code-review-graph vs graphicle
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 — One Rust program giving coding agents a code graph plus memory of docs, decisions and past sessions, served over MCP to Claude Code, Codex, Cursor and VS Code.
Both build a local code graph for AI coding tools. code-review-graph focuses on review blast radius; Graphicle adds memory.
| code-review-graph | graphicle | |
|---|---|---|
| Stars | 33k | 509 |
| Forks | 3.0k | 36 |
| Language | Python | Rust |
| License | MIT | Apache-2.0 |
| Last activity | 8 days ago | yesterday |
| Topics | code-intel | code-intel, memory |
| Curated connections | 9 | 5 |
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.
graphicle — the curator's take
Use it when you want code intelligence and project memory from one local install instead of a code-graph MCP plus a separate memory server. Skip it if you already run a dedicated code graph you like, or need team-shared memory. Its memory comparison against seven systems is pre-release and self-reported.