Open source · MIT · Bring your own key

Your browser,
driven by AI.

OpenSidebar is an open-source Chrome extension that puts an autonomous agent in your side panel — describe a task in plain English and it sees the page, clicks, types, and carries multi-step work across tabs to done.

Bring your own API key. No subscription, no telemetry, no backend — everything runs in your browser.

Runs 100% in your browser 51 browser tools Vision + planning + verification
▶ 60-sec tour OpenSidebar side panel driving a web task
Quick start

Two minutes to your first task

The Chrome Web Store listing is on the way. Until then, load the unpacked build — it takes one clone and one command.

Chrome Web Store

One-click install

A signed listing so anyone can add OpenSidebar straight from Chrome.

Coming soon
From source

Load the unpacked build

# clone & build
git clone https://github.com/krisshkodrani/OpenSidebar
cd OpenSidebar
corepack enable
corepack pnpm install
corepack pnpm run dist

# then in Chrome
chrome://extensions  Developer mode 
Load unpacked  select dist/

Requires Node.js 22+ and a supported provider API key.

Recorded live

See it actually do the work

No mockups, no cherry-picked frames — these are real sessions the agent drove end to end.

▶ 2:06 Agent completing a checkout on a shopping site

One agent for the open web

Checkout, a job application, a multi-step wizard, reading one page to write on another — no integration, no scripts.

▶ 2:20 Agent operating a ServiceNow workflow

Operates enterprise apps, live

The same agent drives ServiceNow — creating incidents, ordering from the catalog, filtering lists. One agent, every workflow.

▶ Watch Mode Watch Mode flagging a page change

Watch Mode keeps an eye out

Leave it watching a page and it tells you the moment something changes — flagged “back in stock” the instant it flipped.

▶ Setup Choosing a provider and model in settings

Your provider, your models

Paste a key, pick your models, go. Fireworks, OpenRouter, Moonshot, or Xiaomi — nothing hardcoded.

▶ 3:35 · narrated Full OpenSidebar tour

Watch the full tour

Eleven scenes in three acts — the open web, staying in control, and the ServiceNow finale. Narrated, 3:35.

Recorded live — no scripts, no post-editing. Executor: Kimi K2.7 Code (vision) · Planner: GLM 5.2 · Fireworks AI

What it does

An agent that sees, plans, acts — and stays in your control

Sees the page like you do

A vision model works from the live screenshot and DOM — reads charts, zooms into fine print, and handles pages that defeat text-only bots.

51 browser tools

Clicking, typing, scrolling — plus file upload and download, tab and window management, and structured table, chart, and filter extraction.

Safe by default

Four approval modes. Consequential actions pause for you, and form submits are dry-run first — you approve the exact field values before they’re sent.

Plans, executes, verifies

A planner decomposes the task, an executor drives it, a verifier confirms the result — and stuck runs escalate to a stronger model instead of burning turns.

Remembers what matters

A local profile you review yourself, per-site skills learned from successful runs, and checkpoints that survive restarts. Sensitive fields are consent-gated and encrypted.

Watch Mode

Leave it watching a page and it tells you the moment the page changes — a price, a status, a new listing.

Speak or type

Voice input transcribes straight into the composer — describe the task out loud and let it run.

Yours to inspect

Every session produces a full-fidelity local trace. Keys live in Chrome storage; traffic goes browser → provider and nowhere else.

Bring your own key

Your provider. Your models. Your data.

Fireworks recommended OpenRouter Moonshot / Kimi Xiaomi MiMo

Your API key stays in Chrome storage; page context goes only to the provider you configure. No analytics, no tracking, no hosted relay, no OpenSidebar servers.

In the open-source repo · developer builds

Trust, but verify — locally.

The repo ships a full observability workspace: replay any run as a story — plan, nodes, turns, and the verifier's judge model showing its per-criterion reasoning and cost — then record whether the outcome was actually right. Traces never leave your machine.

  • MIT licensed. Audit every claim on GitHub.
  • Nx + pnpm monorepo. Manifest V3, Vitest, staged e2e harness.
  • Benchmarks with receipts. Neutral public numbers, published with per-task judge outputs — coming shortly.
▶ Trace viewer Adjudicating a run in the built-in trace viewer — judge reasoning and a recorded verdict