a crew with AI](https://docs.foxora.ai/crews/creating-a-crew-with-ai) ([md](https://docs.foxora.ai/crews/creating-a-crew-with-ai.md)): Describe the recurring outcome and required expertise, generate a proposed team, inspect every role and permission, then test the draft before regular use. - [Creating a crew manually](https://docs.foxora.ai/crews/creating-a-crew-manually) ([md](https://docs.foxora.ai/crews/creating-a-crew-manually.md)): Create a crew, select the lead, add only necessary specialists, define coordination instructions, choose a tier, and save the initial configuration. - [Adding and configuring agents](https://docs.foxora.ai/crews/adding-and-configuring-agents) ([md](https://docs.foxora.ai/crews/adding-and-configuring-agents.md)): Add existing agents or create specialists, remove overlapping roles, order or describe handoffs, and confirm each member has only the capabilities it needs. - [Choosing a crew for a task](https://docs.foxora.ai/crews/choosing-a-crew-in-a-session) ([md](https://docs.foxora.ai/crews/choosing-a-crew-in-a-session.md)): Open the composer crew picker, select the crew that matches the task, confirm its tier and lead, then send an objective with a measurable definition of done. - [Testing and managing crews](https://docs.foxora.ai/crews/testing-and-managing-crews) ([md](https://docs.foxora.ai/crews/testing-and-managing-crews.md)): Use a representative multi-part task, inspect delegation and synthesis, adjust one role or rule at a time, and retest before duplicating, disabling, or deleting the crew. ### Bots - [Overview](https://docs.foxora.ai/bots/overview) ([md](https://docs.foxora.ai/bots/overview.md)): Configure a reusable bot, connect it to supported surfaces, test its behavior, and operate it with clear permissions and escalation rules. - [How bots differ from agents](https://docs.foxora.ai/bots/how-bots-differ-from-agents) ([md](https://docs.foxora.ai/bots/how-bots-differ-from-agents.md)): Compare private agent tasks with published bot interactions, then choose the surface whose audience, lifecycle, and security model fit the use case. - [Creating a bot](https://docs.foxora.ai/bots/creating-a-bot) ([md](https://docs.foxora.ai/bots/creating-a-bot.md)): Create the bot, assign its agent or crew, choose the supported surface, set its name and audience, and save an unpublished draft for testing. - [Configuring bot behavior](https://docs.foxora.ai/bots/configuring-bot-behavior) ([md](https://docs.foxora.ai/bots/configuring-bot-behavior.md)): Define supported requests, response style, unavailable actions, escalation rules, and the exact information the bot may expose. - [Connecting tools and channels](https://docs.foxora.ai/bots/connecting-tools-and-channels) ([md](https://docs.foxora.ai/bots/connecting-tools-and-channels.md)): Add only the plugin or native tools the bot needs, connect a channel, map the destination, and confirm the bot identity and permissions. - [Testing a bot](https://docs.foxora.ai/bots/testing-a-bot) ([md](https://docs.foxora.ai/bots/testing-a-bot.md)): Test normal, unsupported, ambiguous, and permission-sensitive messages in a safe destination; verify replies, tool calls, routing, and failure handling. - [Managing and disabling bots](https://docs.foxora.ai/bots/managing-and-disabling-bots) ([md](https://docs.foxora.ai/bots/managing-and-disabling-bots.md)): Inspect active connections and recent behavior, update one configuration at a time, disable before maintenance, and verify traffic no longer routes to the bot. ### Skills - [Overview](https://docs.foxora.ai/skills/overview) ([md](https://docs.foxora.ai/skills/overview.md)): Understand how skills add repeatable procedures and supporting resources to agents without changing the underlying agent identity. - [Built-in skills](https://docs.foxora.ai/skills/built-in-skills) ([md](https://docs.foxora.ai/skills/built-in-skills.md)): Browse the built-in catalog, open the skill details, compare the supported use case and requirements, attach it to a test agent, and run its example workflow. - [Installing a skill](https://docs.foxora.ai/skills/installing-a-skill) ([md](https://docs.foxora.ai/skills/installing-a-skill.md)): Select a trusted source, review instructions and bundled files, inspect required tools and permissions, install it, and verify the installed version. - [Creating a custom skill](https://docs.foxora.ai/skills/creating-a-custom-skill) ([md](https://docs.foxora.ai/skills/creating-a-custom-skill.md)): Define a narrow trigger and outcome, write an explicit procedure, add only necessary resources or scripts, validate references, and test with a dedicated agent. - [Skill instructions and resources](https://docs.foxora.ai/skills/skill-instructions-and-resources) ([md](https://docs.foxora.ai/skills/skill-instructions-and-resources.md)): Separate required procedure from background reference material, keep paths and commands portable, document inputs and outputs, and verify every linked resource exists. - [Testing a skill](https://docs.foxora.ai/skills/testing-a-skill) ([md](https://docs.foxora.ai/skills/testing-a-skill.md)): Run a standard case, an edge case, and a failure case; confirm the skill activates at the right time and does not overreach beyond its stated workflow. - [Managing and removing skills](https://docs.foxora.ai/skills/managing-and-removing-skills) ([md](https://docs.foxora.ai/skills/managing-and-removing-skills.md)): Review attached agents before updating, test a new version in isolation, detach an obsolete skill, and remove it only after dependent configurations are migrated. ### Tools - [Overview](https://docs.foxora.ai/tools/overview) ([md](https://docs.foxora.ai/tools/overview.md)): Understand tool discovery, typed inputs and results, approval boundaries, failure reporting, and the difference between built-in, plugin, and MCP tools. - [Built-in tool