GitNexus
AIAn MCP-native engine that indexes any codebase into a knowledge graph of dependencies, call chains and execution flows so coding agents stop grepping.
GitNexus
An MCP-native engine that indexes any codebase into a knowledge graph of dependencies, call chains and execution flows so coding agents stop grepping.
About GitNexus
GitNexus is a code intelligence engine built on the premise that coding agents fail because they see files instead of the system. It parses every file with Tree-sitter across 13 languages and deterministically resolves imports, call chains, field types and return types, so a chain like user.address.getCity().save() resolves at every hop with no embedding guesswork — on the VS Code repository that is 262,322 symbols and 1,030,565 relationships in one graph. Leiden community detection then clusters those symbols into functional modules scored by cohesion, surfacing the auth core, billing engine and ingestion pipeline as discovered architecture rather than documentation. From there it answers the question that matters before an edit ships: change one function and GitNexus traces every downstream caller grouped by depth with confidence scores, and detect_changes maps a git diff onto affected execution flows. Repos can be grouped into one unified graph with cross-repo edges, so a breaking change in one microservice surfaces in every dependent one. Seven MCP tools expose all of this to Claude Code, Cursor, Codex, Windsurf, OpenCode and Antigravity. On the DeepSWE benchmark, letting the model walk resolved execution flows solved 68.4% of issues against 37.0% for the bare model, at $0.88 per fix versus $1.79 and 10.6% fewer steps.
Screenshots
Key Features
Use Cases
Frequently asked questions about GitNexus
What is GitNexus?
An MCP-native engine that indexes any codebase into a knowledge graph of dependencies, call chains and execution flows so coding agents stop grepping.
How does GitNexus work?
GitNexus works by combining Deterministic Symbol Resolution: Tree-sitter parsing resolves imports, call chains, field types and return types across the codebase with zero embedding guesswork, so multi-hop chains resolve exactly., Leiden Architecture Clustering: Community detection groups symbols into functional clusters scored by cohesion and modularity, revealing real module boundaries that no one wrote down., Blast Radius Analysis: Change a function and GitNexus lists every downstream caller grouped by depth with confidence scores, turning a one-line edit into a measured impact set., Git Diff Impact Mapping: detect_changes takes your uncommitted diff and maps it to the execution flows it affects before you commit., Cross-Repo Unified Graph: Group repositories into a single graph with cross-repo edges so a breaking API change surfaces in every consuming service. to help users with Agent Codebase Onboarding: Give a coding agent process-level answers about callers and execution flows instead of pages of file dumps, cutting tokens and steps., Pre-Merge Impact Review: Check the blast radius of a change across depth levels before opening the pull request, not during code review or in production., Microservice Change Safety: Query many repositories as one graph to see which downstream services a contract change will break., Legacy Code Comprehension: Use discovered clusters and resolved call chains to understand an undocumented system's real architecture., Safe Large-Scale Refactoring: Rename or restructure with the full set of resolved references in hand rather than trusting a text search..
What are the main features of GitNexus?
Key features include Deterministic Symbol Resolution: Tree-sitter parsing resolves imports, call chains, field types and return types across the codebase with zero embedding guesswork, so multi-hop chains resolve exactly., Leiden Architecture Clustering: Community detection groups symbols into functional clusters scored by cohesion and modularity, revealing real module boundaries that no one wrote down., Blast Radius Analysis: Change a function and GitNexus lists every downstream caller grouped by depth with confidence scores, turning a one-line edit into a measured impact set., Git Diff Impact Mapping: detect_changes takes your uncommitted diff and maps it to the execution flows it affects before you commit., Cross-Repo Unified Graph: Group repositories into a single graph with cross-repo edges so a breaking API change surfaces in every consuming service..
Who is GitNexus for?
GitNexus is useful for anyone interested in Agent Codebase Onboarding: Give a coding agent process-level answers about callers and execution flows instead of pages of file dumps, cutting tokens and steps., Pre-Merge Impact Review: Check the blast radius of a change across depth levels before opening the pull request, not during code review or in production., Microservice Change Safety: Query many repositories as one graph to see which downstream services a contract change will break., Legacy Code Comprehension: Use discovered clusters and resolved call chains to understand an undocumented system's real architecture., Safe Large-Scale Refactoring: Rename or restructure with the full set of resolved references in hand rather than trusting a text search..
How much does GitNexus cost?
GitNexus offers a free tier with paid plans for advanced features.
How do I get started with GitNexus?
Visit https://www.akonlabs.com to sign up and explore GitNexus.
Explore more AI Mcps tools
Browse all Mcps tools →Compare GitNexus: vs OzBrain · vs QApilot MCP for Android · vs Noodle Seed · vs Chrome DevTools MCP