code-review-graphLocal-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.
Why switchBoth compute a Tree-sitter-style call graph and blast-radius for agents; code-review-graph is a Python MCP with a persisted graph, ripwire is a single offline C++ binary that rebuilds in ~0.3s and adds tests-to-run and quality deltas.
Full comparison → gortexCode-intelligence engine in one static Go binary: tree-sitter graph over 257 languages, compiler-grade resolution for 17, multi-repo, 175 configurable MCP tools — up to 50x fewer tokens. 100% local.
Why switchSame shape — one static binary, tree-sitter graph, compiler-grade resolution, many languages — ripwire differentiates on change-oriented ranking (`--for`), published evals against graph-DB MCPs, and an explicit lineage of the metrics it uses.
Full comparison → codebase-memory-mcpCode intelligence MCP in pure C: tree-sitter knowledge graph over 158 languages, average repo indexed in milliseconds, sub-ms queries, 10x fewer tokens. Single static binary, zero deps.
Why switchBoth are dependency-free native (C vs C++23) code-graph servers for agents that index in milliseconds; codebase-memory-mcp is MCP-first, ripwire is CLI-first with MCP optional.
Full comparison → codegraph-mcpNo-train, on-prem code knowledge graph served to AI agents over MCP — symbols, call edges, cross-language links and blast-radius queries, with a hash-chained audit log of every read.
Why switchBoth serve a no-train, on-prem code knowledge graph to agents; ripwire is the no-server variant and explicitly benchmarks itself against graph-database code-context MCP servers on index time and memory.
Full comparison → tokensaveCode-intelligence MCP server for coding agents — a pre-indexed semantic graph (libSQL + FTS5) they query instead of grepping: symbols, callers, impact radius in one call. 100% local, 50+ languages.
Why switchSame goal — replace grep-and-read-whole-files with a pre-indexed graph query — but tokensave keeps a libSQL+FTS5 index behind an MCP server while ripwire recomputes per run with no store.
Full comparison → repowiseCodebase 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.
Why switchOverlaps on the quality lens: both score code health from McCabe/Halstead/churn-style signals; repowise is the deeper health product, ripwire only reports deltas around the change you are about to make.
Full comparison →