Skip to main content
BugViper connects to your GitHub repositories, parses every function, class, file, and import into a Neo4j knowledge graph, then sends a LangGraph-powered AI agent to review your pull requests — posting inline comments on the exact lines where bugs, security issues, and code quality problems were found. Alongside automated reviews, BugViper exposes the same graph through a full-text and semantic code search interface and an AI chat agent that can answer natural language questions about your codebase.

Three core capabilities

PR reviews

Comment @bugviper review on any pull request to trigger an inline AI review. The agent explores the knowledge graph for context — call chains, class hierarchies, cyclomatic complexity — before flagging bugs and security issues on the exact diff lines.

Code search

Search your entire indexed codebase by symbol name, file content, or natural language intent. Full-text search is backed by Apache Lucene inside Neo4j; semantic search uses cosine similarity over 1536-dimension embeddings.

Ask Agent

Ask the AI chat agent natural language questions about your codebase. It reasons across 19 Neo4j tools, cites the source files it used, and shows relevant code inline — without you needing to know Cypher.

The knowledge graph model

When you index a repository, BugViper runs Tree-sitter parsers across every source file and writes the result into Neo4j as a property graph. Each entity in your code becomes a node, and the connections between them become typed relationships:
Node typeWhat it represents
RepositoryThe top-level repository being indexed
FileA source file (path, language, raw content)
FunctionA function or method, including its source and cyclomatic complexity
ClassA class definition with its member functions
VariableModule-level or class-level variable declarations
ModuleAn imported package or module
Relationships between nodes — CONTAINS, DEFINES, CALLS, IMPORTS, INHERITS — let the review agent trace call chains, check blast radius, and understand inheritance before it writes a single comment. BugViper calculates cyclomatic complexity for every function at parse time, so the agent can prioritize high-risk areas automatically.

Supported languages

BugViper parses 17 programming languages via Tree-sitter, including Python, TypeScript, JavaScript, Go, Rust, Java, C++, and more. See the full language list.

Ready to get started?

The quickstart walks you through indexing your first repository and triggering an AI pull request review in four steps.
Follow the quickstart to install the GitHub App, configure your environment, index a repository, and trigger your first review.