Let the user audition voices and choose one by index. Args: language: Spoken language code passed to Speech. Returns:

Add system information to the prompt.

Combined analysis of language and emotion Args: text: string to analyze Returns: dictionary with language related

Apply security measures to block any website malicious/annoying execution, privacy violation etc..

This is a fallback for stealth mode to bypass SSL verification. Which can fail on some setup.

Check all links, one by one.

Clean and normalize text for speech synthesis by removing technical elements. Args: sentence (str): The input text to cle

Clean URL to keep only the part needed for navigation to the page

Clear a section of the memory. Ignore system message index. Args: start (int): Starting bound of the section to clear.

Click an element specified by XPath.

Check if the config file exists.

Create an undetected ChromeDriver instance with proper error handling.

Create a folder to store the voices. Args: path (str): The path to the folder.

Create the work directory if it does not exist.

Download the model if not already downloaded.

Print the current status of agenticSeek.

Estimate the complexity of the text. Args: text: The input text Returns: str: The estimated complexity

Execute Go code by compiling and running it.

Execute Java code by compiling and running it.

Execute bash commands and display output in real-time.

Executes a search query against a SearxNG instance using POST and extracts URLs and titles.

Execute python code.

Executes the file finding operation for given filenames. Args: blocks (list): List of filenames to search for Ret

Execute C code by compiling and running it.

Check if the code execution failed.

Check if the code execution failed.

check if bash command failed.

Checks if the execution failed based on the output.

Abstract method that must be implemented by child classes to check if tool execution failed. Args: output (str): The outp

Check if the code execution failed.

Checks if the file finding operation failed. Args: output (str): The output string from execute() Returns:

Check if the code execution failed.

Expands the prompt with the tools available.

Extract the reasoning block of a reasoning model like deepseek.

Fill form inputs based on a list of [name](value) and submit.

Fill inputs based on a list of [name](value) strings.

Filter out echo portions from the transcribed text. Returns the original text if it's not an echo, or an empty string if it is.

Find the name of the default AI. It is required for STT as a trigger word.

Find and click a submit button matching the specified type.

Find the last session path.

Finds a specific MCP server by its name. Args: query (str): a name or string that more or less matches the MCP server nam

Find the planner agent. Returns: Agent: The planner agent

Returns the API keys for the tools.

Find buttons and return their type and xpath.

Get the path to the Chrome executable.

Gets information about a file, including its name, path, type, content, and permissions. Args: file_path (str): The path

Find and return a free TCP port on the local machine.

Get the last blocks result.

Get the primary TTS language.

Extracts task names from the given text. This method processes a multi-line string, where each line may represent a task name.

Get page text as formatted Markdown

Get the date

Get the list of tools names and their description.

Get the list of tools names.

Get the user input from the microphone or the keyboard.

Initialize TTS, letting the user audition and pick a voice. Returns: None. Sets self.speech to a ready Speech instance.

Install the ChromeDriver if not already installed. Return the path. Automatically updates the driver if the version does not match the instal

Abstract method that must be implemented by child classes to provide feedback to the AI from the tool. Args: output (str)

Provides feedback about the file finding operation. Args: output (str): The output string from execute() Returns:

check if any bash command is unsafe.

Check if the transcribed text is likely the assistant hearing itself. Compares the transcribed text against the last text spoken by TTS.

Check if a URL is a valid link (page, not related to icon or metadata).

Check if the text qualifies as a meaningful sentence or contains important error codes.

Detect if AI attempt to run the code using bash. If so, return True, otherwise return False. Code written by the AI will be e

Few shot learning for complexity estimation. Use the build in add_examples method of the Adaptive_classifier.

Few shot learning for tasks classification. Use the build in add_examples method of the Adaptive_classifier.

check if a link is valid.

check if a link is valid.

Inference of the LLM router model. Args: text: The input text

Load a JSON file.

Recover the last session.