Flagship · Founder project
Variorum
The memory your codebase never had.
An AI-powered engineering memory layer for GitHub repositories. It preserves the decisions, the history, and the reasoning around your code, so context does not disappear when engineers move on.
Code is version-controlled. The reasoning behind it is not. Why a decision was made, why a workaround exists, which docs are stale, and what is risky to touch all live in people's heads, scattered commits, and old pull requests. That knowledge erodes as teams grow and people leave, and new engineers lose days rebuilding context that used to exist.
- Cited answers from your real codebase
- Ask in plain English and get an answer grounded in the actual code, docs, and pull requests, with citations that link to the exact lines and PRs.
- Change-risk analysis before you code
- Plan a change and see the files it touches, how risky each one is, who owns it, and which tests are missing.
- Docs that fix themselves
- When documentation drifts from the code, Variorum detects it and opens a fix pull request with the evidence attached.
- Insight where you already work
- Risk-scored briefings on every pull request, untested scenarios surfaced, and a weekly health digest in Slack.
Variorum proposes, humans decide.
It never auto-merges and never force-pushes. It builds the cited memory around your code and surfaces it when you need it.
- Frontend
- Next.js (App Router), React, TypeScript strict, Tailwind CSS
- Backend
- FastAPI, Python, Pydantic, SQLAlchemy, Alembic
- Data
- PostgreSQL, full-text search, optional pgvector
- Code understanding
- tree-sitter
- AI architecture
- Provider-agnostic layer over Gemini, DeepSeek, and Perplexity
- Integration
- GitHub App