catalog](https://docs.foxora.ai/tools/built-in-tool-catalog) ([md](https://docs.foxora.ai/tools/built-in-tool-catalog.md)): Browse tools by capability, open the input and permission details, identify read-only versus mutating actions, and attach only the required tools to an agent. - [How agents select tools](https://docs.foxora.ai/tools/how-agents-select-tools) ([md](https://docs.foxora.ai/tools/how-agents-select-tools.md)): Give the agent a clear outcome, confirm relevant tools are enabled, inspect the chosen call and arguments, and refine instructions if it repeatedly chooses the wrong capability. - [Tool inputs and results](https://docs.foxora.ai/tools/tool-inputs-and-results) ([md](https://docs.foxora.ai/tools/tool-inputs-and-results.md)): Review each required input and target, run the call, expand the result shape, and use status, identifiers, paths, or URLs to verify the operation. - [Tool permissions and approvals](https://docs.foxora.ai/tools/tool-permissions-and-approvals) ([md](https://docs.foxora.ai/tools/tool-permissions-and-approvals.md)): Match the tool to the task autonomy mode, read the exact target and proposed action, approve only understood requests, and revoke unused access afterward. - [Handling tool failures](https://docs.foxora.ai/tools/handling-tool-failures) ([md](https://docs.foxora.ai/tools/handling-tool-failures.md)): Capture the tool name, inputs, error code, and timestamp; check permissions and connectivity, correct one cause, then repeat the smallest failing call. - [Creating or connecting custom tools](https://docs.foxora.ai/tools/creating-or-connecting-custom-tools) ([md](https://docs.foxora.ai/tools/creating-or-connecting-custom-tools.md)): Choose MCP for a custom server or Composio for a supported integration, define a narrow schema and permissions, connect it, and test with a non-destructive operation. ### Memory Den - [Overview](https://docs.foxora.ai/memory-den/overview) ([md](https://docs.foxora.ai/memory-den/overview.md)): Understand local memory capture, recall, provenance, review, correction, deletion, and the boundary between memory and task history. - [How automatic memory works](https://docs.foxora.ai/memory-den/how-automatic-memory-works) ([md](https://docs.foxora.ai/memory-den/how-automatic-memory-works.md)): Complete a focused interaction, inspect what Foxora selected as durable, distinguish inferred context from explicit facts, and correct anything that should not persist. - [Memory recall in tasks](https://docs.foxora.ai/memory-den/memory-recall-in-sessions) ([md](https://docs.foxora.ai/memory-den/memory-recall-in-sessions.md)): Open a later task on the same device, ask a relevant question, inspect the recalled memory card or activity, and provide updated information when the fact has changed. - [Exploring saved memories](https://docs.foxora.ai/memory-den/exploring-saved-memories) ([md](https://docs.foxora.ai/memory-den/exploring-saved-memories.md)): Open Memory Den, search or filter entries, select a memory, read its content and metadata, and follow the source reference before relying on it. - [Memory sources and provenance](https://docs.foxora.ai/memory-den/memory-sources-and-provenance) ([md](https://docs.foxora.ai/memory-den/memory-sources-and-provenance.md)): Open an entry, inspect its source task and creation context, compare it with the original transcript, and mark unsupported or outdated conclusions for correction. - [Editing and deleting memories](https://docs.foxora.ai/memory-den/editing-and-deleting-memories) ([md](https://docs.foxora.ai/memory-den/editing-and-deleting-memories.md)): Select the exact local memory, edit the smallest inaccurate portion or delete it, confirm the action, then test recall in a new local task. - [Memory privacy and storage](https://docs.foxora.ai/memory-den/memory-privacy-and-storage) ([md](https://docs.foxora.ai/memory-den/memory-privacy-and-storage.md)): Review what is stored locally, restrict device access and backups, export only when necessary, and clear local memory separately from account or subscription changes. ### Scheduled Tasks - [Overview](https://docs.foxora.ai/scheduled-tasks/overview) ([md](https://docs.foxora.ai/scheduled-tasks/overview.md)): Create dependable scheduled automation by defining the task, target, timezone, recurrence, permissions, delivery, and run monitoring. - [Creating a scheduled task](https://docs.foxora.ai/scheduled-tasks/creating-a-scheduled-task) ([md](https://docs.foxora.ai/scheduled-tasks/creating-a-scheduled-task.md)): Create the task, name the outcome, write the input, select an agent or crew, choose the first run time and destination, then save it disabled until tested. - [Schedules and recurrence](https://docs.foxora.ai/scheduled-tasks/schedules-and-recurrence) ([md](https://docs.foxora.ai/scheduled-tasks/schedules-and-recurrence.md)): Choose one-time or recurring execution, set the timezone, configure frequency and boundaries, preview upcoming times, and check daylight-saving behavior where relevant. - [Selecting an agent or crew](https://docs.foxora.ai/scheduled-tasks/selecting-an-agent-or-crew) ([md](https://docs.foxora.ai/scheduled-tasks/selecting-an-agent-or-crew.md)): Choose a tested configuration whose tools and model fit the task, confirm external connections, and avoid changing that configuration without retesting the schedule. - [Editing, pausing, and deleting tasks](https://docs.foxora.ai/scheduled-tasks/editing-pausing-and-deleting-tasks) ([md](https://docs.foxora.ai/scheduled-tasks/editing-pausing-and-deleting-tasks.md)): Pause before major edits, change one schedule or input field, run a manual test, resume after verification, and delete only after preserving required run outputs. - [Scheduled-task permissions](https://docs.foxora.ai/scheduled-tasks/scheduled-task-permissions) ([md](https://docs.foxora.ai/scheduled-tasks/scheduled-task-permissions.md)): Review every tool and external destination, keep high-impact actions