Guida Complete

Programmable browser automation
on your Windows desktop

Navigate, extract and run scripts in a visible browser. Keep workspaces, queues and results on your machine, and connect an MCP assistant when you need one.

Download Guida Complete Getting Started Guide

Download Guida Complete

Recommended

Full desktop app with browser automation, MCP, scripting, queues, workflow tools, and operator UI.

Download Guida Node

Advanced

For remote execution. Runs headed browser automation and workspace workers through the Remote Ops API.
MCP-ready Expose browser actions to compatible AI tools Local-first No account, telemetry, or cloud sync required Approval and audit Review AI-triggered browser actions before execution
Guida quad layout showing four live browser tabs with MCP History and Store panes visible
Four live tabs WebView2 rendering MCP history Workspace store Full HD viewports

Available in Guida Complete

The Windows app combines a real browser, local project state, and AI-facing tools for practical automation workflows.

Automate browser tasks with scripts

Use JavaScript, Lua, or Janet to navigate pages, click elements, extract content, and save results.

Let AI operate the browser through MCP

Connect MCP-capable tools so an AI can inspect tabs, request actions, and run scripts with oversight.

Process queue-backed workflows across tabs

Enqueue URLs or records, run worker pools, and process items in parallel browser tabs.

Store extracted data locally or in databases

Write to workspace storage, queues, search indexes, PostgreSQL, MongoDB, S3-compatible storage, or Elasticsearch.

Review and audit sensitive AI actions

Use domain controls, tool approval, audit logging, and secret isolation to keep automation inspectable.

Support AI-assisted development

Give coding assistants a visible browser surface for rendered-page checks, UI investigation, and evidence gathering alongside conventional test tools.

See Guida in use

The app is visible, inspectable, and built around workflows you can review while they run.

Two-screen Guida desktop recording preview for a career portal assessment workflow Watch the demo

Assess career portals with Codex and Guida

Watch a two-screen desktop workflow where Codex uses Guida to inspect rendered career sites, compare page behavior, and capture findings. Guida is useful when a coding assistant needs a visible, approval-gated browser alongside Playwright or Puppeteer checks.

2 min 56 sec Two-screen capture Local workspace notes
MCP Approval Center showing a pending navigate approval with exact tool parameters and approve or deny actions

Approve AI-triggered actions

Review pending MCP requests with exact parameters before allowing browser actions to run.

 Queue Console showing queue counts, pending items, payload details, worker controls, and triage actions

Operate queues directly

Inspect pending work, dead-letter failures, payloads, worker state, and recovery actions in one console.

 Workflow Ledger Console showing selected run items, details, execution recovery, queue linkage, and event tabs

Understand workflow state

See what ran, what failed, what can be retried, and how queue work links back to durable ledger truth.

Built for programmable browser work

Build contracted data operations, connect AI tools, process queues, and keep sensitive actions inspectable.

Programmable Browser Automation

Drive WebView2 browser tabs with scripts: navigate pages, click elements, fill forms, extract content, and capture screenshots.

Certified Extractor Catalogs

Define reusable extractor contracts, validate catalogs, run bounded certification with evidence, and follow results over time.

Semantic Pipelines

Connect extractors, validation gates, mappers, and destinations with preflight, preview, provenance, and bounded execution.

Guida Control

Use the separate proprietary alpha console to observe and operate Guida nodes over a trusted Remote Ops channel.

AI and MCP Control

Connect MCP-capable tools so AI agents can inspect tabs, request browser actions, and run scripts with your oversight.

Complete, Node, and Remote Ops

Use Guida Complete for the full local operator UI, Guida Node for headed remote execution, and Remote Ops as their explicitly enabled JSON-RPC control plane.

Built-in Script Engine

JavaScript, Lua, and Janet with a generated API contract, IntelliSense, debugging, and workspace-aware execution.

Workspaces and Data Destinations

Persist data in workspace storage, queues, full-text search, PostgreSQL, MongoDB, S3-compatible storage, and Elasticsearch.

Workspace Backups

Create full workspace archives or smaller managed-state backups with consistent SQLite snapshots for queues and workflow ledger history.

Approval and Domain Controls

Review AI-requested actions before they run, approve once or for the session, and restrict navigation to allowed domains.

Audit Trail and Secret Isolation

MCP actions are logged, secrets are encrypted with DPAPI, and MCP-origin scripts cannot read decrypted secret values.

Recipes from real scripts

Start from workflows that ship with Guida, then adapt them to your own workspace.

Scraping and Extraction Beginner

Scrape and store page data

Extract page content, save it to the workspace store, and index it for full-text search.
Queues and Workers Intermediate

Queue URLs and process them

Add URLs to a workspace queue, dequeue each item, and commit completed work.
MCP and AI Intermediate

Ask the local LLM

Send a prompt to the configured local LLM and optionally summarize the active page.

AI and automation in Guida Complete

From connection to automation in three steps.

1

Connect your AI

Point any MCP-compatible AI at Guida's server. Or use Ollama and LlamaSharp directly inside the app.

2

Stay in control

Inspect requested browser actions and choose the approval settings that fit your workspace.

3

Automate with confidence

Reviewed scripts run unattended. Workspaces persist data. Queue workers process items in parallel.

The g.* scripting API

Navigate, extract, and store data with a clean scripting API. Write scripts yourself, or let the AI generate them.

scrape-products.js 
async function main() {
  try {
    await g.nav.navigateToUrl("https://example.com/products");
    await g.dom.waitForDomStable();

    // Extract name and price from every product card
    const products = await g.dom.getElements(
      ".product", ["innerText", "data-price"]
    );

    // Store each product in the workspace
    for (const p of products) {
      g.store.put("products", p.innerText, p);
    }

    g.log("Stored " + products.length + " products");
  } catch (e) {
    g.log("Error: " + e.message);
  }
}
g.nav.navigateToUrl("https://example.com/products")
g.dom.waitForDomStable()

-- Extract name and price from every product card
local products, err = g.dom.getElements(
  ".product", "innerText,data-price"
)
if err then
  g.log("Error: " .. err)
  return
end

-- Store each product in the workspace
for i, p in ipairs(products) do
  g.store.put("products", p.innerText, p)
end

g.log("Stored " .. #products .. " products")
(g.nav.navigateToUrl "https://example.com/products")
(g.dom.waitForDomStable)

# Extract name and price from every product card
(def products (g.dom.getElements
  ".product" "innerText,data-price"))

# Store each product in the workspace
(each p products
  (g.store.put "products" (get p "innerText") p))

(g.log (string "Stored " (length products) " products"))

Ready to take control?

Download Guida, connect your AI, and start automating - with full visibility into every action.

Download Guida Complete Download Guida Node Getting Started Guide