iyaja/llama-fs
Llama Fs
llama-fs is an automated directory manager and file system organizer that uses large language models to categorize, rename, and sort files into structured directories. It functions as a local data pipeline that analyzes file content to determine appropriate folder hierarchies and naming patterns.
The project emphasizes privacy by routing data processing to local model instances, ensuring sensitive file information remains on the device rather than being sent to cloud providers. It utilizes multimodal analysis to process images, audio, and text, allowing the system to identify and classify diverse media types for automatic organization.
The system includes real-time filesystem monitoring to detect directory changes and trigger automated cleanup tasks. It supports batch processing for restructuring entire directory trees in a single operation and recursive directory synthesis to automatically create nested folder hierarchies.
Features
- Automated File Organizers - Ships an automated file organizer that monitors directory changes and replicates organization patterns.
- Privacy-Preserving Pipelines - Provides a privacy-focused workflow routing file analysis to local model instances instead of cloud providers.
- Multimodal Content Classifiers - Processes images and audio through specialized models to identify content for automated sorting.
- Content-Based Organizers - Renames and sorts files into structured folders by analyzing internal text via language models.
- File System Organizers - Uses large language models to analyze file text and determine appropriate folder structures and filenames.
- Private File Managers - Uses local Llama 3 instances to organize sensitive documents without routing data to cloud providers.
- Automated Directory Monitoring - Provides automated directory monitoring to relocate files based on analyzed content and naming patterns.
- Local-First Tool Processing - Utilizes local-first tool processing to route AI requests to local model instances for data privacy.
- Hierarchical Organizers - Analyzes unstructured data to create logical folder hierarchies and move files into appropriate locations.
- Filesystem Change Monitors - Provides real-time filesystem change monitors to trigger automated organization and cleanup workflows.
- Multimodal Analysis Tools - Employs multimodal analysis tools to identify and classify image and audio content for automated sorting.
- Multimodal Classification - Implements multimodal classification to identify the purpose and destination of images and audio files.
- File Renaming and Relocations - Implements file renaming and relocations to move files and automatically create missing directory structures.
- Recursive Directory Managers - Includes recursive directory managers to automatically synthesize nested folder hierarchies based on model suggestions.
- Local Data Processing - Directs data processing to local model instances to ensure sensitive file data remains on the device.
- Batch File Operations - Implements batch file operations to apply structural mapping across entire directory trees in a single pass.
