RepoRevenant — Forgotten Code Deserves a Second Life

This is a submission for the Hacktoberfest Open-Source AI Challenge Week 4: Ghost in the Machine

---

What I Built

RepoRevenant is an open-source, AI-powered software forensics and repository resurrection platform.

"Forgotten code deserves a second life."

Software projects are abandoned every day — not because their core ideas were wrong, but because language runtimes move on. A repository written in 2017 often fails silently on Python 3.12+ because of PEP 594 removals (imp, cgi, pipes), collections.abc drift, and print-statement syntax errors.

RepoRevenant enforces a strict epistemic hierarchy — the AI is never trusted blindly:

Tier	Source	Can Declare Resurrection?
Observed Facts — AST errors, dependency scans	Python ast, GitPython	No (establishes baseline)
AI Hypotheses — root-cause diagnosis	Local Open-Weight LLM (Llama 3, Mistral)	No (unverified)
Proposed Repairs — unified diffs	AI Agent Engine + Unified Patcher	No (pending human approval)
Human Approval — developer consent	Interactive Review UI	Prerequisite
Verified Outcome — post-patch test suite exit code 0	Ephemeral Pytest Sandbox	YES — Empirical Proof

The theme "Ghost in the Machine" maps directly: the ghost is the dormant intelligence trapped inside an abandoned codebase. RepoRevenant is the medium that calls it back.

---

Demo

🔗 Live Demo: reporevenant.vercel.app

The live deployment runs the frontend on Vercel proxied to a secured backend exposing two controlled sample repositories:

• sample-pyvault — a legacy secrets manager with PEP 594 imp and cgi violations
• sample-math-matrix — a 2016 linear algebra library with collections.Mapping drift

Local full-power run:

git clone https://github.com/divyanshigupta786/Repo-Revenant.git
cd Repo-Revenant
npm install
python -m venv .venv && .venv\Scripts\activate
pip install -r backend/requirements.txt
npm run backend   # FastAPI on :8000
npm run dev       # Next.js on :3000

---

Code

divyanshigupta786 / Repo-Revenant

REPOREVENANT

"Forgotten code deserves a second life."
Investigate the forgotten. Repair the broken. Prove the resurrection.

RepoRevenant is an open-source, AI-powered software investigation and repository resurrection platform built for the "Ghost in the Machine" open-source AI challenge.

Software projects are frequently abandoned when maintainers move on, dependencies rot, or runtime platforms advance. A codebase written in 2017 often fails on modern runtimes—not because its core algorithms are flawed, but because language syntax shifted, standard library modules were purged (such as Python's PEP 594 removal of imp, cgi, and pipes), and abstract base classes drifted.

RepoRevenant inspects repository structure, extracts empirical Abstract Syntax Tree (AST) evidence, isolates the code in clean temporary sandboxes, executes baseline test suites to document exact pre-patch failures, synthesizes targeted repairs using replaceable open-weight AI models, and proves the resurrection by verifying post-patch test suites pass with exit code 0.

---

Table of Contents

1. Product…

View on GitHub

Key source files:

• backend/app/main.py — FastAPI forensic daemon (7-stage pipeline)
• backend/app/engine/ — AST analyzer, AI agent engine, unified patcher
• backend/app/db.py — SQLite schema (investigations, findings, patches, test runs)
• components/HeroAnimations.jsx — Three.js resurrection core + Anime.js timelines

---

How I Built It

RepoRevenant is a 7-stage forensic pipeline built around fully local, replaceable open-weight models:

Backend — Python / FastAPI

1. Intake — Validates HTTPS Git URLs with SSRF protection (blocks RFC 1918 IPs, 169.254.169.254)
2. Inspector — Parses requirements.txt/setup.py, discovers test suites, scans language composition
3. Analyzer — Deterministic Python AST pass: flags PEP 594 removals, collections.abc drift, Python 2 print statements — no AI needed for facts
4. Verifier — Executes baseline pytest in an isolated temporary sandbox (env-scrubbed, 30s timeout)
5. AI Engine — Sends AST evidence + source snippets to local Ollama (llama3:8b, mistral:7b, codellama:7b) for contextual root-cause hypotheses and repair synthesis
6. Patcher — Validates AI-generated diffs with ast.parse(), creates rollback backups, applies with human approval
7. Reporter — Exports Resurrection Certificates as .md, telemetry as .json, diffs as .patch

Frontend — Next.js / Three.js

• Three.js Resurrection Core — 3D WebGL scene of fragmented archival nodes reconnecting
• Anime.js — Coordinated entrance timelines
• Lenis — Accessible smooth scroll (prefers-reduced-motion compliant)
• Ctrl+K Command Palette — Navigate views, trigger investigations, switch inference providers

Open-Weight AI Models Used

Model	Role
llama3:8b (Ollama)	Primary diagnosis + repair synthesis
mistral:7b (Ollama)	Alternate repair synthesis
codellama:7b (Ollama)	Code-specialized repair fallback
Built-in Heuristic Expert	Air-gapped deterministic fallback (zero neural API)

---

Why Does Open Innovation Matter?

If RepoRevenant were built on a closed API, it would be fundamentally unusable for its own purpose.

Abandoned repositories often contain private intellectual property, proprietary algorithms, and trade secrets — the exact code an organization cannot afford to send to a third-party cloud endpoint for "repair." The ability to run llama3:8b locally via Ollama means:

1. Zero cloud leakage — source code is analyzed on the host machine; nothing leaves
2. Air-gapped operation — the deterministic expert engine operates with zero neural API calls in restricted environments
3. Swappable models — the MODEL_PROVIDER env var lets developers substitute any OpenAI-compatible local endpoint. Llama 3 today, a future specialized code-repair model tomorrow
4. Auditability — because both the models and the forensic engine are open-source, every diagnostic decision can be traced, reproduced, and challenged

A closed API wouldn't just be a privacy risk — it would be a trust violation against the very repositories users are trying to resurrect.

---

My Agent Session

Session saved via DevRelay — link coming after final verification run.

---

The Spirit of It

There's a particular kind of sadness to an abandoned repository.

Someone cared enough to write it — to name it, to structure it, to leave comments explaining why. Then life happened: they moved on, the company pivoted, the project "finished." Five years later, python setup.py install explodes with ModuleNotFoundError: No module named 'imp', and all that careful work becomes invisible.

RepoRevenant started from a single observation: the code still knows what it wanted to do. The AST is still there. The test assertions still describe the intended behavior. The ghost is still in the machine.

Watching the Three.js resurrection scene — fragmented archival nodes slowly pulling back together as the post-patch test suite returns exit code 0 — that's the moment it lands. Not because the AI did something magic, but because the code was never actually broken. It just needed someone to listen to it again.

---

Prize Categories

• 🏆 Ghost in the Machine — Core challenge category
• 🤖 Best Use of Open-Weight / Local AI — Ollama + Llama 3 / Mistral / CodeLlama, fully replaceable
• 🔒 Best Privacy-Preserving AI Application — Zero cloud leakage, air-gapped deterministic fallback
• 🛠️ Best Developer Tooling — Forensic pipeline, unified diff reviewer, Resurrection Certificate export

---