gated or narrowly scoped, verify connected-account access, and use the least powerful agent configuration. - [Troubleshooting scheduled tasks](https://docs.foxora.ai/scheduled-tasks/troubleshooting-scheduled-tasks) ([md](https://docs.foxora.ai/scheduled-tasks/troubleshooting-scheduled-tasks.md)): Inspect next-run time, timezone, enabled state, selected agent or crew, connection status, and the latest run error; fix one cause and use Run now to retest. ### Workflows - [Overview](https://docs.foxora.ai/workflows/overview) ([md](https://docs.foxora.ai/workflows/overview.md)): Design, test, publish, and monitor workflows made from triggers, steps, conditions, delays, approvals, and connected actions. - [Creating a workflow with AI](https://docs.foxora.ai/workflows/creating-a-workflow-with-ai) ([md](https://docs.foxora.ai/workflows/creating-a-workflow-with-ai.md)): Describe the trigger, required inputs, ordered result, error behavior, and approval points; generate the draft, then inspect every node and mapping before testing. - [Creating a workflow manually](https://docs.foxora.ai/workflows/creating-a-workflow-manually) ([md](https://docs.foxora.ai/workflows/creating-a-workflow-manually.md)): Create a blank workflow, add and configure the trigger, build one step at a time, map typed inputs, define outputs, and save an unpublished draft. - [Triggers, steps, and actions](https://docs.foxora.ai/workflows/triggers-steps-and-actions) ([md](https://docs.foxora.ai/workflows/triggers-steps-and-actions.md)): Choose the initiating event, inspect its payload, connect each step’s required input to a validated value, and make the final side effect explicit. - [Delays and conditional behavior](https://docs.foxora.ai/workflows/delays-and-conditional-behavior) ([md](https://docs.foxora.ai/workflows/delays-and-conditional-behavior.md)): Add a condition with complete true and false paths, configure delays with a timezone or duration, and define what happens when data is missing or late. - [Approvals inside workflows](https://docs.foxora.ai/workflows/approvals-inside-workflows) ([md](https://docs.foxora.ai/workflows/approvals-inside-workflows.md)): Insert approval immediately before the consequential step, show the exact proposed action and target, define expiry or rejection behavior, and test both decisions. - [Testing a workflow](https://docs.foxora.ai/workflows/testing-a-workflow) ([md](https://docs.foxora.ai/workflows/testing-a-workflow.md)): Use representative test data, run each branch including failures and retries, inspect step-level logs, and verify no real external side effect occurs unexpectedly. - [Publishing and managing workflows](https://docs.foxora.ai/workflows/publishing-and-managing-workflows) ([md](https://docs.foxora.ai/workflows/publishing-and-managing-workflows.md)): Name and version the tested draft, publish it, monitor initial runs, pause before structural edits, and retire versions only after dependent triggers are migrated. ### Runs - [Overview](https://docs.foxora.ai/runs/overview) ([md](https://docs.foxora.ai/runs/overview.md)): Use run records to start work, monitor progress, inspect outputs and usage, diagnose failures, retry safely, or cancel execution. - [Starting a run](https://docs.foxora.ai/runs/starting-a-run) ([md](https://docs.foxora.ai/runs/starting-a-run.md)): Choose the tested agent, crew, workflow, or task, enter validated input, confirm model and destination, start once, and open the created run record. - [Monitoring live progress](https://docs.foxora.ai/runs/monitoring-live-progress) ([md](https://docs.foxora.ai/runs/monitoring-live-progress.md)): Follow the current step and elapsed time, expand agent and tool activity, answer approval requests, and interrupt only after checking whether work is still advancing. - [Run history and outputs](https://docs.foxora.ai/runs/run-history-and-outputs) ([md](https://docs.foxora.ai/runs/run-history-and-outputs.md)): Filter runs by source, status, and date, open the required record, inspect its input and output, then follow identifiers or links to the persistent destination. - [Reviewing failed runs](https://docs.foxora.ai/runs/reviewing-failed-runs) ([md](https://docs.foxora.ai/runs/reviewing-failed-runs.md)): Open the first failed step, capture its error and preceding input, distinguish configuration from transient failure, and preserve logs before changing anything. - [Retrying or cancelling a run](https://docs.foxora.ai/runs/retrying-or-cancelling-a-run) ([md](https://docs.foxora.ai/runs/retrying-or-cancelling-a-run.md)): Check whether completed steps are safe to repeat, correct the input or configuration, retry once from the supported boundary, or cancel and confirm execution stops. - [Run logs and diagnostics](https://docs.foxora.ai/runs/run-logs-and-diagnostics) ([md](https://docs.foxora.ai/runs/run-logs-and-diagnostics.md)): Open the run timeline and logs, correlate timestamps across agents and tools, copy a redacted diagnostic bundle, and include the run identifier in support requests. ### Plugins - [Overview](https://docs.foxora.ai/plugins/overview) ([md](https://docs.foxora.ai/plugins/overview.md)): Connect supported applications through Composio, expose selected actions as tools, and manage account access without putting credentials in prompts. - [Installing and connecting a plugin](https://docs.foxora.ai/plugins/installing-and-connecting-a-plugin) ([md](https://docs.foxora.ai/plugins/installing-and-connecting-a-plugin.md)): Open the catalog, choose the application, start the Composio authorization flow, select the correct account, approve required scopes, and confirm connection status. - [Supported plugin catalog](https://docs.foxora.ai/plugins/supported-plugin-catalog) ([md](https://docs.foxora.ai/plugins/supported-plugin-catalog.md)): Search by application or capability, inspect available actions and authentication requirements, and choose the