mcp-titan
54
The Titan Memory MCP Server provides a neural memory system that supports learning and predicting sequences for LLMs, with emphasis on maintaining memory state. It offers integration with Cursor and Claude, featuring efficient memory management and transformer-based architecture.
help
Get help information for available tools
init_model
Initialize the Titan Memory model
forward_pass
Forward pass through the model to get prediction
train_step
Perform training steps to update the model
get_memory_state
Get current memory status and statistics
manifold_step
Update memory along the manifold direction
prune_memory
Delete less relevant memories to free up space
save_checkpoint
Save memory status to file
load_checkpoint
Load memory status from file
reset_gradients
Reset the accumulated gradient to recover from training problems