Lobsters is a community-driven platform for sharing and discussing links to articles, tutorials, and projects related to technology and programming. Readers can learn about a wide range of topics, from software development and system administration to cybersecurity and artificial intelligence. With user submissions, comments, and voting, Lobsters provides a platform for collaborative learning and knowledge sharing among technology enthusiasts.

Lobsters

Matryoshka is a document analysis tool that reduces LLM token usage by 80% through recursive analysis and caching. Instead of repeatedly sending entire codebases to the LLM, it treats documents as external environments that can be queried incrementally. The tool uses a declarative S-expression query language (Nucleus) and stores results server-side, sending only metadata and aggregated answers to the LLM context. A hybrid approach combining direct reads of small files with Matryoshka queries for large files achieves 82% token savings while maintaining full coverage. The system integrates with AI agents via the Model Context Protocol and includes program synthesis capabilities for custom parsing tasks.

(iterate think thoughts): Stop Round-Tripping Your Codebase: How to Cut LLM Token Usage by 80% Using Recursive Document Analysis

Real-World Example: Analyzing anki-connect