Generic chatbots suffer from amnesia. Coral AI implements a sophisticated Local Vector Memory database stored securely on your hard drive.
Core Architecture
How It Works Under The Hood
The Persistent Local Memory Engine module is built on a highly optimized C++ and Python bridge. By bypassing standard Windows UI restrictions, Coral AI directly interfaces with system memory, native Win32 APIs, and DOM structures to achieve near-zero latency execution.
Vector SQLite DB
Stores context locally on your C: drive, ensuring no private facts are uploaded to the cloud.
Dynamic Recall
Automatically queries past memory files when a related task is requested.
Explicit Forget Tools
Total control over what it remembers via the `delete_memory` execution tool.
Workflow Persistence
Can remember sequence of actions to recreate macros instantly.
This module does not operate in isolation. It is dynamically invoked by the Coral PlannerAgent via JSON-RPC, allowing it to be chained endlessly with vision and memory modules.