narrowest integration that provides the needed operation. - [Using plugin tools in tasks](https://docs.foxora.ai/plugins/using-plugin-tools-in-sessions) ([md](https://docs.foxora.ai/plugins/using-plugin-tools-in-sessions.md)): Attach the plugin tool to an agent, select that agent in a task, request a read-only action first, inspect inputs and results, then approve any intended write action. - [Managing connected accounts](https://docs.foxora.ai/plugins/managing-connected-accounts) ([md](https://docs.foxora.ai/plugins/managing-connected-accounts.md)): Open the plugin’s connections, identify each provider account, test its status, update which agents or automations may use it, and remove stale authorization. - [Reconnecting or removing a plugin](https://docs.foxora.ai/plugins/reconnecting-or-removing-a-plugin) ([md](https://docs.foxora.ai/plugins/reconnecting-or-removing-a-plugin.md)): Preserve affected workflow details, reconnect through Composio when authorization expires, retest a harmless action, or disconnect and confirm dependent tools stop working. - [Plugin permissions and security](https://docs.foxora.ai/plugins/plugin-permissions-and-security) ([md](https://docs.foxora.ai/plugins/plugin-permissions-and-security.md)): Review provider scopes, Foxora assignment, agent tools, autonomy, and external target together; minimize each layer and audit consequential activity. ### Channels - [Overview](https://docs.foxora.ai/channels/overview) ([md](https://docs.foxora.ai/channels/overview.md)): Connect a messaging surface, define routing and permissions, test inbound and outbound behavior, and operate the channel safely. - [Connecting a channel](https://docs.foxora.ai/channels/connecting-a-channel) ([md](https://docs.foxora.ai/channels/connecting-a-channel.md)): Choose the provider, authorize the correct account, select the workspace and room, confirm the Foxora identity, and save the connection without broad routing. - [Routing messages to agents or bots](https://docs.foxora.ai/channels/routing-messages-to-agents-or-bots) ([md](https://docs.foxora.ai/channels/routing-messages-to-agents-or-bots.md)): Select the source room or event, choose the target bot or agent, define mention or thread behavior, set fallbacks, and test the mapping with a unique message. - [Channel permissions](https://docs.foxora.ai/channels/channel-permissions) ([md](https://docs.foxora.ai/channels/channel-permissions.md)): Restrict allowed rooms and senders, limit the target’s tools, keep high-impact actions approved, and test that unauthorized messages do not trigger work. - [Managing connected channels](https://docs.foxora.ai/channels/managing-connected-channels) ([md](https://docs.foxora.ai/channels/managing-connected-channels.md)): Review connection health, destination mappings, recent traffic, and dependent bots or workflows; pause routing before changing credentials or account ownership. - [Channel troubleshooting](https://docs.foxora.ai/channels/channel-troubleshooting) ([md](https://docs.foxora.ai/channels/channel-troubleshooting.md)): Check provider authorization, selected workspace and room, event subscriptions, routing rules, bot access, and latest delivery error; then resend one test message. ### MCP - [Overview](https://docs.foxora.ai/mcp/overview) ([md](https://docs.foxora.ai/mcp/overview.md)): Understand MCP clients, servers, transports, advertised capabilities, configuration, approval boundaries, and the difference from Composio plugins. - [Adding an MCP server](https://docs.foxora.ai/mcp/adding-an-mcp-server) ([md](https://docs.foxora.ai/mcp/adding-an-mcp-server.md)): Create a server entry, choose local or remote transport, enter the command or endpoint, add required dedicated credentials, connect, and inspect discovered capabilities. - [Configuring MCP servers](https://docs.foxora.ai/mcp/configuring-mcp-servers) ([md](https://docs.foxora.ai/mcp/configuring-mcp-servers.md)): Set transport, arguments, environment, authentication, timeout, and allowed capabilities explicitly; save, reconnect, and confirm the effective configuration. - [Using MCP tools in tasks](https://docs.foxora.ai/mcp/using-mcp-tools-in-sessions) ([md](https://docs.foxora.ai/mcp/using-mcp-tools-in-sessions.md)): Enable selected MCP tools for an agent, open a test task, request a read-only operation, inspect the exact server and arguments, and verify the returned data. - [Using Foxora as an MCP server](https://docs.foxora.ai/mcp/using-foxora-as-an-mcp-server) ([md](https://docs.foxora.ai/mcp/using-foxora-as-an-mcp-server.md)): Enable the Foxora MCP server surface, choose exposed capabilities and authentication, add it to the client, then test discovery and one bounded call. - [Managing and removing servers](https://docs.foxora.ai/mcp/managing-and-removing-servers) ([md](https://docs.foxora.ai/mcp/managing-and-removing-servers.md)): Review dependent agents and workflows, disable the server, confirm tools disappear from new tasks, then remove its configuration and revoke credentials. - [MCP security and troubleshooting](https://docs.foxora.ai/mcp/mcp-security-and-troubleshooting) ([md](https://docs.foxora.ai/mcp/mcp-security-and-troubleshooting.md)): Check process or endpoint reachability, transport logs, authentication, schema compatibility, and capability discovery; keep privileges minimal while isolating the failing layer. ### Models - [Overview](https://docs.foxora.ai/models-providers/overview) ([md](https://docs.foxora.ai/models-providers/overview.md)): Choose between Foxora-managed models and agent-level BYOK, then select a model or processing tier that fits the task and budget. - [Connecting an AI provider](https://docs.foxora.ai/models-providers/connecting-an-ai-provider) ([md](https://docs.foxora.ai/models-providers/connecting-an-ai-provider.md)): Open provider settings, choose a supported provider, enter the key in the protected field, validate the connection, and