Execute a tool and return the result Args: tool_name: Name of the tool to execute arguments: Argumen

Execute a tool and return the result

Execute a tool and return the result

Extract image to text description

Format the system prompt with available tools in Qwen3 format

Generate a unique session ID

Get detailed error information for debugging

Get LLM instance based on configuration.

Get current memory context as a string

Retrieve relevant experiences for a given question. Args: question: The current question Re

Get current system state information

Get formatted timestamp

Get formatted timestamp

Get tool descriptions for the model

Index contextual chunks in the retrieval pipeline

Send documents to the retrieval pipeline for indexing

Send documents to the retrieval pipeline for indexing

Initialize the LLM client based on provider

Initialize Ollama backend

Initialize the system prompt for OpenAI co-founders research

Initialize the system prompt for the conversation

Initialize the system prompt for the conversation

Initialize the system prompt for the conversation

Initialize the system prompt with memory context based on memory mode

Check if path is within workspace.

Get non-streaming response from the model Args: messages: Conversation messages Returns:

Process using Gemini's native multimodal API with thinking mode

Resolve path relative to workspace.

Internal function to run a timer.

Start a new session

Stream response from the model Args: messages: Conversation messages Returns: C

Stream response content

Stream response content

Stream response from the model

Execute Python code in restricted environment

Execute shell command

Read file contents with optional line-based reading

Rewrite TODO list with new pending items

Update status of TODO items

Write content to file

Trigger callback actions when timer expires.

Add an experience to the knowledge base. Args: query: The query/question for indexing experience: Th

Add an item to the HNSW index.

Add a new memory item

Analyze conversation context and determine memory updates Args: conversation_context: List of conversation messa

Analyze an image with a specific query

Answer a question about user conversation history using RAG Args: question: The question to answer t

Answer a question using dual memory system Args: question: The question to answer test_id: Test case

Apply formula to Excel cell. Args: file_path: Path to Excel file sheet_name: Worksheet name cell: Cell reference

Apply tone modification to text (wiki or system prompt) Args: text: Original text tone_style: The tone style to apply

Build RAPTOR tree index from text.

Build or rebuild indexes by sending all chunks to retrieval pipeline

Build or rebuild indexes by sending all chunks to retrieval pipeline

Build knowledge graph from text.

Build Elo leaderboard using highly optimized NumPy + Numba algorithm. This implementation is significantly faster than the basic version

Calculate Inverse Document Frequency for a term

Calculate summary statistics across all metrics

Cancel an active timer. Args: timer_id: ID of the timer to cancel Returns: Dictionary with cancellation status

Change the current working directory. Args: directory: Directory to change to Returns:

Simple chat interface (wraps execute_task for compatibility) Args: message: User message stream: Whe

Stream a message to the model and handle tool calls in a ReAct loop Yields chunks that include: - type: 'thinking',

Stream a message to the model and handle tool calls in a ReAct loop Yields chunks that include: - type: 'thinking',

Chunk a single conversation into segments Args: conversation_id: Unique conversation identifier test

Chunk text into smaller segments. Args: text: Document text to chunk doc_id: Document identifier

Chunk text into smaller segments. Args: text: Document text to chunk doc_id: Document identifier

Clean up browser resources.

Clear all documents.

Clear all indexed documents

Convert between currencies. Args: amount: Amount to convert from_currency: Source currency code (e.g., USD) to_c

Copy a file or directory. Args: source: Source path destination: Destination path overwr

* Convert raw audio buffer to WAV format * @param {Buffer} audioBuffer - Raw PCM audio data * @param {Object} options - Audio format options

Create complex legal scenario questions

Create complex legal scenario questions

Create necessary directories if they don't exist

Create a new directory. Args: directory_path: Path for new directory parents: Create parent director

Create a new worksheet in Excel file. Args: file_path: Path to Excel file sheet_name: Name for new worksheet

Create sample legal documents for the knowledge base

Create sample legal documents for the knowledge base

Create sample memory cards for testing

Create simple direct legal questions

Create simple direct legal questions

Create a task that requires reading multiple files

Delete an item from the HNSW index.