Score8.1
Popularity117.0
Risknone
TierGold
Score breakdown
Usefulness9.0
Novelty8.0
Momentum7.0
Maturity8.8
Open-source/build8.4
Evidence8.0
Workflow potential9.2
Setup ease6.4
Popularity is tracked separately. Support, ads, sponsorships, and tips never affect these signals.
Why it matters
Useful for AI coding-agent power users (Claude Code, Codex, OpenCode, Cursor, Zed, Antigravity, Aider, KiloCode, Kiro) who hit bugs in upstream `DeusData/codebase-memory-mcp` and want a fork that already integrates the fixes — this fork cherry-picks 11 upstream-pending PRs (incremental-reindex preserves inbound CALLS edges, Cypher aggregation groups by non-aggregate function, `detect_changes` hono
Who should use it
AI coding-agent power users (Claude Code, Codex, OpenCode, Cursor, Zed, Antigravity, Aider, KiloCode, Kiro) who hit bugs in upstream `DeusData/codebase-memory-mcp` and want a fork that already integrates the fixes — this fork cherry-picks 11 upstream-pending PRs (incremental-reindex preserves inbound CALLS edges, Cypher aggregation groups by non-aggregate function, `detect_changes` honors `since`, libgit2 ≥ 1.8 build fix, JSON control-character escaping, ADR preservation across re-index, stack-buffer-overflow fix in `append_args_json`, and more)AI agent authors who want a single-call `explore` MCP tool that returns blast-radius + nearby-neighbors + verbatim line-numbered source grouped by file — this fork's headline agent-native addition, designed so an agent reads like a `Read` rather than chaining 5-8 graph queriesEngineering teams that need transitive blast-radius from `detect_changes` — the `depth` parameter produces a caller blast radius with `impacted_symbols` tagged `hop` + `transitive` and a deduped `impacted_count`Swift-heavy codebases — `struct`/`enum`/`actor` are distinct graph labels (`Struct`/`Enum`/`Actor`) instead of all being lumped as `Class`, Swift enum cases are distinct `EnumCase` nodes (including multi-name `case a, b, c` lines), and an `enum`'s `static func`s are no longer double-emitted as both a Method and a Function nodeEngineering teams that need Hybrid LSP coverage — upstream integrates Hybrid LSP semantic type resolution for Python / TypeScript / JavaScript / JSX / TSX / PHP / C# / Go / C / C++ / Java / Kotlin / Rust, ships 158 tree-sitter grammars vendored in, ships 14 MCP tools, supports 11 coding agents with auto-detect (Claude Code, Codex CLI, Gemini CLI, Zed, OpenCode, Antigravity, Aider, KiloCode, VS Code, OpenClaw, Kiro)Kernel-scale indexable codebases — upstream full-indexes the Linux kernel (28M LOC, 75K files) in 3 minutes and answers structural queries in under 1 msInfrastructure-as-code heavy stacks — upstream indexes Dockerfiles / Kubernetes manifests / Kustomize overlays as graph nodes with cross-references (`Resource` nodes for K8s kinds, `Module` nodes for Kustomize overlays with `IMPORTS` edges)Engineering teams evaluating research vs production — upstream's design and benchmarks are in arXiv:2603.27277 (83% answer quality, 10× fewer tokens, 2.1× fewer tool calls vs file-by-file exploration across 31 real-world repositories)Evaluation: `./scripts/build.sh` builds the integrated binary (first build compiles all 158 vendored tree-sitter grammars, a few minutes), `make -j -f Makefile.cbm cbm` is the fast iterative rebuild path, `cp build/c/codebase-memory-mcp ~/.local/bin/ && claude mcp add codebase-memory -s user -- ~/.local/bin/codebase-memory-mcp` is the install path; do NOT run the binary's `update` subcommand (it pulls upstream release and overwrites the integrated build)
Who should skip it
Move on from win4r/codebase-memory-mcp-pro if the licensing terms, language support, or platform requirements do not fit your project.
About this signal
win4r/codebase-memory-mcp-pro is tracked by RepoRadar as a community fork of codebase-memor in the MIT community fork of `DeusData/codebase-memory- section. It was first seen on 2026-06-25 and last updated on 2026-06-25. The current verdict is 'try now' with a Gold tier and moderate setup difficulty. Across RepoRadar's eight signals, win4r/codebase-memory-mcp-pro is strongest on workflow potential (9.2) and practical usefulness (9.0) and weakest on setup ease (6.4) — a profile worth weighing against your own priorities. This page summarizes the evidence RepoRadar has captured from captured source metadata. The score, tier, risk label, and verdict on this page are never influenced by sponsorship, ads, or tips — they reflect only the usefulness, popularity, novelty, momentum, maturity, and evidence signals described in the RepoRadar methodology.
How this item is evaluated
RepoRadar assigned win4r/codebase-memory-mcp-pro a composite score of 8.1 out of 10, placing it in the Gold tier. This score combines weighted sub-signals: usefulness (35%), novelty (18%), momentum (14%), maturity (10%), open-source/build quality (7%), evidence quality (6%), workflow potential (6%), and setup ease (4%). Popularity is tracked separately at 117.0 and never affects the composite score or tier. The risk label of 'none' reflects inherent user-impacting hazards, not generic novelty. Items with no risk flag may still require normal code review before production use.
Risk explanation
No inherent user-impacting risk is flagged from the captured evidence.
Evidence links
Closest alternatives / related signals
codebase-memory-mcp-prowin4rcodebase-memory-mcpdeusdatacode-intelligenceknowledge-graphtree-sitter158-grammars