assign it only to the intended agent. - [Bring Your Own Key](https://docs.foxora.ai/models-providers/bring-your-own-key) ([md](https://docs.foxora.ai/models-providers/bring-your-own-key.md)): Create or edit an agent, switch its model source to BYOK, select the provider and model, add or choose the key, save, and verify provider-side usage. - [Selecting models](https://docs.foxora.ai/models-providers/selecting-models) ([md](https://docs.foxora.ai/models-providers/selecting-models.md)): Filter compatible models, compare capability, latency, context, and provider pricing, select one for the agent, and test with a representative request. - [Processing tiers](https://docs.foxora.ai/models-providers/processing-tiers) ([md](https://docs.foxora.ai/models-providers/processing-tiers.md)): Use Fast for routine work, Premium for stronger general reasoning, or Max for the hardest tasks; confirm availability under the active subscription before running. - [Default and per-task models](https://docs.foxora.ai/models-providers/default-and-per-session-models) ([md](https://docs.foxora.ai/models-providers/default-and-per-session-models.md)): Set a stable default through the agent configuration, choose the appropriate agent or crew in each task, and confirm the effective model before sending expensive work. - [Availability, cost, and limits](https://docs.foxora.ai/models-providers/availability-cost-and-limits) ([md](https://docs.foxora.ai/models-providers/availability-cost-and-limits.md)): Check plan credits for managed access or provider limits for BYOK, inspect current usage and rate-limit messages, and reduce scope or change models when needed. ### Settings - [Overview](https://docs.foxora.ai/settings/overview) ([md](https://docs.foxora.ai/settings/overview.md)): Navigate each settings category, distinguish global defaults from task or agent configuration, and verify changes in the affected surface. - [Appearance settings](https://docs.foxora.ai/settings/appearance-settings) ([md](https://docs.foxora.ai/settings/appearance-settings.md)): Choose theme, accent, density, text scale, and motion preferences; apply them and check conversation, editor, terminal, and Stage readability. - [Voice settings](https://docs.foxora.ai/settings/voice-settings) ([md](https://docs.foxora.ai/settings/voice-settings.md)): Select microphone and speaker devices, grant OS access, set voice behavior, run an input and output test, and disable listening when unused. - [Browser settings](https://docs.foxora.ai/settings/browser-settings) ([md](https://docs.foxora.ai/settings/browser-settings.md)): Choose managed or existing-browser mode, authorize the required bridge or permissions, test a harmless page, and confirm the active browser context. - [Plugin and channel settings](https://docs.foxora.ai/settings/plugin-and-channel-settings) ([md](https://docs.foxora.ai/settings/plugin-and-channel-settings.md)): Open the relevant connection, review provider account and scopes, test status, update assignments, and disconnect only after checking dependent bots or workflows. - [Brand settings](https://docs.foxora.ai/settings/brand-settings) ([md](https://docs.foxora.ai/settings/brand-settings.md)): Set approved name, logo, colors, and presentation defaults, preview them on the intended bot or shared surface, and verify accessibility and ownership rights. - [Permission settings](https://docs.foxora.ai/settings/permission-settings) ([md](https://docs.foxora.ai/settings/permission-settings.md)): Review filesystem, terminal, browser, computer-use, microphone, and notification access; grant the minimum needed and retest after revocation. - [Data and system settings](https://docs.foxora.ai/settings/data-and-system-settings) ([md](https://docs.foxora.ai/settings/data-and-system-settings.md)): Inspect local storage and runtime paths, export required data, adjust supported system options, and use reset or clear actions only after reviewing their exact scope. - [Keyboard settings](https://docs.foxora.ai/settings/keyboard-settings) ([md](https://docs.foxora.ai/settings/keyboard-settings.md)): Open shortcut mappings, identify conflicts, change the binding, save, and test it in the relevant workspace context. - [About and update settings](https://docs.foxora.ai/settings/about-and-update-settings) ([md](https://docs.foxora.ai/settings/about-and-update-settings.md)): Check Desktop and runtime versions, read release information, save active work, install the signed update, restart, and verify a small task. ### Account & Authentication - [Overview](https://docs.foxora.ai/account-authentication/overview) ([md](https://docs.foxora.ai/account-authentication/overview.md)): Create and protect an account, sign clients in through the browser, manage profile and devices, recover access, and understand local-data boundaries. - [Creating an account](https://docs.foxora.ai/account-authentication/creating-an-account) ([md](https://docs.foxora.ai/account-authentication/creating-an-account.md)): Open the official sign-up page, enter the requested account details, verify the email or identity-provider flow, choose a plan when prompted, and complete the profile. - [Signing in](https://docs.foxora.ai/account-authentication/signing-in) ([md](https://docs.foxora.ai/account-authentication/signing-in.md)): Start sign-in from Foxora, inspect the browser domain and requested account, authenticate, approve the handoff, and return to confirm the signed-in identity. - [Resetting your password](https://docs.foxora.ai/account-authentication/resetting-your-password) ([md](https://docs.foxora.ai/account-authentication/resetting-your-password.md)): Open the official reset flow, enter the account email, use the newest reset message, choose a unique password, then sign in and review authorized devices. - [Profile settings](https://docs.foxora.ai/account-authentication/profile-settings) ([md](https://docs.foxora.ai/account-authentication/profile-settings.md)): Open