Snarky Squirrel
Automated pull-request reviewer that runs a multi-agent LangGraph pipeline, scores code quality and security findings on a 0β10 scale, and optionally posts a structured review comment to GitHub. Built on AWS Bedrock (Claude Haiku), DynamoDB, FastAPI, and Cognito auth.
Sample Output
Agent Pipeline
Supervisor
Routes the pipeline and decides agent execution order via the LLM.
Security Agent
Scans the PR diff for vulnerabilities. Runs first.
Code Quality Agent
Checks style, complexity, and best practices using prior findings.
PR Reviewer Agent
Produces a holistic review reading all prior findings.
Summary Agent
Aggregates all findings into a scored report and lineage trace.
Score Formula
score = 10 β (CRITICAL Γ 5 + HIGH Γ 2 + MEDIUM Γ 1 + LOW Γ 0.5)
A CRITICAL finding sets should_block = true.
Setup
Features
Links
Questions, issues, or ideas β open a GitHub issue or reach out directly.