Get it for macOS

Dashboards built by prompting an agent that open in their own side-panel tab, stay interactive, refresh their own data and change when you ask again.


Overview

View source

What you get

  • Ask an agent in any thread for a dashboard, report, tracker or small tool you want to keep. It writes the dashboard in OpenUI Lang with OpenUI's dashboard components, the plugin checks and saves it, and the reply shows a card that opens it in its own side-panel tab.
  • 62 components: OpenUI's 45 dashboard components (KPIs, time series, bars, donuts, tables, funnels, maps and more) plus tabs, record lists with a details drawer, search, toggles, sliders, notes and a sandboxed HTML frame.
  • Filters, tabs, search and drill-down respond with no model call. Your choices are remembered in your browser.
  • Live data from a JSON or CSV file in the thread's folder, the branch's commits, changed files and pull request, a read-only tool of an MCP server you add, or a script you approve. These refresh without the agent; data only the agent can reach is refreshed by asking it.
  • Change a dashboard by asking again, or click Edit, point at a part and say what should change. Every save is a new version; the newest 100 stay viewable, and an old one can be restored.
  • A Colours button for your own accent, chart palette and light or dark look, and a Dashboards page that lists every dashboard and holds the Connections section.
  • For agents: the dashboards skill and the tools dashboard_save, dashboard_get and dashboard_sources.

How it stays read-only

  • Every save is checked: a program cannot contain Mutation, links open only http and https, and free HTML runs in a sandboxed frame with no network.
  • Only MCP tools that the server marks read-only and that you confirm can be called.
  • A script runs on your computer only after you read and approve its exact text. An approved script is not sandboxed, and an agent you allow to run shell commands could approve one through bb's command line.
  • Tokens stay in the operating system's secure store, never in the plugin's database, the page or the agent's view.

Requirements and costs

  • bb 0.49 or later. No account and no outside service of the plugin's own: the plugin itself contacts only the web MCP servers you add. Pull request data comes through bb's built-in GitHub pull request plugin, and an approved script reaches whatever its text reaches.
  • Viewing, filtering and refreshing cost no model call. Each change, Edit request, AskAgent click or agent-source refresh is one agent turn.
  • Tested on macOS only. Scripts are not supported on Windows. Connections with a token need the system's secure store; the Windows and Linux stores are untested, and Linux needs secret-tool with a keyring.
  • No telemetry of its own. OpenUI's runtime usage report stays off unless OPENUI_RUNTIME_TELEMETRY_ENABLED is set.

Built on OpenUI Lang and OpenUI's dashboard component library: openui.com.

More from Muhammad Ahsan

GitHub PR DashboardSee why each pull request is stuck, and get it unstuck, without leaving bb. My PRs lists your pull requests, review requests for you and your teams, the ones you reviewed, and assigned ones by repository, each with its +/- lines and led by what blocks it: failing CI down to the job, changes requested, unresolved comments, conflicts or a stack. Reviewed turns amber when the author pushes after your review. Open one for its reviewers and their verdicts, labels, and tabs: Overview (the description, then comments and reviews), Checks with error annotations, Files with syntax-highlighted diffs and review threads under their lines, Commits with the ones since your review marked, and Comments. Edit the title and description, comment on a line or range, reply, delete your own comments, submit a review, mark your draft ready, and close or reopen, each only when you click. A menu links the PR to a bb thread, asks about it, explains it, or sends every finding to an agent, starting in the PR's project; Fix with agent does it for one comment or failed job. Jira keys open in bb's My Jira plugin. Search, hide or fold repositories, move by keyboard, switch gh accounts, and get alerts when CI fails or someone comments. Uses the GitHub CLI login or a token; github.com only.NewUsage ExplorerSee how much of your Claude plan is left and where your AI coding spend went, by session, day and model, across every agent CLI you use. Each limit window shows what is left, when it resets and where you will land at your current pace, with a plain verdict on whether there is room for a big task. Sessions carry their titles and projects; open one for its models and its cost by token type, or click a model to filter the whole page. Reads Claude Code, Codex, Gemini CLI, OpenCode and the other CLIs ccusage supports from their local logs, and draws each provider in its own colour. Prices come from LiteLLM's public price list, so a newly released model is priced without a plugin update. Plan limits use the Claude Code sign-in already on your machine and need a Claude subscription.NewMarkwrightEdit Markdown files like a Word document, inserting tables, diagrams, callouts and templates from a / menu instead of typing syntax. A save rewrites only the blocks you changed, so untouched text keeps its exact bytes and git diffs stay small. Eight Mermaid starters render as live diagrams while you edit their source, and eleven document templates fill an empty file in one click. Every save checks the file's hash first: if an agent changed it while you typed, autosave pauses and you compare, keep yours or take theirs. Files with footnotes, reference-style links or $$ math open read-only in bb's preview; needs bb 0.49 or later and no account or external service.NewJira BoardSee every Jira ticket assigned to you in one bb tab, filtered and grouped the way you work, and move it along without opening Jira. Filter by status and type, search by key or words, and group by status, initiative and epic, or the boards that list each ticket. Open a ticket beside the list to read its lineage, description, subtasks and comments, then step to the next one with Previous and Next or the keyboard. Change a status in place from the moves your workflow allows. Needs Jira Cloud with Atlassian's Rovo MCP server allowed for your organization; you sign in with Atlassian in the browser and set up nothing else.New

More in Thread Content 99

Change what people see or do inside an open thread.

View all
Generative UITurns agent replies into charts, diagrams, maps, plans and forms you can use, right in the chat. Agents choose from 86 components on their own, with no setup: sliders and filters recompute in the page, and buttons, choices and forms put your answers in your message, which reaches the agent when you send it. Test reports, logs, lint errors and coverage files render as their own components instead of pasted text, and a thread's changes, commits, pull request and workers are read live from BB. Adds about 6,400 tokens of instructions to sessions whose replies you read, and looks up photos, places and map tiles on Wikimedia Commons, Wikipedia, Photon and OpenStreetMap unless you turn web lookups off. Relies on BB internals, so a BB update can show the blocks as code until the plugin catches up.ComicBit1.1K
Agent TracesSee where your agents' time goes, from every thread down to each command, tool call, and subagent of a turn. A turn opens as a timeline that splits the agent's time into waiting on you, tools, subagents, thinking, writing, and model time, and it grows live while the agent works. Select a call to see its exit code, output, and arguments, or jump to the reply that followed it in the chat. A Traces page in the sidebar compares your recent threads by active time, calls, and errors, and two turns can be compared phase by phase. Turns export as OpenTelemetry or an HTML snapshot, and the bb agent-traces command gives agents the same answers. Traces come from the thread history on your bb server; an OpenTelemetry collector is optional.Nicolas Charpentier390