From 5da7f80daeffda300a3ab6fed337fe2da66c5d71 Mon Sep 17 00:00:00 2001 From: Timothy Jaeryang Baek Date: Fri, 10 Jul 2026 18:08:36 -0500 Subject: [PATCH] refac --- docs/ecosystem/computer/capabilities.md | 20 --------- .../automations-and-notifications.md | 41 ----------------- .../integrations/messaging-and-tools.md | 44 ------------------- docs/ecosystem/computer/is-it-right.md | 7 +++ docs/ecosystem/computer/open-webui.md | 12 ----- docs/ecosystem/computer/personas.md | 20 --------- docs/ecosystem/computer/use-cases/index.md | 39 +++++++++++----- docs/getting-started/essentials.mdx | 2 +- 8 files changed, 35 insertions(+), 150 deletions(-) delete mode 100644 docs/ecosystem/computer/capabilities.md delete mode 100644 docs/ecosystem/computer/integrations/automations-and-notifications.md delete mode 100644 docs/ecosystem/computer/integrations/messaging-and-tools.md delete mode 100644 docs/ecosystem/computer/open-webui.md delete mode 100644 docs/ecosystem/computer/personas.md diff --git a/docs/ecosystem/computer/capabilities.md b/docs/ecosystem/computer/capabilities.md deleted file mode 100644 index 778d5894..00000000 --- a/docs/ecosystem/computer/capabilities.md +++ /dev/null @@ -1,20 +0,0 @@ ---- -title: "What Open WebUI Computer can do" -unlisted: true ---- - -# What Open WebUI Computer can do - -This is a map to the documentation, not a feature checklist. Start with the job you need to complete; each guide explains the prerequisites, verification, and trust boundary. - -| Need | Documentation | -| --- | --- | -| Reach the same workspace, terminal, and git state from another device | [Your workspace](./workspace/workspace-paths) and [remote access](./remote-access/security-model) | -| Let an AI or coding-agent subscription work in a real repository | [AI and coding agents](./agents/models) | -| Review an agent, a diff, or a local service while away | [Use cases](./use-cases/agent-supervision) | -| Keep a task running and hear about the result | [Automations and notifications](./integrations/automations-and-notifications) | -| Work from Open WebUI while the action happens in Computer | [Use Open WebUI with a Computer workspace](./integrations/open-webui-gateway) | -| Give an agent a vetted external capability | [MCP and OpenAPI tool servers](./integrations/messaging-and-tools) | -| Run, secure, back up, or repair the service | [Operations](./operate/data-and-backups) and [troubleshooting](./troubleshooting/install-and-login) | - -Every capability is tied to the same boundary: it acts on the machine and workspace you select. Read the [security model](./remote-access/security-model) before enabling remote or unattended access. diff --git a/docs/ecosystem/computer/integrations/automations-and-notifications.md b/docs/ecosystem/computer/integrations/automations-and-notifications.md deleted file mode 100644 index 1db3add7..00000000 --- a/docs/ecosystem/computer/integrations/automations-and-notifications.md +++ /dev/null @@ -1,41 +0,0 @@ ---- -title: Automations, notifications, and webhooks -sidebar_position: 3 -unlisted: true ---- - -# Automations, notifications, and webhooks - -Automations are useful when a repeated check belongs beside the repository and tools that actually perform it: run a test suite, inspect a build result, or prepare a report in a known workspace. Notifications report what happened; authenticated webhooks trigger a known automation. They are not a safe way to accept arbitrary instructions from the internet. - -This legacy combined route remains for existing links. Start with [Schedule trusted work](./automations) for the task itself, then add [Notifications and webhooks](./notifications-and-webhooks) for delivery and secret-trigger handling. - -## Use this when - -Use this when you need a known prompt to run on a recurring schedule in one known workspace, then want a browser, webhook, or bot notification when it finishes or fails. - -## Before you start - -- Choose a stable workspace, model, and narrowly written prompt. -- Confirm the host stays on and the selected provider/model is available at the scheduled time. -- Configure the notification target first and use its test action. - -## Do it - -1. Create and validate the task with [Schedule trusted work](./automations). -2. Create and test its delivery or trigger with [Notifications and webhooks](./notifications-and-webhooks). -3. Review run history before enabling a recurring schedule. - -Automations can also have an authenticated webhook trigger. Treat that URL as a secret