# Memory and Context **Vector Storage** Traditional chatbots often suffer from amnesia, forgetting details as soon as a session ends. Clawd Bot utilizes a local vector database to maintain persistent memory. When you interact with the agent, key information is embedded and stored. This allows the agent to recall preferences, past projects, and specific instructions given days or weeks ago. The memory is semantic, meaning the agent understands the meaning behind your query rather than just matching keywords. **Adaptive Context** Clawd Bot manages its context window dynamically. It intelligently retrieves relevant memories based on the current task. If you ask it to update a project you worked on last month, it pulls the relevant context from its database before generating a response. **User Personalization** Over time, Clawd Bot becomes attuned to your specific workflow. It learns your preferred coding style, the tone you use for emails, and the specific folder structures you prefer. This personalization happens automatically as you use the bot, creating an agent that is uniquely yours. --- # Agent Instructions: Querying This Documentation If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question. Perform an HTTP GET request on the current page URL with the `ask` query parameter: ``` GET https://docs.clawdtoken.xyz/2-features/memory-and-context.md?ask= ``` The question should be specific, self-contained, and written in natural language. The response will contain a direct answer to the question and relevant excerpts and sources from the documentation. Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.