Opinionated PHP code-quality analyzer that scores findings across quality pillars and emits reports for terminals, CI, SARIF, HTML, and a local dashboard.
An opinionated static analyzer for TypeScript and JavaScript projects - 119 rules across 11 pillars, baselines, SARIF/HTML/Markdown reports, CI annotations, and a local dashboard.
AI pull-request reviewer: hybrid RAG + a code graph + Claude Code/Codex. Whole-repo context, inline GitHub comments grounded on exact code. MCP server + Claude Code/Codex plugin.
Static security scanner for AI agents, MCP tools, and LLM applications. Detects OWASP LLM Top 10 risks, unsafe tool use, prompt injection paths, secrets, and AI infrastructure misconfigurations. Zero runtime dependencies.
Blast radius and provenance for a codebase - what breaks if I change this symbol, and where a pasted snippet came from, read from the bytes on disk right now. No precomputed graph.
Code similarity search by compression - find near-duplicate files, clone families, and where a pasted snippet came from. No embeddings, no model, no vector database.
Reusable Rust engine (crate) for self-hosted advisory AI PR reviewers — reviews GitHub, GitLab & Bitbucket PRs. Line-anchored inline comments, committable suggestions, tree-sitter structural context, OSV.dev CVE scans. Ships as one binary (npm, PyPI, crates.io, curl) with JSON output, so the bot around it can be any language that spawns a process.