Installation
Or add to your Cargo.toml:
[]
= "0.1"
Optional Features
# With HTTP server
# With GPU acceleration (macOS)
# With GPU acceleration (NVIDIA)
Server Binary
Basic Usage
use ;
async
Core Features
- Smart Compression: Intelligent content prioritization and compression to fit any token budget
- Multi-Format Support: PDF, images, text, code - all handled seamlessly with automatic extraction
- Priority System: Critical/High/Medium/Low/Minimal priority levels for fine-grained control
- Query-Based Filtering: LLM-powered relevance scoring to keep only what matters
- Vision Processing: Image analysis and description with GPU acceleration (Metal/CUDA)
- Semantic Chunking: Syntax-aware chunking for code and semantic boundaries for text
- Embedding Support: Vector-based similarity scoring for semantic retrieval
- Agent Memory: Cognitive-inspired memory architecture (Working/Episodic/Semantic)
- HTTP Server: REST API for language-agnostic integration
Documentation
For detailed documentation and examples, visit:
Contributing
Contributions are welcome! Please feel free to submit a Pull Request.
- Fork the repository
- Create your feature branch (
git checkout -b feature/amazing-feature) - Commit your changes (
git commit -m 'Add some amazing feature') - Push to the branch (
git push origin feature/amazing-feature) - Open a Pull Request
License
This project is licensed under the MIT License - see the LICENSE file for details.
Contact
Project Link: https://github.com/berkekiran/forgetless