OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
Coding Agents

Code Review Graph

A Python developer tool that builds and incrementally updates a Tree-sitter-based code knowledge graph, then serves focused review context through MCP and a CLI.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Code Review Graph — OpenViST project profile in Coding Agents.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use it when an AI coding workflow needs targeted repository context rather than repeated broad codebase rereading, especially during reviews or large-repository work.

Who it is for

  • Developers using MCP-compatible AI coding tools.
  • Teams reviewing or exploring large repositories.
  • Engineers building local code-aware AI workflows.

Documented uses

  • Map structural relationships among repository code elements.
  • Provide AI tools with focused files and symbols for a review.
  • Keep repository context updated incrementally through hooks and watch mode.
  • Configure supported AI coding tools with MCP integration.
Before you choose

Requirements & limits

The documented setup is local and self-hosted, uses a CLI, requires Python 3.10+, and identifies the project as MIT-licensed.

  • Whether the target AI coding tool is among the platforms supported by the installer.
  • Whether a local Tree-sitter graph and MCP workflow fits the development environment.
  • Repository size and resulting build time.
  • How the workflow should handle files that fail to parse and produce partial graph results.
  • Whether incremental hooks and watch mode are useful for keeping context current.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Install and build a local review graph

Set up Code Review Graph for an AI coding tool and create the repository graph.

Before you start

  • Python 3.10 or newer.
  • A local Git or SVN working tree.
  • An AI coding tool supported by the documented installer.

Steps

  1. Install the package with pip or pipx.

  2. Run code-review-graph install to detect installed AI coding tools and configure them.

  3. Run code-review-graph build to parse the codebase.

  4. Open the project and ask the assistant to build the code review graph for the project.

Expected outcome

The repository has a persistent structural graph that can provide targeted context through MCP.

Guide limitations

  • Build time scales with repository size.
  • Files that fail to parse produce a partial result and retain their previous graph rows.
  • The editor or AI coding tool must be restarted after installation.
Documentation 1 ↗
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
1 October 2026
Original website title
tirth8205/code-review-graph · Official homepage title · retained in its source language
How we review sourcesSuggest a correction