Account settings, edit supported identity or profile fields, save once, and confirm the updated information in another Foxora surface. - [Authorized devices](https://docs.foxora.ai/account-authentication/authorized-devices) ([md](https://docs.foxora.ai/account-authentication/authorized-devices.md)): Review device name, platform, location or activity metadata, identify the current installation, and revoke any device you no longer recognize or control. - [Signing out of other devices](https://docs.foxora.ai/account-authentication/signing-out-of-other-devices) ([md](https://docs.foxora.ai/account-authentication/signing-out-of-other-devices.md)): Select the exact remote device or use the all-other-devices action, confirm revocation, then change credentials if access may have been compromised. - [Deleting your account](https://docs.foxora.ai/account-authentication/deleting-your-account) ([md](https://docs.foxora.ai/account-authentication/deleting-your-account.md)): Export required account and local data, cancel dependent subscriptions or connections, review the permanent deletion scope, confirm once, and separately clear local data on each device if desired. ### Plans, Credits & Usage - [Overview](https://docs.foxora.ai/plans-credits-usage/overview) ([md](https://docs.foxora.ai/plans-credits-usage/overview.md)): Choose among Free, Starter, Pro, and Max, understand monthly Foxora credits, distinguish BYOK billing, and monitor usage before limits interrupt work. - [Plans and pricing](https://docs.foxora.ai/plans-credits-usage/plans-and-pricing) ([md](https://docs.foxora.ai/plans-credits-usage/plans-and-pricing.md)): Compare Free, Starter, Pro, and Max by included credits and required capabilities, select monthly or available longer-term billing, and confirm the checkout summary before purchase. - [Understanding credits](https://docs.foxora.ai/plans-credits-usage/understanding-credits) ([md](https://docs.foxora.ai/plans-credits-usage/understanding-credits.md)): Identify whether an agent uses managed access or BYOK, inspect the managed run’s credit usage, compare task complexity and tier, and use the usage window to plan remaining work. - [Viewing usage](https://docs.foxora.ai/plans-credits-usage/viewing-usage) ([md](https://docs.foxora.ai/plans-credits-usage/viewing-usage.md)): Open Usage or run `foxora usage`, review weekly and monthly windows, filter or inspect recent activity where available, and investigate unexpected changes before more runs. - [Usage and rate limits](https://docs.foxora.ai/plans-credits-usage/usage-and-rate-limits) ([md](https://docs.foxora.ai/plans-credits-usage/usage-and-rate-limits.md)): Read whether the notice concerns credits, a time window, concurrency, or a BYOK provider limit; wait, reduce load, change configuration, or upgrade only after identifying the limit. - [Managing a subscription](https://docs.foxora.ai/plans-credits-usage/managing-a-subscription) ([md](https://docs.foxora.ai/plans-credits-usage/managing-a-subscription.md)): Open Billing, confirm the current plan and renewal date, select the intended plan or cycle, review the effective date and total, and save the confirmation. - [Updating billing information](https://docs.foxora.ai/plans-credits-usage/updating-billing-information) ([md](https://docs.foxora.ai/plans-credits-usage/updating-billing-information.md)): Open the secure billing portal, select the subscription, update the supported payment and billing fields, save, and confirm the next invoice uses the intended details. - [Cancelling a subscription](https://docs.foxora.ai/plans-credits-usage/cancelling-a-subscription) ([md](https://docs.foxora.ai/plans-credits-usage/cancelling-a-subscription.md)): Review the access end date, unused credits, exports, active automations, and BYOK keys; confirm cancellation once and verify the account shows the expected future plan state. ### Security & Privacy - [Overview](https://docs.foxora.ai/security-privacy/overview) ([md](https://docs.foxora.ai/security-privacy/overview.md)): Apply layered security to accounts, projects, autonomy, tools, connections, local storage, secrets, exports, and deletion. - [Permission and autonomy security](https://docs.foxora.ai/security-privacy/permission-and-autonomy-security) ([md](https://docs.foxora.ai/security-privacy/permission-and-autonomy-security.md)): Classify task risk, choose Ask Permissions, Accept Edits, Auto, or Bypass Permissions, review tool targets, and lower autonomy after the bounded task. - [Local data storage](https://docs.foxora.ai/security-privacy/local-data-storage) ([md](https://docs.foxora.ai/security-privacy/local-data-storage.md)): Review the device locations and application controls for sessions, Memory Den, attachments, logs, and settings; secure the OS account, backups, and disk. - [Memory privacy](https://docs.foxora.ai/security-privacy/memory-privacy) ([md](https://docs.foxora.ai/security-privacy/memory-privacy.md)): Inspect saved local memories and provenance, remove sensitive or outdated entries, test recall, and remember that clearing a session does not necessarily clear its durable memories. - [Authentication and task security](https://docs.foxora.ai/security-privacy/authentication-and-session-security) ([md](https://docs.foxora.ai/security-privacy/authentication-and-session-security.md)): Use the official browser flow, verify account identity, review authorized devices, revoke unknown sessions, and reset credentials after suspicious activity. - [Managing secrets and API keys](https://docs.foxora.ai/security-privacy/managing-secrets-and-api-keys) ([md](https://docs.foxora.ai/security-privacy/managing-secrets-and-api-keys.md)): Add provider keys only to dedicated agent or connection fields, restrict the associated agent and tools, rotate exposed keys at the provider, and retest after replacement. - [Exporting or deleting