AdaptTable for Chakra

AI table assistant in Chakra

@adapttable/ai is optional and provider-neutral. This Chakra demo combines a conversational assistant with a real table. Try filtering, grouping, column pinning and a proposed edit; available actions depend on the mounted features and the host's permissions. Row pinning requires an ungrouped view in this demo.

Start in Simulated mode: suggested prompts run deterministic local scenarios, not a language model. The conversation shows action receipts; a proposed write still follows approval and save policy. Connect backend sends your prompt and permitted table context to an endpoint you run. The assistant keeps the same table session and Chakra controls in both modes.

Three integration levels share that session: a custom bridge that maps any agent format onto session.execute, an AgentEnvelope on your transport, and optional JSON, OpenAI, MCP or HTTP helpers from your own runtime. Execution never requires another model call.

Chakra supplies the assistant's controls as well as filters and approval. Use the ready panel or render the same headless conversation state in your own UI.

The code

import { useTableAssistant } from "@adapttable/ai-react";
import { assistantHttpTransport } from "@adapttable/ai/http";
import { tableAgent } from "@adapttable/ai-react";
import { DataTable, agentApproval } from "@adapttable/chakra";
import { TableAssistant } from "@adapttable/chakra/assistant";
import { editing } from "@adapttable/chakra/editing";
import { filters } from "@adapttable/chakra/filters";
import { useMemo, useState } from "react";

const suggestions = [
  {
    id: "core-team",
    title: "Show only the Core team",
    prompt: "Show only the Core team.",
    requires: ["view.setFilters"],
  },
];

export function Orders({ rows, columns, onEdit }) {
  const [session, setSession] = useState();
  const transport = useMemo(
    () => assistantHttpTransport({ endpoint: "/api/table-agent" }),
    []
  );
  const assistant = useTableAssistant({ session, transport, suggestions });

  return (
    <>
      <DataTable
        data={rows}
        columns={columns}
        rowKey={(row) => row.id}
        features={[
          filters([{ key: "team", type: "multiSelect", getValue: (row) => row.team }]),
          agentApproval(),
          editing(onEdit),
          tableAgent({
            tableId: "orders",
            writePolicy: "allow",
            approval: "writes",
            commit: "stage",
            columns: { salary: { type: "number", writable: true } },
            bridge: { attach: setSession },
          }),
        ]}
      />
      <TableAssistant
        assistant={assistant}
        open={assistant.open}
        onOpenChange={assistant.setOpen}
      />
    </>
  );
}

Install

pnpm add @adapttable/chakra @adapttable/core @chakra-ui/react @emotion/react

The same feature in the other kits

• AI table assistant in Mantine — Rounded, friendly, filled controls
• AI table assistant in MUI — Material elevation, uppercase actions
• AI table assistant in Ant Design — Compact, tinted header, crisp
• AI table assistant in Radix — Radix Themes, iris accent
• AI table assistant in Base UI — Unstyled primitives, blue accent
• AI table assistant in shadcn — Monochrome, ring focus
• AI table assistant in Tailwind — Unstyled — your own classes

More Chakra features

• Filtering in Chakra — Operators, an AND/OR tree, chips, and find in the same URL.
• Column management in Chakra — Show, hide, reorder, pin and resize — from a menu you did not write.
• Column groups in Chakra — Spanning headers that collapse to a stub, a kept child, or a custom cell.
• Row selection in Chakra — A set of ids that survives paging, with bulk actions over it.
• Rows in Chakra — Pin rows, merge cells, and a 3-dot menu for add and delete.
• Row reordering in Chakra — Flat, grouped and tree moves — keyboard, confirm, host writes.
• Inline cell editing in Chakra — Kit-native editors in the cell; every write goes through your handler.
• Row grouping in Chakra — Drag, keyboard and mobile grouping controls with live aggregation overrides.
• Aggregation in Chakra — Footer totals, pinned summaries, group aggregates — not data rows.
• Nested tables in Chakra — A real table under a row — same engine, own columns, own keys.
• Export and print in Chakra — Browser files or cancellable server jobs — CSV, XLSX and PDF.
• Row and column virtualization in Chakra — 100k rows, 40 columns, virtualized rows and columns, sticky chrome.
• Tree data in Chakra — Nesting, chevrons, URL expansion, and host-owned tree moves.
• Mobile cards in Chakra — Every row becomes a card on phones. Automatically, with the same state.
• Pivot tables in Chakra — Rows down the side, dimensions across the top, subtotals at every level.
• Saved views in Chakra — Name an arrangement, share it as a link, manage the list in place.
• Spreadsheet formulas in Chakra — ROUND, POWER, SQRT, IF — computed columns, errors in the cell.
• Right-to-left Chakra data table — Arabic strings, a flipped axis, and a popover that opens from the right edge.
• Live updates in Chakra — Rows change while you read them. Sort and selection hold.
• Accessible Chakra data table — Arrow-key focus, a visible ring, forced-colors, and live announcements.

Reference: ai-http, ai-integrations, ai, agent-capabilities. More of this kit: AdaptTable for Chakra, or the live demo.