Graft
Graft is an open-source context layer designed to optimize the efficiency and cost-effectiveness of AI coding agents, particularly when operating within large codebases. It addresses the challenge of context window limitations and high API costs by managing how code context is retrieved and injected into models like claude-code and openai models.
Key Features
- Context Optimization: Reduces the amount of irrelevant code sent to the LLM, lowering token usage and costs.
- Performance Improvement: Enhances the accuracy and speed of AI agents by providing more relevant, curated context.
- Compatibility: Designed to work seamlessly with major AI coding assistants.