TypeScript Repository Indexing for Code Agent Retrieval

2026-04-20

AI Summary

This work addresses the performance bottlenecks of existing Language Server Protocol (LSP)-based code parsing approaches in large-scale TypeScript projects, where frequent symbol queries hinder efficient function-level indexing. To overcome this limitation, we propose abcoder-ts-parser, which uniquely integrates the native capabilities of the TypeScript Compiler API directly into the indexing pipeline. By leveraging the compiler’s abstract syntax tree (AST), semantic information, and module resolution logic, our method constructs a graph-structured index—UniAST—that preserves call chains and dependency relationships. Experimental evaluation on three open-source projects, including one with up to 1.2 million lines of code, demonstrates that abcoder-ts-parser substantially outperforms conventional LSP-based architectures, achieving significant improvements in both indexing efficiency and reliability.

Technology Category

• Natural Language Processing: Code Generation / Program Synthesis from Natural Language
• Cognitive Modeling & Cognitive Systems: Symbolic Representations
• Machine Learning: Large Multimodal Models (LMMs)

Application Category

• Graph Algorithms and Modeling for the Web: Querying, indexing, and retrieval in Web-related graphs
• Search and Retrieval-Augmented AI: Web crawling and indexing
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions

Abstract

Graph-based code indexing can improve context retrieval for LLM-based code agents by preserving call chains and dependency relationships that keyword search and similarity retrieval often miss. ABCoder is an open-source framework that parses codebases into a function-level code index called UniAST, but its existing parsers combine lightweight AST parsers for syntactic analysis with language servers for semantic resolution, but because LSP-based resolution requires a JSON-RPC call for each symbol lookup, these per-symbol calls become a bottleneck on large TypeScript repositories. We present abcoder-ts-parser, a TypeScript parser built on the TypeScript Compiler API that works directly with the compiler's AST, semantic information, and module resolution logic. We evaluate the parser on three open-source TypeScript projects with up to 1.2 million lines of code and find that it produces reliable indexes significantly more efficiently than the existing architecture. For a live demonstration, watch: https://youtu.be/ryssr7ouvdE

Problem

• TypeScript
• code indexing
• language server protocol
• symbol resolution
• performance bottleneck

Innovation

• TypeScript Compiler API
• code indexing
• semantic resolution
• LLM-based code agents
• graph-based retrieval