data](https://docs.foxora.ai/security-privacy/exporting-or-deleting-data) ([md](https://docs.foxora.ai/security-privacy/exporting-or-deleting-data.md)): Choose account data, local sessions, local Memory Den, or application settings separately, export what must be retained, verify the archive, then confirm only the intended deletion. ### Foxora CLI - [Overview](https://docs.foxora.ai/cli/overview) ([md](https://docs.foxora.ai/cli/overview.md)): Use the Foxora CLI with the same local runtime as Desktop, either through its interactive terminal UI or a one-shot headless run. - [Installing the CLI](https://docs.foxora.ai/cli/installing-the-cli) ([md](https://docs.foxora.ai/cli/installing-the-cli.md)): Install Foxora CLI on Windows, macOS, or Linux, provision the runtime, sign in, and verify the installation. - [Authentication and setup](https://docs.foxora.ai/cli/authentication-and-setup) ([md](https://docs.foxora.ai/cli/authentication-and-setup.md)): Provision the local engine, Memory Den, and Bun runtime, complete browser sign-in, and confirm the active account. - [Interactive CLI usage](https://docs.foxora.ai/cli/interactive-cli-usage) ([md](https://docs.foxora.ai/cli/interactive-cli-usage.md)): Open the terminal UI, select local sessions and crews, send requests, review activity, and manage approvals from the keyboard. - [Headless runs](https://docs.foxora.ai/cli/headless-runs) ([md](https://docs.foxora.ai/cli/headless-runs.md)): Run one prompt with an optional fast, pro, or max crew, print the reply, and use the process exit code in scripts. - [Command reference](https://docs.foxora.ai/cli/command-reference) ([md](https://docs.foxora.ai/cli/command-reference.md)): Use the exact Foxora CLI v5.0.3 commands, options, environment variables, and supported examples. - [Configuration and updates](https://docs.foxora.ai/cli/configuration-and-updates) ([md](https://docs.foxora.ai/cli/configuration-and-updates.md)): Configure engine, gateway, and resource endpoints, update the CLI and runtime, and verify health afterward. - [CLI troubleshooting](https://docs.foxora.ai/cli/cli-troubleshooting) ([md](https://docs.foxora.ai/cli/cli-troubleshooting.md)): Diagnose command discovery, runtime, authentication, command syntax, and update problems with the built-in checks. ### API Reference - [Overview](https://docs.foxora.ai/api/overview) ([md](https://docs.foxora.ai/api/overview.md)): Make a first authenticated API request, verify the response and usage, and use the endpoint-specific pages for production handling. - [Authentication](https://docs.foxora.ai/api/authentication) ([md](https://docs.foxora.ai/api/authentication.md)): Use a signed-in Foxora account access token as a Bearer token over HTTPS, test `/v1/me`, and sign out or revoke the session after suspected exposure. - [Chat Completions API](https://docs.foxora.ai/api/chat-completions-api) ([md](https://docs.foxora.ai/api/chat-completions-api.md)): Fetch a valid model identifier, construct the messages payload, send `POST /v1/chat/completions`, parse the response and usage, and handle streaming only as documented. - [Account endpoint](https://docs.foxora.ai/api/account-endpoint) ([md](https://docs.foxora.ai/api/account-endpoint.md)): Send authenticated `GET /v1/me`, validate the status and account fields, and use the result to confirm the token belongs to the expected account. - [Usage endpoint](https://docs.foxora.ai/api/usage-endpoint) ([md](https://docs.foxora.ai/api/usage-endpoint.md)): Send authenticated `GET /v1/me/usage`, inspect weekly and monthly windows and plan context, and compare the response before and after a controlled request. - [Models endpoint](https://docs.foxora.ai/api/models-endpoint) ([md](https://docs.foxora.ai/api/models-endpoint.md)): Send `GET /v1/models`, select a currently returned identifier compatible with the desired request, and refresh discovery when availability changes. - [Errors and status codes](https://docs.foxora.ai/api/errors-and-status-codes) ([md](https://docs.foxora.ai/api/errors-and-status-codes.md)): Log the status, request identifier, safe response details, and retryability; correct invalid requests, reauthenticate on authorization errors, and back off on transient limits. - [Rate limits and versioning](https://docs.foxora.ai/api/rate-limits-and-versioning) ([md](https://docs.foxora.ai/api/rate-limits-and-versioning.md)): Read rate-limit headers and error bodies, use bounded exponential backoff with jitter for retryable responses, cap concurrency, and pin the documented API version behavior. ### Troubleshooting - [Overview](https://docs.foxora.ai/troubleshooting/overview) ([md](https://docs.foxora.ai/troubleshooting/overview.md)): Diagnose Foxora systematically by isolating the failing layer, preserving evidence, applying one reversible fix, and verifying with the same test. - [Installation and startup problems](https://docs.foxora.ai/troubleshooting/installation-and-startup-problems) ([md](https://docs.foxora.ai/troubleshooting/installation-and-startup-problems.md)): Confirm OS and architecture support, installer source and version, disk and security prompts, runtime status, then repair or reinstall without clearing local data first. - [Account and sign-in problems](https://docs.foxora.ai/troubleshooting/account-and-sign-in-problems) ([md](https://docs.foxora.ai/troubleshooting/account-and-sign-in-problems.md)): Check connectivity, browser domain, account identity, clock, authorized devices, and subscription state; repeat the browser handoff and capture the exact failure. - [Task and project problems](https://docs.foxora.ai/troubleshooting/session-and-project-problems) ([md](https://docs.foxora.ai/troubleshooting/session-and-project-problems.md)): Confirm the active local task and project path, folder availability, repository state, permissions, and free disk space; test read access before edits. - [Agent, crew, and tool