Automation
Plugin
actionbook
Actionbook turns the websites you work in every day into something your AI agent can actually operate. Direct API requests when possible, UI automation when not, with login handled. Fast and resilient.
Plugin Signal88/100Strong
maintained98
capable77
documented100
adopted68
Install on Claude Code
> /plugin marketplace add actionbook/actionbook> /plugin install actionbook@actionbook-marketplace
What's inside
Skills
11/actionbookActivate when the user needs to interact with any website — browser automation, web scraping, screenshots, form filling, UI testing, monitoring, or building AI agents. Provides pre-verified page actions with step-by-step instructions and tested selectors./actionbook-scraperGenerate and verify web scraper scripts using Actionbook's verified selectors. Auto-validates generated scripts and fixes errors./agent-browserAutomates browser interactions for form filling and web page interaction. Used by the request-website command to submit website indexing requests./arxiv-viewerView, search, and download academic papers from arXiv. Supports API queries, web scraping via Actionbook, and HTML paper reading via ar5iv. Use when user asks about arxiv papers, academic papers, research papers, paper summaries, latest papers, or wants to search/download/read/deep-researchDeep research and analysis tool. Generates comprehensive HTML reports on any topic, domain, paper, or technology. Use when user asks to research, analyze, investigate, deep-dive, or generate a report on any subject. Supports academic papers (arXiv), technologies, trends,/actionbookAccess pre-computed website action manuals containing page descriptions, functionality, DOM structure, and element selectors for browser automation. Use when you need CSS/XPath selectors for UI elements, building browser-based AI agents, or looking up how to interact with a
Show all 11 skillsShow fewer
/agent-browserAutomates browser interactions for web testing, form filling, screenshots, and data extraction. Use when the user needs to navigate websites, interact with web pages, fill forms, take screenshots, test web applications, or extract information from web pages./rust-learnerLearn Rust language features and crate updates. Use when user asks about Rust version changelog, what's new in Rust, crate updates, Cargo.toml dependencies, tokio/serde/axum features, or any Rust ecosystem questions./actionbookBrowser action engine. Provides up-to-date action manuals for the modern web — operate any website instantly, one tab or dozens, concurrently./active-researchDeep research and analysis tool. Generates comprehensive HTML reports on any topic, domain, paper, or technology. Enhanced with advanced browser automation — SPA handling, network idle wait, batch operations, stealth browsing, and intelligent page analysis. Use when user asks to/extractExtract structured data from websites and produce an executable Playwright script plus extracted data. Use when the user wants to scrape, extract, pull, collect, or harvest data from any website — product listings, tables, search results, feeds, profiles, or any repeating
Agents
12code-generatorGenerates and verifies web scraper scripts using verified selectors from Actionbook.scraper-executorAgent for generating agent-browser scraper scripts using Actionbook selectors.structure-analyzerAnalyzes webpage structure using Actionbook data and presents selector information in a clear, actionable format.website-requesterAgent for submitting website indexing requests to Actionbook using **agent-browser CLI**.browser-fetcherBackground agent for fetching arxiv.org web content using **agent-browser CLI**.html-readerBackground agent for reading ar5iv.org HTML papers using **agent-browser CLI**.
Show all 12 agentsShow fewer
paper-fetcherFetch paper metadata from arXiv API.paper-summarizerDownload, summarize, and generate reports for arXiv papers.search-executorExecute arXiv API search queries.researcherDeep research agent that uses Actionbook browser CLI to browse the web, collect information from multiple sources, and generate structured json-ui reports.crate-researcherBackground agent for fetching Rust crate information using **agent-browser CLI**.rust-changelogBackground agent for fetching Rust version changelogs using **agent-browser CLI**.
Commands
16/analyzeAnalyze a webpage's structure using Actionbook's verified selectors and show available elements for scraping./generateGenerate web scraper scripts using Actionbook's verified selectors./list-sourcesList all websites that have verified selector data in Actionbook./request-websiteRequest a new website to be indexed in Actionbook by submitting its URL through the request form./citationsExtract the bibliography/references from an arXiv paper (ar5iv.org)./downloadDownload an arXiv paper PDF to local directory.
