Shashank Shekhar Singh
Shashank Shekhar Singh is an individual ML engineer and open-source developer, not a company. He builds CodeGraphContext, an open-source code-intelligence engine that indexes repositories into semantic knowledge graphs so developers and AI assistants can query calls, imports, inheritance, dependencies, and other structural relationships through a CLI, MCP server, or HTTP API.
At a Glance
- Software developers and maintainers of complex codebases
- Teams using AI coding assistants or agentic IDEs
- Open-source project contributors and maintainers
- Organizations needing repository-wide code navigation, dependency analysis, and refactoring context
- +1 more
AI Tools by Shashank Shekhar Singh
(1)CodeGraphContext
Code Graph MCP Server for AI
Discussions
No discussions yet
Be the first to start a discussion about Shashank Shekhar Singh
Latest News
CodeGraphContext v0.5.7 released with broad parser-correctness and query/indexing fixes
CodeGraphContext v0.5.6 released with LadybugDB visualizer, security, Java query, and test improvements
CodeGraphContext v0.5.5 released with indexing, parser, MCP-over-SSE, query-safety, and bundle fixes
Singh published 'Coding specifically for the Love of Structure: Why I Built CodeGraphContext,' describing the project's motivation, CLI, MCP, visualization, and bundles
Products & Services
Open-source CLI toolkit and MCP server that parses source repositories with Tree-sitter and optional SCIP indexers, resolves symbols and relationships into a queryable property graph, and exposes the result to developers and AI assistants. It is distributed as the codegraphcontext Python package under the MIT License.
Market Position
CodeGraphContext positions itself as a graph-based structural code-understanding layer rather than a conventional text-search or code-completion tool. Its official comparison frames it as complementary to or more structurally aware than assistants such as GitHub Copilot and Cursor, with emphasis on multi-hop dependency tracking, cross-repository navigation, explainability, and graph-database scaling; its practical alternatives include RAG-over-code tools, IDE code search, and other Neo4j- or graph-backed code-analysis MCP servers.
Leadership
Founders
Shashank Shekhar Singh
Mechanical Engineering B.Tech student at IIT (BHU) Varanasi (2022–2026), ML engineer/open-source developer; his public portfolio lists internships or programs with American Express, Google Summer of Code/HumanAI, Summer of Bitcoin, Linux Foundation LFX, Code for GovTech, and Blue Yonder. He is the author and active maintainer of CodeGraphContext under GitHub handle Shashankss1205.
Executive Team
Shashank Shekhar Singh
Creator and Lead Maintainer, CodeGraphContext
IIT (BHU) Mechanical Engineering student and ML engineer/open-source developer. His public profiles identify him as the author/maintainer of CodeGraphContext and list experience with American Express, HumanAI through GSoC, Summer of Bitcoin, Linux Foundation LFX, Code for GovTech, and Blue Yonder.
Founding Story
Singh describes CodeGraphContext as a passion project started because conventional AI coding assistants treated source code primarily as text and lacked a reliable model of code structure. During his 2025 Summer of Bitcoin work, he developed the idea into a graph-based engine using AST parsing, graph databases, and MCP so developers and AI agents could trace call chains, dependencies, and architecture rather than rely on fuzzy text search.
Business Model
Revenue Model
CodeGraphContext is an MIT-licensed open-source project distributed through GitHub and PyPI. Public project pages show a GitHub Sponsors option; no commercial subscription, API-usage pricing, or paid license model was identified.
Target Markets
- Software developers and maintainers of complex codebases
- Teams using AI coding assistants or agentic IDEs
- Open-source project contributors and maintainers
- Organizations needing repository-wide code navigation, dependency analysis, and refactoring context
- Researchers and developers building MCP-based coding tools
- Tracing direct and indirect call chains in large repositories
- Understanding imports, module boundaries, class hierarchies, and dependencies
- AI-assisted code explanation and repository-aware coding
- Context-aware refactoring and impact analysis
- Dead-code, hotspot, and unexpected-dependency detection
- Interactive architecture exploration and visualization