Tree-sitter

ast-grep is a fast, polyglot command-line and programmatic tool for structural code search, linting, and rewriting at scale. It matches code patterns against abstract syntax trees, allowing users to locate and modify code across thousands of files, run customized AST-based lint rules with structured error reporting, and use interactive codemods. It supports many programming languages, can load custom tree-sitter parsers, and provides Node.js bindings for programmatic syntax-tree traversal.

Code-Graph-RAG is an open-source retrieval-augmented generation system for querying, understanding, and editing multilingual codebases. Its Tree-sitter-based parser extracts functions, classes, methods, modules, and relationships, then stores them in Memgraph under a unified graph schema. An interactive CLI converts natural-language questions into Cypher queries, retrieves source code by name or intent, and supports AI-assisted editing and optimization. It provides AST-based surgical patches with diff previews, structural search and rewriting through ast-grep, dead-code discovery by traversing call and reference edges, and runtime-call overlays from test traces or production eBPF profiles. The project also supports MCP integration and publishes the `cgr` command-line tool to PyPI.

TypeScript is a programming language developed by Microsoft as a superset of JavaScript. It adds optional static types for application-scale JavaScript and compiles to readable, standards-based JavaScript for browsers, hosts, and operating systems. The compiler is distributed through npm, with stable and nightly builds, and the project provides a browser-based playground, documentation, roadmap, and community resources.

Agent Context Workshop is a hands-on workshop resource for building and evaluating context layers for coding agents. It uses selected crates from the Qdrant Rust codebase to extract syntax with tree-sitter, resolve symbols and relationships with rustdoc JSON, store the resulting code knowledge graph in Neo4j, and expose graph tools such as search, blast-radius analysis, and implementor lookup to an agent. The workshop compares graph-based agents with grep-style agents using gold-verified questions, deterministic scoring, cached evaluation results, tool-adoption measurements, and trace inspection. Additional notebooks cover static Python resolution with Griffe and an optional Fenic-and-LLM semantic layer. The GitHub repository maintains the workshop through ordered Jupyter notebooks, typed extraction and graph code, evaluation harnesses, tests, committed Qdrant seed data, and a committed evaluation cache; it is licensed under Apache-2.0.

An open-source Microsoft codebase whose merged fix pull requests were used to construct an evaluation dataset for comparing agentic and vector search in a coding-agent task.