Show all 16 commandsShow fewer
/figuresExtract all figures and their captions from an arXiv paper (ar5iv.org)./latestGet the latest paper submissions for a specific arXiv category./outlineGet the table of contents (outline) of an arXiv paper from ar5iv.org./paperView and summarize an arXiv paper by ID or URL./readRead a specific section from an arXiv paper's HTML version (ar5iv.org)./reportGenerate a comprehensive AI-powered paper report with ActionBook branding/searchSearch arXiv papers using advanced query syntax./trendingGet trending and highlighted papers from arXiv homepage./crate-infoGet information about a Rust crate including latest version, features, and changelog./rust-featuresGet Rust version changelog and new features.
MCP
1Badges
1README
110x Faster | 90% Token Saving | 30 Actions at Once
Website · GitHub · X · Discord
Actionbook
Actionbook turns the websites you work in every day into something your AI agent can actually operate. Direct API requests when possible, UI automation when not, with login handled. Fast and resilient.
Table of Contents
- Why Actionbook?
- Installation
- Quick Start
- Examples
- Available Tools
- Documentation
- Contributing
Why Actionbook?
❌ Without Actionbook
- Slow. Agents take a snapshot after every single step, parse the page, then decide what to do next. Searching one room on Airbnb takes 5 minutes.
- Brittle. Modern websites use virtual DOMs, streaming components, and SPAs. Agents don't understand these rendering mechanisms, so they fail on dropdowns, date pickers, and login walls.
- One at a time. Your agent finishes one page before it can start the next. Need to check 30 company websites? That's 30 rounds, one after another.
✅ With Actionbook
- 10x faster. Action manuals tell agents exactly what to do. No parsing, no guessing.
- Accurate. Direct API calls when possible, UI fallback when not. Login handled either way.
- Concurrent. Stateless architecture. Operate dozens of tabs in parallel.
See an agent visits 192 First Round portfolio company websites and collects their taglines in 2 minutes. (Video is not sped up)
https://github.com/user-attachments/assets/35079a19-7236-47a8-87ed-3edf6436c2bf
Installation
Actionbook runs as a remote MCP connector paired with the Actionbook Chrome extension — no CLI install required. Your AI agent connects to the hosted MCP endpoint, and the extension drives your real Chrome so agents reuse your logged-in sessions.
👉 For the full step-by-step setup — with per-client instructions and screenshots — visit the dashboard. The three steps below are the quick overview.
1. Install the Chrome extension from the Chrome Web Store.
2. Add Actionbook as a connector in your AI app. Open your app's connector settings — Claude (Settings → Connectors → Add custom connector), ChatGPT (Settings → Connectors), Perplexity, Hermes, OpenClaw, or any other MCP-compatible app — and paste the Actionbook endpoint:
https://edge.actionbook.app/mcp
3. Finish setup from the dashboard — it walks you through connecting your client and confirms the extension is linked.
Note: The standalone
@actionbookdev/clipackage is deprecated. Use the remote connector + Chrome extension above.
Quick Start
Once the extension is installed and your client is connected (see Installation), just talk to your agent — Actionbook handles the rest:
Open stripe.com, linear.app, and vercel.com, then grab the pricing from each.
Behind the scenes the agent uses Actionbook to fetch action manuals and operate your real Chrome — opening tabs, reading snapshots, clicking, and filling forms across pages concurrently. To nudge it explicitly, add this to your prompt:
Use Actionbook to understand and operate the web page.
Examples
Explore real-world examples in the Examples Documentation.
Available Tools
Actionbook exposes a single actionbook MCP tool whose subcommands cover action lookup (search, manual) and browser control (goto, snapshot, click, type, …). Your agent discovers the full command set from the tool description once connected.
Chrome Extension
Install the extension from the Chrome Web Store. Once you sign in from the dashboard, it connects to the hosted MCP endpoint automatically.
Documentation
For comprehensive guides, API references, and tutorials, visit our documentation site:
Stay tuned
We move fast. Star Actionbook on Github to support and get latest information.
