mlsanityData to 14 Oct 2026

TypeScript Repository Indexing for Code Agent Retrieval

arXiv 2604.18413 ↗First posted 20 Apr 2026cs.SEcited by 2

Not on the map. Why?

Abstract (arXiv)

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. 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

Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). First posted on arXiv 20 Apr 2026.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 2.

2 papers.

Similar, not cited

Close in wording, no citation either way

  1. 2026OwlPath: Lossless Knowledge Compression for LLM Bug Repair
  2. 2024CodexGraph: Bridging Large Language Models and Code Repositories via Code Graph Databases
  3. 2025RANGER -- Repository-Level Agent for Graph-Enhanced Retrieval
  4. 2026LARGER: Lexically Anchored Repository Graph Exploration and Retrieval
  5. 2026CODESTRUCT: Code Agents over Structured Action Spaces
  6. 2026Codebase-Memory: Tree-Sitter-Based Knowledge Graphs for LLM Code Exploration via MCP
  7. 2025SpIDER: Spatially Informed Dense Embedding Retrieval for Software Issue Localization
  8. 2025SWE-PolyBench: A multi-language benchmark for repository level evaluation of coding agents