Code Trajectory FAQs

Question 1

What does 'Flow Awareness' mean for LLMs using Code Trajectory?

Accepted Answer

'Flow Awareness' means LLMs don't just see the current state of your code, but also its evolution and the 'vector' of changes. Functions like `get_file_trajectory` narrate file history, and `get_global_trajectory` reveals ripple effects across your project, aiding in deeper contextual understanding.

Question 2

Can I control the granularity and intent of the tracked history?

Accepted Answer

Yes. You can explicitly record your coding intentions (e.g., 'Refactoring Auth system'), tagging subsequent snapshots with this goal. Additionally, a `consolidate` feature allows you to clean up noisy trial-and-error edits into clear, meaningful history checkpoints.

Question 3

What is Code Trajectory and what problem does it solve?

Accepted Answer

Code Trajectory provides Large Language Models (LLMs) with a persistent memory of your coding history. It solves 'New Session Amnesia' by enabling LLMs to retain context, momentum, and architectural intent across multiple chat sessions, eliminating the need to re-explain past work.

Question 4

Is Code Trajectory compatible with popular AI development environments?

Accepted Answer

Yes, Code Trajectory integrates as a Model Context Protocol (MCP) server. It's designed to be configurable with popular AI clients and editors such as Claude Desktop, VSCode, Cursor, and Windsurf, enabling seamless integration into your workflow.

Question 5

How does Code Trajectory track my code history without polluting my main Git repository?

Accepted Answer

It automatically creates 'shadow snapshots' as micro-commits in a hidden `.trajectory` Git repository whenever you save a file. This ensures your main project's Git history remains clean and focused on major changes, while providing granular history for the AI.

Code Trajectory

Code Trajectory

Características Principales

Casos de Uso

Características Principales

Casos de Uso