Join the community:
- Chat with us on Discord - Get help, share your agents, and discuss ideas
- Follow @ActionbookHQ on X - Product updates and announcements
Contributing
- Read the Contributing Guide - See repository setup, package layout, and validation workflows for the public repo.
- Request a Website - Suggest websites you want Actionbook to index.
License
See LICENSE for the license details.
File tree
563actionbook/actionbookView on GitHub
.changeset/
config.json
README.md
.claude-plugin/
marketplace.json
plugin.json
.github/
ISSUE_TEMPLATE/
bug-report.yml
config.yml
feature-request.yml
question.yml
pull_request_template.md
workflows/
discord-release-notify.yml
e2e-windows.yml
release-cli.yml
test.yml
.gitignore
.prettierignore
.prettierrc.json
CLAUDE.md
CODE_OF_CONDUCT.md
CONTRIBUTING.md
docs/
actionbook-demo.mp4
api-reference/
cli.mdx
evaluate-api.mdx
mcp-tools.mdx
community/
contributing.mdx
docs.json
examples.mdx
favicon.ico
guides/
browser.mdx
cli-and-skills.mdx
dify-plugin.mdx
installation.mdx
mcp-server.mdx
sdk-integration.mdx
skills.mdx
index.mdx
logo/
dark.svg
light.svg
openclaw.mdx
quickstart.mdx
snippets/
install-tabs.mdx
LICENSE
mcp-servers.json
package-lock.json
package.json
packages/
actionbook-extension/
.gitignore
background.js
callback.html
callback.js
CHANGELOG.md
cloud-config.js
icons/
icon-128.png
icon-16.png
icon-48.png
manifest.json
offscreen.html
offscreen.js
package.json
popup.html
popup.js
PRIVACY.md
README.md
scripts/
package.js
cli/
cli-darwin-arm64/
bin/
.gitignore
.gitkeep
CHANGELOG.md
package.json
cli-darwin-x64/
bin/
.gitignore
.gitkeep
CHANGELOG.md
package.json
cli-linux-arm64-gnu/
bin/
.gitignore
.gitkeep
CHANGELOG.md
package.json
cli-linux-x64-gnu/
bin/
.gitignore
.gitkeep
CHANGELOG.md
package.json
cli-win32-arm64/
bin/
.gitignore
.gitkeep
CHANGELOG.md
package.json
cli-win32-x64/
bin/
.gitignore
.gitkeep
CHANGELOG.md
package.json
.gitignore
bin/
actionbook.js
build.rs
Cargo.lock
Cargo.toml
CHANGELOG.md
docs/
api-reference.md
package.json
scripts/
postinstall.js
src/
action_result.rs
action.rs
api/
api_response.rs
client.rs
mod.rs
types.rs
browser/
cookies/
clear.rs
delete.rs
get.rs
list.rs
mod.rs
set.rs
element.rs
interaction/
batch_click.rs
click.rs
cursor_position.rs
drag.rs
eval.rs
fill.rs
focus.rs
hover.rs
mod.rs
mouse_move.rs
press.rs
scroll.rs
select.rs
type_text.rs
upload.rs
mod.rs
navigation/
back.rs
forward.rs
goto.rs
mod.rs
reload.rs
observation/
attr.rs
attrs.rs
batch_snapshot.rs
box.rs
describe.rs
html.rs
inspect_point.rs
logs_console.rs
logs_errors.rs
mod.rs
network_har.rs
network_request_detail.rs
network_requests.rs
pdf.rs
query.rs
screenshot.rs
snapshot_transform.rs
snapshot.rs
state.rs
styles.rs
text.rs
title.rs
url.rs
value.rs
viewport.rs
session/
close.rs
list.rs
mod.rs
provider.rs
restart.rs
start.rs
status.rs
stealth.rs
storage/
clear.rs
delete.rs
get.rs
list.rs
mod.rs
set.rs
tab/
batch_open.rs
close.rs
list.rs
mod.rs
open.rs
wait/
condition.rs
element.rs
mod.rs
navigation.rs
network_idle.rs
cli.rs
commands/
get.rs
manual.rs
mod.rs
search.rs
config.rs
daemon/
bridge.rs
browser.rs
cdp_error_classifier.rs
cdp_session.rs
cdp.rs
chrome_reaper.rs
mod.rs
registry.rs
router.rs
server.rs
session.rs
error.rs
extension/
installer.rs
mod.rs
ping.rs
status.rs
