Back to Home
Listen to page:
Documentation · v5 Agentic AI

yuktai: accessible, agentic AI that runs in the browser

An open-source React / Next.js toolkit: a data grid you can talk to, browser AI agents, WCAG accessibility and page Q&A. Everything on this page is a live demo of the real package.

7,213+npm downloads
10Agentic features
FreeCost
ZeroAPI keys needed
English + TeluguLanguages

Built during weekends and late nights, yuktai started as an accessibility plugin and grew into an agentic toolkit. Version 5 adds agents that understand plain-English (and Telugu) questions, test pages for accessibility, review forms and designs, and run multi-step tasks on a grid, all with rule-based logic in the browser, so they work offline and never send your data anywhere.

What's new in v5: 10 agentic features

Smart grid queries
"salary over 1 lakh and age under 30" → filters, sort, limit. Understands 10k, lakh, crore.
BI copilot
Group by, compare this month vs last month, trends.
Task runner
"filter, then sort, then summarize" runs as ordered steps with a before/after summary.
Anomaly finder
Flags unusual numbers and duplicate rows.
QA tester
15 WCAG checks, a 0–100 score and a Markdown report.
Accessibility copilot
Explains issues in plain English and applies safe fixes with undo.
Page understanding
Ask "what is this page for?" or "which fields have no label?"
Form review
Labels, autocomplete, error messages, senior-friendly tips.
Design review
Hierarchy, readability, focus states, clutter.
Voice commands
"bigger text", "high contrast", "next row" in English and Telugu.

Live demo: talk to a grid

useAgenticGrid + AgenticGridBar on 10 sample rows. Try the examples, or type your own. For 10 lakh rows on a real database, open the Yuktai Grid demo.

NameCityDepartmentSalaryJoinedStatus
Ravi KumarHyderabadEngineering₹1,45,00012 Mar 2024Active
Sneha VarmaBengaluruDesign₹92,00003 Aug 2025Active
Imran ShaikhMumbaiFinance₹1,18,00022 Jun 2022On leave
Kavya IyerChennaiEngineering₹1,62,00007 Oct 2026Active
Arjun MehtaDelhiSales₹76,00030 Sept 2024Active
Lakshmi RaoHyderabadHR₹68,00005 May 2023Active
Vikram JoshiPuneEngineering₹5,20,00011 Nov 2021Active
Priya NairKochiDesign₹88,00001 Oct 2026Probation
Rohit NaiduVijayawadaSales₹71,00014 Feb 2025Active
Divya ReddyHyderabadFinance₹1,25,00019 Jan 2023Active
Why it matters: The agent is rule-based, not a chatbot guessing: every answer says which filters it used, so the user can check it. If Chrome's built-in Gemini Nano is available it can be plugged in, but it is never required.

Live demo: test this page

runQaAudit() runs 15 WCAG checks and reviewDesign() checks hierarchy and readability, on this very page, right now.

import { runQaAudit, auditToMarkdown } from "@yuktishaalaa/yuktai";

const report = runQaAudit();          // 15 WCAG checks on the current page
console.log(report.score);            // 0–100
console.log(report.issues[0].fix);    // what to change, in plain English
const md = auditToMarkdown(report);   // paste into a ticket or PR

Live demo: ask this page

askAboutPage() reads the page structure (headings, forms, links, images) and answers questions about it. Search across page and grid text uses a BM25 index that also handles Telugu.

Live demo: multi-step tasks and voice commands

Task planner · planTasks()
Voice command parser · parseVoiceA11yCommand()

All-in-one: AgenticPanel

One component with six tabs: Copilot, QA, Forms, Design, Ask and Voice. Drop <AgenticPanel /> into any page.

Core: accessibility engine

  • WCAG 2.2 auto-fix: adds missing ARIA roles, labels and states to plain markup.
  • Speak on focus: reads the focused element aloud with the browser's speech engine.
  • Dyslexia-friendly mode, larger targets, reduced motion and keyboard mode.
  • Colour-blind filters: deuteranopia, protanopia, tritanopia, grayscale.

Open it from the ♿ button in the yuktai tools (bottom-left).

Core: in-browser RAG

  • Gemini Nano when Chrome's built-in AI is available.
  • Transformers.js fallback with 4-bit quantised models, so it also works on phones.
  • BM25 context index for fast keyword search over page and grid text, no model needed.

Try it from the 💬 button in the yuktai tools.

Core: Vibe Coder

Describe a page and get a starting layout from built-in templates. Free, offline, no API. Open it from the ⚡ button in the yuktai tools.

Use it in your Next.js app

1. Agentic grid with your own question bar

"use client";
import { YuktaiGrid, AgenticGridBar, useAgenticGrid } from "@yuktishaalaa/yuktai";

const columns = [
  { key: "name",   label: "Name",   type: "text"   },
  { key: "salary", label: "Salary", type: "number" },
  { key: "joined", label: "Joined", type: "date"   },
];

export default function StaffPage({ rows }) {
  // The agent: plain-English questions → filters, sort, highlights, summaries
  const grid = useAgenticGrid({ data: rows, columns, rowKey: "id" });

  return (
    <>
      <AgenticGridBar
        grid={grid}
        examples={["salary over 1 lakh", "joined this month", "anything unusual?"]}
      />
      <YuktaiGrid
        data={grid.gridData}
        highlightIds={grid.highlightIds}
        columns={columns.map((c) => ({ ...c, sortable: true }))}
      />
    </>
  );
}

2. Or the grid's built-in assistant with your own rules

<YuktaiGrid
  data={rows}
  columns={columns}
  ai                         // built-in assistant: chat + voice
  webmcp                     // exposes the grid as a tool to browser AI agents
  toolName="my_staff_grid"
  inputLanguage="te-IN"      // understands Telugu questions too
  customRules={[
    {
      name: "high-earners",
      phrases: ["high earners", "top people"],
      description: "Salary over 1 lakh",
      execute: ({ executeTool }) =>
        executeTool("filter", { key: "salary", operator: "greaterThan", value: 100000 }),
    },
  ]}
/>

Custom rules run before the built-in intents and match by phrase, so you can teach the assistant your own words.

Technical compatibility

AreaSupport
FrameworksReact 19 · Next.js 16 (App Router)
TypesFull TypeScript definitions
SSR safetyBrowser-only code checks for window, no hydration crashes
DataAgents run in the browser; your data stays on the device
Large dataServer mode: the grid asks your API page by page (tested on 10 lakh rows)
Browser AIWebMCP tool for browser agents · optional Gemini Nano
LanguagesEnglish and Telugu input; en-IN number format (10,00,000)
TestsVitest + happy-dom test suite for the agentic module
Install

Add yuktai to any React or Next.js project:

npm install @yuktishaalaa/yuktai