code-review-graph vs codeflow
Local-first code intelligence graph for AI coding tools: Tree-sitter AST graph + blast-radius analysis served over MCP, so agents read ~82x fewer tokens per review question. — versus — Paste a GitHub URL or drop a local folder → interactive architecture map in the browser: dependency graph, blast radius, health grade, security scan. Single index.html, zero install.
Both build a dependency graph with blast-radius analysis; codeflow renders it visually for humans with zero setup, code-review-graph serves a tree-sitter-accurate graph to AI agents over MCP.
| code-review-graph | codeflow | |
|---|---|---|
| Stars | 22k | 4.6k |
| Forks | 2.2k | 713 |
| Language | Python | HTML |
| License | MIT | — |
| Last activity | 2 days ago | 6 days ago |
| Topics | coding | coding |
| Curated connections | 4 | 3 |
code-review-graph — the curator's take
The rare benchmark-honest repo: it tells you the 528x number is the best case and its recall metric is circular. Install once, it configures 14 platforms (Codex, Claude Code, Cursor...). Reach for it on monorepos where review context is the token sink; skip on small repos where a grep costs less than the graph's own metadata.
codeflow — the curator's take
The fastest 'what am I looking at?' tool for an unfamiliar repo: zero install, code never leaves the browser, and blast-radius answers 'what breaks if I touch this?' before you refactor. The JSON export and README-card GitHub Action make it more than a toy. NOT compiler-grade: dependency edges come from lightweight in-browser parsing across 30+ languages, so trust it for orientation, not for exhaustive call-graph truth — agents needing tree-sitter-accurate graphs should use code-review-graph or codegraph-mcp. Big repos also eat GitHub API rate limits fast without a token.