trigger, revoke it when no longer needed, and do not place it in public clients or issue trackers. - -## Verify it worked - -The automation displays an upcoming run and **Run now** creates a run-history entry with a linked chat. Its notification target’s test succeeds before you rely on an automatic notification. - -## If it did not - -Check the schedule’s next-run value, model availability, and run history error. Re-test the notification target and confirm the browser/device permits notifications. If a webhook invocation fails, regenerate the URL rather than weakening authentication. - -## Trust boundary - -Automations execute with full tool approval/high trust in their configured workspace because no person is present to approve each tool call. Give them only stable, reviewed prompts, models, workspaces, and notification endpoints. Do not use them for untrusted user input, destructive deploys, or a host you cannot monitor. diff --git a/docs/ecosystem/computer/integrations/messaging-and-tools.md b/docs/ecosystem/computer/integrations/messaging-and-tools.md deleted file mode 100644 index c8b48099..00000000 --- a/docs/ecosystem/computer/integrations/messaging-and-tools.md +++ /dev/null @@ -1,44 +0,0 @@ ---- -title: Messaging bots and external tools -sidebar_position: 6 -unlisted: true ---- - -# Messaging bots and external tools - -This legacy combined route remains for existing links. Messaging bots are useful when the fastest way to ask your machine a question is the chat app already on your phone. MCP and OpenAPI tools are useful when the agent needs a declared bridge to another service. They have different trust boundaries, so configure and review them separately. - -| Need | Read this | -| --- | --- | -| Message a private Computer workspace through Telegram, Discord, Slack, WhatsApp, or Signal | [Messaging bots](./messaging-bots) | -| Run a trusted local or remote MCP server | [MCP tool servers](./mcp-tool-servers) | -| Call a defined external HTTP API | [OpenAPI tool servers](./openapi-tool-servers) | - -## Use this when - -Use this when you are choosing the correct integration surface. Do not start with this overview when you need the actual configuration steps; use the specific guide above. - -## Before you start - -- Enter at least one exact platform user ID in **Allowed senders** before starting the bot. An empty list accepts every sender who can reach the bot. -- Use only a private bot account or channel you control. Sender allowlisting is not channel allowlisting, so do not add the bot to groups, shared workspaces, or public channels. -- For tools, obtain the command or endpoint, authentication material, and a clear description of its operations. - -## Do it - -1. Pick the specific guide above. -2. Complete its read-only verification before enabling a write-capable bot or tool. - -Not a fit: do not connect a public community channel, an untrusted group, or a third-party tool server whose data handling and permissions you cannot explain. Use a normal support bot or a constrained service API for that job instead. - -## Verify it worked - -The selected guide's read-only test completes and its result appears in the intended Computer chat/tool row. - -## If it did not - -Stop the integration, correct the named command/endpoint/credential, then rerun the read-only test. If the desired boundary cannot be expressed, do not enable the integration. - -## Trust boundary - -Bots use full approval/high trust: an inbound message can start agent work with host tools. MCP and OpenAPI tools run with the credentials and external permissions you provide; their inputs/results can leave the host. Give each integration the least powerful credential available, and disable it when not needed. diff --git a/docs/ecosystem/computer/is-it-right.md b/docs/ecosystem/computer/is-it-right.md index 16a0072e..d685d3de 100644 --- a/docs/ecosystem/computer/is-it-right.md +++ b/docs/ecosystem/computer/is-it-right.md @@ -31,6 +31,12 @@ Computer runs on a machine you control. Its core workspace does not require a ma External services still need their own network access. For example, a hosted model API, web search provider, Git remote, bot, or tool server can receive the data required for that feature. The point is that they are optional connections to your computer, not the place your core workspace must live. +## A cloud agent can be a better starting point + +Cloud agents are excellent when the job starts with a question, web research, a fresh deliverable, or material you are happy