Create a new browser session with intelligent auto-close and session management

Navigate to a URL and optionally scrape content in one operation. Auto-creates session if needed.

Perform multiple interactions with a page: click, type, hover, select, screenshot, wait, scroll

Manage browser sessions: list, close, cleanup idle sessions, get status

[LEGACY] Navigate to a URL in an existing browser session. Use navigate_and_scrape instead.

[LEGACY] Scrape content from the current page. Use navigate_and_scrape instead.

[LEGACY] Take a screenshot of the current page. Use interact_with_page instead.

[LEGACY] Execute JavaScript in the browser context. Use interact_with_page instead.

[LEGACY] Interact with a page element. Use interact_with_page instead.

[LEGACY] Close a browser session. Use manage_browser_sessions instead.

[LEGACY] List all browser sessions. Use manage_browser_sessions instead.

AI-guided exploration and analysis of DOM structure using goal-oriented patterns. Analyzes stored DOM JSON to identify interactive elements, content areas, and navigation patterns.

Navigate to specific elements in DOM JSON using dot notation paths (e.g., 'body.main.article[0].paragraphs[2]'). Extracts content and provides element information.

Search for DOM elements by type, content, keywords, or attributes. Returns matching elements with their paths for further navigation.

Retrieve stored screenshot for a page. Returns file path or base64 encoded image data for AI visual analysis.

AI-powered analysis of page screenshots with custom prompts. Can focus on specific regions and provide contextual insights.

Scrape documentation from a website using intelligent sub-agents. Jobs are queued and processed automatically by the background worker. Supports plain string selectors for content extraction.

Get status of active and recent scraping jobs (worker runs automatically)

Cancel an active or pending scraping job

Force unlock a stuck scraping job - useful for debugging and recovery

Force unlock all stuck scraping jobs (jobs that haven't been updated recently)

List all configured documentation sources

Delete website pages matching URL patterns (useful for cleaning up version URLs, static assets)

Delete specific pages by their IDs

Delete all pages for a website (useful for clean slate before re-scraping)

Analyze project structure and generate a comprehensive overview

Generate AI-optimized project overview and analysis

Extract and analyze symbols (functions, classes, etc.) from code files

List files in a directory with smart ignore patterns

Search for files by pattern with optional content matching

Fuzzy string replacement in files with smart matching

Clean up orphaned or unused project directories

Store a knowledge graph memory with entity creation

Create a relationship between two entities in the knowledge graph

Search the knowledge graph using semantic or basic search

Find related entities through relationship traversal

Update or create analysis data for a specific file in the TreeSummary system

Remove analysis data for a deleted file from the TreeSummary system

Update project metadata in the TreeSummary system

Get comprehensive project overview from TreeSummary analysis

Clean up stale analysis files older than specified days

Join communication room for coordination

Send message to coordination room

Wait for messages in a room

Close a communication room (soft delete - marks as closed but keeps data)

Permanently delete a communication room and all its messages

List communication rooms with filtering and pagination

List messages from a specific room with pagination

Create a delayed room for coordination when agents realize they need it

Analyze coordination patterns and suggest improvements

Broadcast a message to multiple agents with auto-resume functionality

Create a high-level execution plan that generates coordinated Tasks for implementation

Get an execution plan with progress derived from linked Tasks

Execute a plan by creating Tasks and spawning coordinated agents

List execution plans for discovery and monitoring

Delete an execution plan by ID

Update an execution plan's status, priority, title, description, objectives, acceptanceCriteria, constraints, sections array, or metadata

Spawn architect agent to coordinate multi-agent objective completion

Execute structured phased orchestration with intelligent model selection (Research → Plan → Execute → Monitor → Cleanup)

Spawn fully autonomous Claude agent with complete tool access

Create and assign task to agents with enhanced capabilities

Get list of active agents

Terminate one or more agents

Monitor agents with real-time updates using EventBus system

Continue an agent session using stored conversation session ID with additional instructions

Clean up stale agents with enhanced options and optional room cleanup

Clean up stale rooms based on activity and participant criteria

Run comprehensive cleanup for both agents and rooms with detailed reporting

Get current cleanup configuration and settings for agents and rooms

Create comprehensive execution plan using sequential thinking before spawning agents

Retrieve a previously created execution plan

Execute an objective using a pre-created execution plan with well-defined agent tasks

Report progress updates for agent tasks and status changes