Read the full text contents from a specific file strictly inside the sandboxed workspace folder. Use this to get context from previous documents or code files.

Write or overwrite text content to a specific file inside the sandboxed workspace folder. Automatically creates directories if they do not exist. Use this to save notes, code, or outputs.

Store long-term semantic context or user preferences permanently in the vector database. Use this when the user explicitly asks you to remember something or when key insights are uncovered.

Query the persistent vector database to recall past context, preferences, or project details. Use this to check if you have existing knowledge on a topic the user mentions.

Search the live web using the Tavily API for highly optimized real-time technical answers, documentation, news, or updates.

Locally run a deep learning classification pipeline to detect semantic emotional markers (Joy, Sadness, Anger, Fear, Surprise, Disgust, Neutral) inside a block of text. Use this to adapt your tone or better understand user sentiment.