to upload. They provide a managed virtual computer, so you do not need to install or operate a machine first. + +Choose Computer when the value is in the machine you already own: a local project, an app that is already running, a signed-in browser, installed tools, a long-lived terminal, or files you do not want to copy into a hosted environment. The two approaches can complement each other. Use a cloud agent to research or create a new artifact, then use Computer when the work must meet the actual local project. + ## Use Open WebUI Computer when | You have this problem | What Computer changes | @@ -46,6 +52,7 @@ External services still need their own network access. For example, a hosted mod | Your actual need | Better starting point | | --- | --- | | You only want an AI chat, models, knowledge, prompts, or shared AI workflows. | [Open WebUI](https://docs.openwebui.com/) | +| You want a managed agent to research the web or create a fresh artifact, and no local machine state matters. | A cloud agent or general AI workspace. | | You need a new, disposable, isolated development environment. | A cloud IDE, virtual machine, or container designed for isolation. | | Teammates or untrusted people need separate, safely isolated access to a host. | A multi-user platform with tenant isolation; Open WebUI Computer is not that. | | You want to publish a shell/filesystem interface on the public internet. | Do not use a direct public deployment; use a private network pattern instead. | diff --git a/docs/ecosystem/computer/open-webui.md b/docs/ecosystem/computer/open-webui.md deleted file mode 100644 index 1de7971e..00000000 --- a/docs/ecosystem/computer/open-webui.md +++ /dev/null @@ -1,12 +0,0 @@ ---- -title: "Use Open WebUI with Open WebUI Computer" -unlisted: true ---- - -# Use Open WebUI with Open WebUI Computer - -This page keeps the original route for existing links. The maintained guide is now part of the integrations section. - -[Open the Open WebUI gateway guide →](./integrations/open-webui-gateway) - -Use Open WebUI when you want its AI interface and choose Open WebUI Computer when the requested work must happen in a particular real workspace. The gateway combines those roles without synchronizing their chats, knowledge bases, users, or configuration. diff --git a/docs/ecosystem/computer/personas.md b/docs/ecosystem/computer/personas.md deleted file mode 100644 index 0a002b66..00000000 --- a/docs/ecosystem/computer/personas.md +++ /dev/null @@ -1,20 +0,0 @@ ---- -title: "Find your path" -unlisted: true ---- - -# Find your path - -Choose a guide from the work you need to do now. You do not need to understand every feature before starting. - -| Your situation | Start here | -| --- | --- | -| You have an existing project but do not know terminal, git, SSH, or agent vocabulary. | [Is Open WebUI Computer right for me?](./is-it-right) | -| You design or review a live prototype and need to see it on a real device. | [Preview a local app on another device](./use-cases/real-device-preview) | -| The useful branch, log, or running terminal is on a machine you left behind. | [Fix something away from your desk](./use-cases/remote-fix) | -| A coding agent is working in a repository and needs supervision. | [Supervise an agent from anywhere](./use-cases/agent-supervision) | -| You want a repeatable private check to report back when it finishes. | [Schedule trusted work](./integrations/automations-and-notifications) | -| You use Open WebUI and want it to direct work in a real workspace. | [Connect Open WebUI to a Computer workspace](./integrations/open-webui-gateway) | -| You already understand private infrastructure and want to add capabilities carefully. | [Explore integrations](./integrations/messaging-and-tools) | - -Start locally and add only the next capability you can explain and verify. If you do not control the host machine, need a disposable environment, or need safely isolated access for untrusted people, [read the fit guide](./is-it-right) before continuing. diff --git a/docs/ecosystem/computer/use-cases/index.md b/docs/ecosystem/computer/use-cases/index.md index a1b5121d..08b0c2c4 100644 --- a/docs/ecosystem/computer/use-cases/index.md +++ b/docs/ecosystem/computer/use-cases/index.md @@ -9,18 +9,33 @@ Computer is most compelling when the work, context, or tools you need are alread Start locally first. Add private remote access only after seeing the existing work on the host feels useful. -| I need to… | Start here | The proof of value | -| --- | --- | --- | -| Turn