problems](https://docs.foxora.ai/troubleshooting/agent-crew-and-tool-problems) ([md](https://docs.foxora.ai/troubleshooting/agent-crew-and-tool-problems.md)): Check the selected configuration, instructions, model access, enabled skills and tools, approval state, and first failing call; test one agent and one tool in isolation. - [Browser and computer-use problems](https://docs.foxora.ai/troubleshooting/browser-and-computer-use-problems) ([md](https://docs.foxora.ai/troubleshooting/browser-and-computer-use-problems.md)): Check the selected mode, bridge or OS permission, active profile and window, screen visibility, focus, and connection state; retest on a harmless target. - [Workflow and scheduled-task problems](https://docs.foxora.ai/troubleshooting/workflow-and-scheduled-task-problems) ([md](https://docs.foxora.ai/troubleshooting/workflow-and-scheduled-task-problems.md)): Check enabled state, trigger or next-run time, timezone, input mapping, selected agent, connections, approval wait, and first failed step; use a manual test run. - [Plugin, channel, and MCP problems](https://docs.foxora.ai/troubleshooting/plugin-channel-and-mcp-problems) ([md](https://docs.foxora.ai/troubleshooting/plugin-channel-and-mcp-problems.md)): Check provider authorization, Composio connection or MCP transport, scopes, destination mapping, capability discovery, and latest error; reconnect only the failing layer. - [Collecting diagnostics](https://docs.foxora.ai/troubleshooting/collecting-diagnostics) ([md](https://docs.foxora.ai/troubleshooting/collecting-diagnostics.md)): Record versions, platform, time, reproduction steps, run or task identifiers, exact error, redacted logs, and expected versus actual behavior without exposing secrets. - [Contacting support](https://docs.foxora.ai/troubleshooting/contacting-support) ([md](https://docs.foxora.ai/troubleshooting/contacting-support.md)): Search relevant documentation, prepare the redacted diagnostic bundle, describe impact and the smallest reproduction, include identifiers and time, then use the official support channel. ### FAQ - [Overview](https://docs.foxora.ai/faq/overview) ([md](https://docs.foxora.ai/faq/overview.md)): Find the correct source of truth for common questions and verify the answer against the current device, account, configuration, or external connection. - [General questions](https://docs.foxora.ai/faq/general-questions) ([md](https://docs.foxora.ai/faq/general-questions.md)): Identify the Foxora surface involved, open its overview and current settings, confirm the installed version, and use the relevant step-by-step guide for the task. - [Account and billing questions](https://docs.foxora.ai/faq/account-and-billing-questions) ([md](https://docs.foxora.ai/faq/account-and-billing-questions.md)): Open Account, Billing, and Usage, verify identity and plan, compare the recorded renewal or credit window, and use the secure billing portal for changes. - [Models and credits questions](https://docs.foxora.ai/faq/models-and-credits-questions) ([md](https://docs.foxora.ai/faq/models-and-credits-questions.md)): Check whether the agent uses Foxora-managed access or BYOK, identify the model or processing tier, inspect Usage, and compare provider billing separately for BYOK. - [Data and privacy questions](https://docs.foxora.ai/faq/data-and-privacy-questions) ([md](https://docs.foxora.ai/faq/data-and-privacy-questions.md)): Separate account data from local tasks and Memory Den, inspect device storage and connected-service permissions, and export or delete only the intended category. - [Agents and automation questions](https://docs.foxora.ai/faq/agents-and-automation-questions) ([md](https://docs.foxora.ai/faq/agents-and-automation-questions.md)): Choose agent, crew, bot, scheduled task, or workflow by the desired trigger and coordination pattern, then test the configuration with a bounded input. ### Release Notes - [Overview](https://docs.foxora.ai/release-notes/overview) ([md](https://docs.foxora.ai/release-notes/overview.md)): Use release notes to plan upgrades, identify client-specific versions, understand behavioral changes, and validate the installation afterward. - [Latest release](https://docs.foxora.ai/release-notes/latest-release) ([md](https://docs.foxora.ai/release-notes/latest-release.md)): Compare the latest published Desktop and CLI versions with Settings About and `foxora --version`, read upgrade notes, install the applicable release, and verify it. - [V5 release notes](https://docs.foxora.ai/release-notes/v5-release-notes) ([md](https://docs.foxora.ai/release-notes/v5-release-notes.md)): Review the foxora workspace, studio, tasks, projects, agents, crews, Memory Den, autonomy, workflows, schedules, plugins, channels, MCP Server, CLI, API, and migration requirements. - [Previous releases](https://docs.foxora.ai/release-notes/previous-releases) ([md](https://docs.foxora.ai/release-notes/previous-releases.md)): Locate the installed version, read releases in chronological order up to the target, note breaking or data changes, and reproduce legacy behavior before upgrading if it matters. - [Known limitations](https://docs.foxora.ai/release-notes/known-limitations) ([md](https://docs.foxora.ai/release-notes/known-limitations.md)): Search by affected surface and version, confirm the limitation matches the observed behavior, apply only the documented workaround, and retest after the fixing release. - [Deprecated features](https://docs.foxora.ai/release-notes/deprecated-features) ([md](https://docs.foxora.ai/release-notes/deprecated-features.md)): Identify the deprecated behavior and removal version, locate every dependent agent, workflow, script, or integration, migrate to the supported replacement, and test before removal. ## More - Whole platform as one Markdown file: https://foxora.ai/llms-full.txt - Product documentation: https://docs.foxora.ai - App & account, billing, cloud agents: https://app.foxora.ai