Jido Browser
Browser automation for Jido AI agents.
Overview
Jido.Browser is an agent-browser-first browser automation library for Jido.
agent-browseris the default and only first-class backend in 2.0- each browser session is backed by a supervised external daemon
- Elixir talks to the daemon over the upstream local JSON socket/TCP protocol
VibiumandWebremain available as legacy, feature-frozen adapters for transitional use
The Hex package and OTP app remain jido_browser, while the public Elixir namespace is Jido.Browser.*.
Installation
Add the dependency:
def deps do
[
{:jido_browser, "~> 2.0"}
]
endInstall the default browser backend:
mix jido_browser.install
That installs the pinned agent-browser binary for the current platform and runs agent-browser install to provision the browser runtime.
Recommended Alias Setup
defp aliases do
[
setup: ["deps.get", "jido_browser.install --if-missing"],
test: ["jido_browser.install --if-missing", "test"]
]
endInstalling Specific Backends
mix jido_browser.install agent_browser
mix jido_browser.install vibium
mix jido_browser.install webQuick Start
{:ok, session} = Jido.Browser.start_session()
{:ok, session, _} = Jido.Browser.navigate(session, "https://example.com")
{:ok, session, snapshot} = Jido.Browser.snapshot(session)
snapshot["snapshot"] || snapshot[:snapshot]
{:ok, session, _} = Jido.Browser.click(session, "@e1")
{:ok, _session, %{content: markdown}} = Jido.Browser.extract_content(session, format: :markdown)
:ok = Jido.Browser.end_session(session)Selectors remain supported, but ref-based interaction is the preferred 2.0 flow:
snapshot-
act on
@eNrefs - re-snapshot
State Persistence
state_path = Path.expand("tmp/browser-state.json")
File.mkdir_p!(Path.dirname(state_path))
{:ok, session} = Jido.Browser.start_session()
{:ok, session, _} = Jido.Browser.navigate(session, "https://example.com")
{:ok, session, _} = Jido.Browser.save_state(session, state_path)
:ok = Jido.Browser.end_session(session)
{:ok, restored} = Jido.Browser.start_session()
{:ok, restored, _} = Jido.Browser.load_state(restored, state_path)Tab Workflow
{:ok, session} = Jido.Browser.start_session()
{:ok, session, _} = Jido.Browser.navigate(session, "https://example.com")
{:ok, session, _} = Jido.Browser.new_tab(session, "https://example.org")
{:ok, session, tabs} = Jido.Browser.list_tabs(session)
{:ok, session, _} = Jido.Browser.switch_tab(session, 1)
{:ok, session, _} = Jido.Browser.close_tab(session, 1)Plugin Setup
defmodule MyBrowsingAgent do
use Jido.Agent,
name: "browser_agent",
plugins: [
{Jido.Browser.Plugin,
[
adapter: Jido.Browser.Adapters.AgentBrowser,
headless: true,
timeout: 30_000
]}
]
endConfiguration
config :jido_browser,
adapter: Jido.Browser.Adapters.AgentBrowser
config :jido_browser, :agent_browser,
binary_path: "/usr/local/bin/agent-browser",
headed: falseLegacy adapters can still be configured explicitly:
config :jido_browser, :vibium,
binary_path: "/path/to/vibium"
config :jido_browser, :web,
binary_path: "/usr/local/bin/web",
profile: "default"Backends
AgentBrowser (Default)
- native snapshot support with refs
- supervised daemon per session
- direct JSON IPC from Elixir
- built-in state save/load and tab management support
Vibium (Legacy)
- retained for transitional compatibility
- feature-frozen in 2.0
Web (Legacy)
- retained for transitional compatibility
- feature-frozen in 2.0
Public API
Core operations:
start_session/1end_session/1navigate/3click/3type/4screenshot/2extract_content/2evaluate/3
Agent-browser-native operations:
snapshot/2wait_for_selector/3wait_for_navigation/2query/3get_text/3get_attribute/4is_visible/3save_state/3load_state/3list_tabs/2new_tab/3switch_tab/3close_tab/3console/2errors/2
Available Actions
Session
StartSessionEndSessionGetStatusSaveStateLoadState
Navigation
NavigateBackForwardReloadGetUrlGetTitle
Interaction
ClickTypeHoverFocusScrollSelectOption
Waiting and Queries
WaitWaitForSelectorWaitForNavigationQueryGetTextGetAttributeIsVisible
Content and Diagnostics
SnapshotScreenshotExtractContentConsoleErrors
Tabs
ListTabsNewTabSwitchTabCloseTab
Advanced and Composite
EvaluateReadPageSnapshotUrlSearchWeb
Using With Jido Agents
defmodule MyBrowsingAgent do
use Jido.Agent,
name: "web_browser",
description: "An agent that can browse the web",
plugins: [{Jido.Browser.Plugin, [headless: true]}]
endJido.Browser.Plugin now exposes 37 browser actions, including snapshot/refs workflows, browser state actions, diagnostics, and tab management.
License
Apache-2.0 - See LICENSE for details.