Generate AI context files
from any codebase.

Checks whether Ollama is running and lists all locally installed models. If Ollama is missing, the interface shows the exact install command for your platform. A curated model reference table lets you compare and pull the right model before starting — ranked by quality, speed, and VRAM requirements.

Register one or more local project paths with an optional description. The description helps the AI understand the purpose of the codebase before it even starts reading files.

An intelligent algorithm examines your project structure and suggests which folders and file types are safe to exclude — node_modules, build artifacts, generated files. You review and confirm. Custom rules are remembered per project.

Choose the Ollama model from your installed list, set the analysis depth, and configure advanced options: Smart Update to skip unchanged files, and an optional file tree embedded in the output.

A live progress panel shows each file being processed, its markdown content appearing in real time, and a running log. If a file fails, retry it individually. Each result can also be edited safely from the UI — changes are saved to the cache and the output is rebuilt from there, never by re-reading your project files.