formatter/
mod.rs
lib.rs
main.rs
output.rs
setup/
api_key.rs
browser_cfg.rs
detect.rs
mod.rs
skills.rs
theme.rs
types.rs
utils/
client.rs
mod.rs
wire.rs
tests/
e2e/
batch_snapshot.rs
bridge.rs
browser_lifecycle.rs
cdp_errors.rs
cloud_mode.rs
cookies.rs
describe_state.rs
element_details.rs
element_read.rs
extension_new_tab.rs
extension.rs
harness.rs
iframe.rs
inspect_point.rs
interaction.rs
logs.rs
main.rs
manual.rs
navigation.rs
network_har.rs
network.rs
page_info.rs
pdf.rs
query.rs
screenshot.rs
search.rs
snapshot.rs
storage.rs
tab_management.rs
timeout.rs
wait.rs
windows_daemon.rs
help_cli.rs
manual_cli.rs
search_cli.rs
setup_cli.rs
stealth_contract.rs
version_cli.rs
dify-plugin/
_assets/
icon.svg
_plugin.py
.difyignore
CHANGELOG.md
constants.py
examples/
browser-automation.yml
main.py
manifest.yaml
package.json
PRIVACY.md
provider/
__init__.py
actionbook.py
actionbook.yaml
providers/
__init__.py
base.py
hyperbrowser.py
steel.py
pyproject.toml
README.md
requirements.txt
tests/
__init__.py
conftest.py
e2e/
__init__.py
conftest.py
test_browser_e2e.py
integration/
__init__.py
conftest.py
test_api_connectivity.py
test_get_action_live.py
test_search_actions_live.py
test_browser_create_session.py
test_browser_operator.py
test_browser_stop_session.py
test_cdp_client.py
test_connection_pool.py
test_get_action_by_area_id.py
test_playwright_worker.py
test_provider.py
test_providers.py
test_search_actions.py
test_workflow_snapshot_recovery.py
tools/
__init__.py
browser_create_session.py
browser_create_session.yaml
browser_operator.py
browser_operator.yaml
browser_stop_session.py
browser_stop_session.yaml
get_action_by_area_id.py
get_action_by_area_id.yaml
search_actions.py
search_actions.yaml
utils/
__init__.py
cdp_client.py
connection_pool.py
http_guard.py
playwright_worker.py
uv.lock
js-sdk/
package.json
src/
api-client.test.ts
api-client.ts
client.test.ts
client.ts
errors.ts
formatter.ts
index.ts
schema-utils.ts
tool-defs.test.ts
tool-defs.ts
types.ts
tsconfig.build.json
tsconfig.json
vitest.config.ts
json-ui/
CHANGELOG.md
example-report-rich.json
example-report.json
package.json
README.md
rust-1.93-report.json
site/
.gitignore
app/
globals.css
layout.tsx
page.tsx
... 306 moreFAQ
actionbook is a Claude Code plugin with 11 hand-picked skills for automation work, indexed on Flowy. Install it with the command on its page. It includes actionbook, actionbook-scraper, agent-browser. Its skills do not fire on their own yet. Request auto-invocation to have Flowy route them as you prompt. Free and open source.
- What is actionbook?
- Actionbook turns the websites you work in every day into something your AI agent can actually operate. Direct API requests when possible, UI automation when not, with login handled. Fast and resilient.
- How do I install actionbook?
- Run these in Claude Code: /plugin marketplace add actionbook/actionbook then /plugin install actionbook@actionbook-marketplace. Then prompt normally.
- Does actionbook auto-invoke its skills?
- Not yet. It is indexed on Flowy as a plain plugin. Request auto-invocation on its page and Flowy will route its skills for you as you prompt.
- Is actionbook free?
- Yes. Flowy is free and open source, with nothing gated. You can read every skill in full before you install.