Matryoshka

Acerca de

Matryoshka empowers large language models (LLMs) to analyze documents vastly exceeding their context windows without traditional RAG or chunking methods. It employs a Recursive Language Model (RLM) approach where the LLM reasons about a query and outputs constrained symbolic commands in the Nucleus DSL. These commands are then executed safely by the Lattice logic engine, which features a robust parser, type inference, and a miniKanren-based solver. A key innovation is its handle-based, in-memory SQLite storage, providing over 97% token savings by presenting LLMs with compact references instead of full data, making it exceptionally efficient for complex and voluminous analysis tasks.

Características Principales

• 62 GitHub stars
• Recursive Language Model (RLM) Architecture: Processes documents far larger than LLM context windows using symbolic commands and a logic engine.
• Nucleus DSL for Safe Execution: Utilizes a constrained S-expression language for LLM outputs, ensuring parseable, type-checked, and safely executable commands.
• Structured Code Analysis: Integrates Tree-sitter for code-aware queries, enabling symbol listing, body extraction, and reference finding across 20+ languages.
• MCP Server for Agent Integration: Provides a Model Context Protocol server (`lattice-mcp`) allowing coding agents to perform efficient, chained document and code analysis.
• Token-Efficient Handle-Based Storage: Achieves 97%+ token savings by storing results in an in-memory SQLite and providing LLMs with compact data handles.

Casos de Uso

• Analyzing extensive reports, log files, or legal documents that exceed typical LLM context limits.
• Empowering AI coding agents to efficiently query and understand large codebases for tasks like refactoring or debugging.
• Performing complex data aggregation and filtering on large datasets without vector databases or manual chunking.