Tagged articles
Tree-Sitter
21 articles · Page 1 of 1
The author tests Graphify, an open-source tool that builds code knowledge graphs for AI coding agents, on the httpx repository, demonstrating 2-second graph builds, 95% token reduction for navigation queries, and practical limitations like name ambiguity between code and documentation.
AI coding agentsTree-Sittercode-navigation
0 likes · 8 min read

CodeGraph uses Tree-Sitter to parse code into a local SQLite knowledge graph, accessed via MCP by AI agents like Claude Code and Cursor, reducing tool calls by 70% and token costs by nearly half while keeping code private on the developer's machine.
AI coding assistantsCodeGraphMCP
0 likes · 10 min read

Graphify builds code knowledge graphs using Tree-sitter AST parsing across 40 languages, enabling coding agents to traverse call, import, and inheritance relationships via query/path/explain commands; on a 1M-line ERPNext repo, adding Graphify raised key fact coverage from 70.8% to 82.0% with similar token cost, though limited to 6 test questions and static analysis gaps remain.
ASTCoding AgentERPNext
0 likes · 19 min read

The article argues that AI coding in legacy systems fails due to missing cross-module context, proposing a queryable repository knowledge layer that links code structure, business rules, and engineering conventions via graph-structured retrieval, and validates its trade-offs through dependency misuse, defect escape, and graph accuracy metrics.
AI codingSCIPTree-Sitter
0 likes · 13 min read

Graphify builds queryable knowledge graphs from codebases using local tree-sitter parsing for code and LLMs for docs, enabling AI assistants to traverse real code relationships via query, path, and explain commands, with benchmark results showing 0.497 recall@10 on LOCOMO versus 0.048 for mem0.
AI coding assistantLOCOMO benchmarkTree-Sitter
0 likes · 9 min read


Geek LabsSep 18, 2026 · Artificial Intelligence
Graft builds a local Markdown knowledge graph for AI coding agents, replacing embedding-based retrieval with deterministic structural analysis and optional LLM semantic layers, auto-refreshing on each query to cut token usage by 42% and improve SWE-bench scores by 12 percentage points.
AI coding agentsGraftLLM
0 likes · 13 min read

Graphify uses tree-sitter AST parsing to generate queryable code knowledge graphs with confidence-labeled edges, community detection, and God node identification, enabling offline architecture governance for legacy Java and microservices without vector databases or LLM tokens.
AST parsingJavaTree-Sitter
0 likes · 10 min read


Geek LabsSep 14, 2026 · Artificial Intelligence
roam-code builds a local SQLite code graph using tree-sitter for 28 languages, letting AI agents query precise call relationships instead of grep or RAG, reducing agent turns by 83%, tokens by 80%, and cost by 63% in experiments, while adding deterministic pre-edit context injection and post-edit verification gates.
AI coding agentsMCPSQLite
0 likes · 16 min read

code-review-graph builds a local AST‑based knowledge graph with Tree‑sitter, exposes MCP query tools to AI editors, and in benchmark tests reduces token consumption by up to 82 times while raising review quality scores from 7.2 to 8.8, especially for large monorepos.
AI code reviewMCP ProtocolSQLite
0 likes · 16 min read

CodeGraph, a local‑first code intelligence tool for AI programming assistants, builds a searchable knowledge graph with tree‑sitter and SQLite, cutting tool calls by 71%, token usage by 57% and task time by 46% while keeping data private and requiring only a few minutes to install and use.
AI programmingCodeGraphMCP
0 likes · 16 min read

The article compares two popular code‑knowledge‑graph projects, Understand Anything and CodeGraph, explaining why such tools are needed in the AI‑coding era, detailing their installation, core architecture, supported features, ideal use cases, and offering a practical guide on which one to adopt first.
AI coding toolsCodeGraphLLM
0 likes · 17 min read


JavaGuideJun 8, 2026 · Artificial Intelligence
CodeGraph builds a local code knowledge graph with tree‑sitter and SQLite, allowing Claude Code, Codex and similar AI tools to query a pre‑indexed graph instead of repeatedly scanning files, which the author’s benchmarks show reduces token consumption by 59%, cuts cost 35%, speeds responses by 49% and improves routing detection for many web frameworks.
AI code toolsCodeGraphLLM token reduction
0 likes · 11 min read

The article reviews ten open‑source utilities that dramatically reduce token consumption for AI coding assistants—cutting up to 80% of Claude Code tokens, saving hundreds of dollars, and shrinking large‑project token usage by as much as 49‑fold through output compression, command‑log filtering, and selective code‑base context.
AI codingClaude CodeRust
0 likes · 14 min read

The article explains why AI coding tools need a persistent code map, describes how the open‑source code‑review‑graph parses a repository into a SQLite‑backed graph of functions, classes, imports and tests, and shows step‑by‑step how to expose this graph to Claude Code via MCP for faster, context‑aware code review.
Claude CodeMCPTree-Sitter
0 likes · 17 min read


Geek LabsMay 4, 2026 · Artificial Intelligence
GitNexus is an open‑source tool that indexes any code repository into a searchable knowledge graph, enabling AI agents to understand code structure through a CLI‑MCP mode or a web UI, and it differentiates itself from DeepWiki by focusing on deep structural analysis and tool‑use hooks.
AI agentsGitNexusMCP
0 likes · 5 min read

CodeFlow is a browser‑only tool that, with just one HTML file, visualizes a project's dependency graph, calculates the explosion radius of code changes, identifies code owners, runs security scans, and exports detailed reports, all without installing software or uploading source code.
D3.jsGitHubTree-Sitter
0 likes · 11 min read

Tree-sitter is a high‑performance incremental parsing library that supports over 50 languages; the article explains its core features, typical use cases such as editor syntax highlighting and static analysis, and walks through a concrete multi‑language SQL extraction implementation in Java, Python, and XML.
JavaPythonSQL extraction
0 likes · 6 min read

This article walks you through building a personalized code editor by installing prerequisites, setting up Neovim 9.0+, adding Tree‑sitter, ripgrep, lazygit, and finally cloning and configuring AstroNvim on Ubuntu, with detailed commands and backup tips.
AstroNvimIDE setupLinux
0 likes · 6 min read

The article reverse‑engineers GitHub Copilot’s VSCode extension, detailing how its webpack‑bundled JavaScript is unpacked, its registerGhostText entry point identified, and its prompt‑building, multi‑layer caching, debouncing, and Jaccard‑based similarity mechanisms operate, offering insights into AI‑assisted code completion design.
AI programming assistantGitHub CopilotJaccard similarity
0 likes · 31 min read

This guide introduces Helix, a modern Rust‑written terminal text editor that leverages Tree‑sitter for fast syntax highlighting and multiple‑selection editing, and provides step‑by‑step instructions for installing it on Arch‑based systems via AUR or on other Linux distributions using Cargo.
HelixLinuxRust
0 likes · 4 min read


phodalJun 29, 2021 · R&D Management
Guarding is a Rust‑based, multi‑language architecture‑guard tool that lets you write readable DSL rules to enforce architectural constraints in Java, JavaScript, Rust, Go and more, using Tree‑sitter for parsing, pest for grammar, and a simple CLI that can be integrated via Git hooks, CI pipelines, or editor plugins.
DSLRustTree-Sitter
0 likes · 7 min read
