code-review-graph vs repowise
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 — Codebase intelligence for AI and humans: deterministic code-health scores calibrated on real defects, graph-aware refactoring plans agents can execute, auto-docs and git analytics over 9 MCP tools.
Both build deterministic code intelligence over MCP; repowise scores health and plans refactors, code-review-graph computes the minimal read-set for a change.
| code-review-graph | repowise | |
|---|---|---|
| Stars | 21k | 3.7k |
| Forks | 2.1k | 438 |
| Language | Python | Python |
| License | MIT | AGPL-3.0 |
| Last activity | yesterday | 4 days ago |
| Topics | coding | coding |
| Curated connections | 4 | 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.
repowise — the curator's take
The interesting bet: defect-risk scoring with NO LLM — 25 deterministic markers calibrated against a real defect corpus (published ROC AUC 0.74), indexed in seconds, then the same dependency graph generates concrete refactoring plans (split the god class, break the cycle) your coding agent executes. Health→locate→fix as one loop is what linters and dashboards don't do. NOT a pure-open play: AGPL-3.0 with a hosted-teams funnel, and benchmark claims are self-published — reproduce them on your repo before quoting them; overlaps only partially with symbol-level code-graph MCPs.