a design review into a project artifact | [Review a prototype and capture feedback](./review-and-share-feedback) | The note, file, or link lands in the intended workspace. | -| Read reports, compare a spreadsheet, and keep findings beside the source files | [Work with local documents and data](./research-documents-data) | The PDFs, data files, and conclusion remain together in one real folder. | -| Keep a school, art, or maker project together across a phone and computer | [Keep a creative project together](./creative-student-project) | References, drafts, and captured ideas return in the same workspace. | -| Pick up exactly where I left off on another screen | [Resume a workspace from another device](./resume-workspace) | Existing files, tabs, and terminal output return. | -| Check a real branch, log, or small correction away from my desk | [Fix an issue from another device](./remote-fix) | The branch, diff, and terminal match the host. | -| Review and steer an AI coding task | [Supervise a coding agent](./agent-supervision) | Agent activity and the real diff are visible together. | -| Test the app already running on my machine from a phone or tablet | [Test a local app on a real device](./real-device-preview) | The preview is served by the existing local process. | -| Investigate a failed build or service alert while away | [Triage an on-call interruption](./on-call-triage) | Logs, process state, and git state come from the host. | -| Run a known recurring check and know whether it finished | [Run recurring checks](./recurring-checks) | A manual run creates a linked result before the schedule is trusted. | -| Use Open WebUI while work happens in one repository | [Use Open WebUI with a real workspace](./open-webui-workspace) | Computer shows the workspace activity behind the answer. | +## I need to keep feedback with a prototype or project + +[Review a prototype and capture feedback](./review-and-share-feedback) shows how to keep the note, file, or link in the intended workspace rather than scattered through another chat. + +## I have reports, PDFs, or a spreadsheet that matter + +[Work with local documents and data](./research-documents-data) keeps the source files and a conclusion together in one real folder. It works without AI, with optional AI as a carefully bounded helper. + +## I am making a school, art, or personal project across devices + +[Keep a creative project together](./creative-student-project) keeps references, drafts, and captured ideas in the same workspace when you switch between a phone and computer. + +## I want to continue what I was already doing + +[Resume a workspace from another device](./resume-workspace) proves that existing files, tabs, and terminal output return instead of making you reconstruct the work. + +## A real project needs a quick technical check + +[Fix an issue from another device](./remote-fix) puts the actual branch, diff, and terminal in front of you. [Test a local app on a real device](./real-device-preview) uses the existing local process rather than a recreated demo. + +## An agent, release check, or alert needs attention + +[Supervise a coding agent](./agent-supervision) puts agent activity beside the real diff. [Triage an on-call interruption](./on-call-triage) uses the host's actual logs and process state. [Run recurring checks](./recurring-checks) proves a scheduled result manually before you trust it unattended. + +## I use Open WebUI, but the answer is in a local workspace + +[Use Open WebUI with a real workspace](./open-webui-workspace) connects the familiar AI conversation to Computer's selected workspace, where the work can be inspected. If Open WebUI Computer is not installed yet, complete the [local trial](/ecosystem/computer/getting-started/local-trial). If a second device cannot reach the host yet, complete [remote access](/ecosystem/computer/remote-access) before following a remote scenario. diff --git a/docs/getting-started/essentials.mdx b/docs/getting-started/essentials.mdx index 0fb9efef..d6976d63 100644 --- a/docs/getting-started/essentials.mdx +++ b/docs/getting-started/essentials.mdx @@ -249,7 +249,7 @@ Open Terminal is the model's scratchpad for one-off tasks inside an Open WebUI c More detail: - [Open WebUI Computer: your computer in a browser](/ecosystem/computer) -- [Connect an Open WebUI Computer workspace to Open WebUI](/ecosystem/computer/open-webui) +- [Connect an Open WebUI Computer workspace to Open WebUI](/ecosystem/computer/integrations/open-webui-gateway) ---