Download
LLM-TLDR is a Python-based tool designed to dramatically reduce the amount of code a large language model needs to read by extracting the essential structure and context from a codebase and presenting only the most relevant parts to the model. Traditional approaches often dump entire files into a model’s context, which quickly exceeds token limits; LLM-TLDR instead indexes project structure, traces dependencies, and summarizes code in a way that preserves semantic relevance while shrinking input size by up to 95 %. This makes queries and analysis much faster and cheaper, with dramatic token savings and latency improvements for LLM-driven development workflows. The project supports multiple programming languages and includes utilities for warming an index and then generating LLM-ready contexts or summaries of specific parts of a project.
Features
- Structural code context extraction for LLMs
- Up to ~95 % reduction in tokens needed
- Dependency and structure tracing
- Faster LLM queries with less latency
- Supports many programming languages
- Ready-to-use CLI and indexing workflows
Project Samples
