Graph-Oriented Generation: Deterministic Context Retrieval for Code

See GOG, a deterministic system using code AST graphs to retrieve precise context for generation, contrasting with similarity-based methods. Witness live examples.

Overview

GOG (Graph-Oriented Generation) is a deterministic context-retrieval system for code generation: instead of embedding chunks and pulling them by similarity, it parses the codebase into an AST-derived graph and traverses it to assemble precise context for a prompt. Live, I’ll run the same prompt through Claude Code two ways — vanilla, and with GOG injecting context — and walk the full path from the initial prompt, through decomposing the project structure into stratum relationships, to the actual AST graph traversal that selects what the model sees. You’ll see the retrieval working, not a slide about it.

Links

https://github.com/dchisholm125/graph-oriented-generation
GOG maps repository graphs to optimize LLM context and boundaries.
https://derekchisholm.com/gog/
Derek Chisholm’s portfolio demonstrates graph-oriented generation research and engineering projects.

Tech stack

Claude Code

Anthropic's agentic coding tool: Unleash Claude's raw power directly in your terminal or IDE to turn complex, hours-long workflows into a single command.

Claude Code is Anthropic’s powerful agentic coding assistant, designed for high-velocity development. It operates natively within your terminal, IDE (VS Code, JetBrains), or via a web interface, allowing you to delegate complex tasks like feature building, bug fixing, and codebase navigation. The agent plans, edits files, executes commands, and creates commits, maintaining awareness of your entire project structure. Internally, Anthropic engineers using Claude Code reported a 67% increase in productivity, demonstrating its capacity to deliver significant gains for Pro and Max plan users.

https://claude.com/code

View projects
Claude Opus

Claude Opus: Anthropic's flagship large language model, delivering frontier intelligence for complex reasoning, advanced coding, and autonomous agentic workflows.

Claude Opus is Anthropic's most capable foundation model (LLM), setting the industry benchmark for complex reasoning, math, and coding. It achieves state-of-the-art results on key evaluations: Opus 4.1 scored 74.5% on SWE-bench Verified. The model features a massive 200,000-token context window (expandable to 1 million for specialized tasks), enabling deep, multi-file analysis and long-horizon agentic workflows. Deploy Opus for enterprise-grade automation, complex financial forecasting, or expediting R&D across critical sectors.

https://claude.ai/

View projects
Claude Sonnet

Claude Sonnet 4.5 is Anthropic's premier model: state-of-the-art for agentic coding, computer use, and complex, long-horizon workflows.

Claude Sonnet 4.5 is engineered for superior agentic performance, excelling in complex, multi-step workflows across coding, finance, and cybersecurity (e.g., achieving a 77.2% score on SWE-bench Verified). This model offers a powerful balance of speed and cost: it is priced at $3 per million input tokens and supports a massive 200,000-token context window. This capacity allows for sustained reasoning, with internal tests confirming the model maintains focus for over 30 hours on demanding tasks. It is available via the Claude API, Amazon Bedrock, and Google Cloud's Vertex AI, making it the top choice for developers building robust, production-ready AI agents.

https://claude.ai

View projects
tree-sitter

An incremental parsing library that builds concrete syntax trees and updates them efficiently during live editing.

Tree-sitter generates robust syntax trees using a C-based runtime and language-specific grammars. It supports over 40 languages (including Rust, JavaScript, and Python) to power features like syntax highlighting and code navigation in Neovim and GitHub. The engine handles syntax errors gracefully and re-parses modified code in O(log n) time. This efficiency ensures immediate feedback without blocking the main editor thread.

https://tree-sitter.github.io/tree-sitter/

View projects
NetworkX

NetworkX is the core Python package for creating, manipulating, and analyzing complex network structures.

NetworkX is the definitive Python library for graph theory and network analysis. It provides classes for multiple graph types (Graph, DiGraph, MultiGraph, MultiDiGraph), allowing users to model diverse systems: social, biological, or infrastructure networks. The package includes numerous standard graph algorithms, such as Dijkstra's shortest path, and functions for calculating key network measures (e.g., degree, clustering). It is highly flexible: nodes and edges can hold arbitrary data, like weights or time-series, making it a powerful, open-source tool for researchers and developers across scientific disciplines.

https://networkx.org

View projects