Wake: Every Deleted Line Had a Reason (An Archival Git Necropolis)

A developer built Wake, a local-first web application that scans Git repositories to deterministically track deleted files, generates grounded obituaries for each deletion using the local open-weight model gemma3:1b, and uses ripgrep to flag surviving code, docs, and configs that still reference the dead files. The system verifies model-generated commit citations against real SHAs and falls back to a deterministic template when a citation is hallucinated, and it was evaluated against 25 hand-labeled historical deletions across expressjs/cors, sindresorhus/is, and chalk/chalk.

This is a submission for the Hacktoberfest Open-Source AI Challenge Week 4: Ghost in the Machine https://dev.to/challenges/hacktoberfest-week4-2026-10-26 . In commit 7e6f7eeac0c16d9abed2cb84ac4b2891a51fa3dc , an open-source maintainer quietly removed CONTRIBUTING.md from expressjs/cors . It was 33 lines of history. If you look at Git log today, that file is just gone. But if you open Wake , that deletion is preserved forever on a stone slab: Born: 2017-10-04 Commit 78dd894 Died: 2025-11-30 Commit 7e6f7ee Lifespan: 2,979 days Last Words: "docs: revamp content 374 " Grounded Obituary: "Removed CONTRIBUTING.md after 2979 days. Purged 33 lines of historical code." Citations: commit 7e6f7ee clickable chip that expands the author, timestamp, and diff inline And then comes the twist. When you look below the headstone, a solitary amber-gold warning appears: STILL HAUNTING . Wake's regex engine traced active survivor files across the repository and found that a living documentation file still contained a dangling markdown link pointing to that dead file. This is Wake : an archival necropolis for dead code, and an exorcist for the ghosts left behind. Wake is an end-to-end, local-first web application that inspects Git repositories, deterministically tracks deleted files, writes grounded obituaries using a local open-weight model gemma3:1b , and locates the "ghosts"—active code, documentation, and configuration files that still reference things that died. Wake was built around a strict principle of Honest AI : TEMPLATE . git apply . oklch 16% 0.01 260 , hairline borders, 2px radii, self-hosted IBM Plex typography, and a single accent—Marigold oklch 78% 0.15 75 —strictly and solely reserved for active hauntings. Hosted Interactive Necropolis Render Live : 👉 https://wake-necropolis.onrender.com https://wake-necropolis.onrender.com Serves authentic precomputed real scans from samples/wake.json and samples/cors.json since free cloud containers lack local Ollama/GPU runtimes . Video Walkthrough 1:12 Full HD 1080p with AI Narration : Click the thumbnail above to play or download the 1080p MP4 walkthrough: wake demo walkthrough.mp4 https://github.com/Shreyansh00987/Wake/raw/main/wake demo walkthrough.mp4 Wake was engineered with a modern, fully offline-capable stack: node:sqlite Node.js 22+ built-in C-SQLite engine with zero external compile dependencies . child process.spawn with -M rename detection. When a file is moved e.g. test/cors.js - test/test.js , Wake tracks the rename lineage and never falsely classifies it as a death. @vscode/ripgrep bundled binary executed with strict argument arrays never shell-interpolated strings . gemma3:1b 806 MB, Q4 K M quantization, licensed under the @fontsource/ibm-plex-sans and @fontsource/ibm-plex-mono for 100% offline functionality. Git Repo │ ├─► git ls-files Load surviving files ├─► git log -M --name-status Extract deletions & trace renames │ ▼ Evidence Extraction │ diffstat, birth SHA, death SHA, lifespan, authors, last words │ ▼ Ollama Inference: gemma3:1b ◄── Structured JSON Schema │ ▼ SHA Citation Verifier ├── Valid citations? ──► Verified Grounded Obituary └── Hallucinated SHA? ──► Deterministic Template Fallback │ ▼ Ripgrep Haunting Detector ├── Scan surviving code, docs, configs excluding node modules, lockfiles └── Detect dangling imports & references │ ▼ Exorcise Engine ──► Produces Copy-Only Unified Diff To maintain total credibility, I evaluated Wake against 25 hand-labeled historical deletions across three popular open-source repositories: expressjs/cors MIT , sindresorhus/is MIT , and chalk/chalk MIT . Here are the real, unvarnished measurements from eval/RESULTS.md : | System / Model | Cases | Citation Validity Rate | Cause Accuracy | Avg Latency | Fallback Rate | |---|---|---|---|---|---| | Deterministic Template Engine | 25 | 100.0% 25/25 | 80.0% 20/25 | < 1ms | 0% | | gemma3:1b Open-Weight | 25 | 80.0% 20/25 | 28.0% 7/25 | 1,964ms | 20% 5/25 | | qwen2.5-coder:1.5b | 25 | Tested in prototype | Tested in prototype | N/A | N/A | Building Wake entirely on open-source software and open-weight models was not a compromise—it was the only design that makes ethical sense for software developers: refactor and an abandoned experiment solely from short Git commit messages is noisy 28% exact cause match . The deterministic regex engine actually outperformed the 1B LLM on category categorization. However, the LLM excels at synthesizing the human summary. test.js or data.ts , searching for test across a codebase triggers hundreds of false positives. Wake mitigates this by requiring token lengths = 4 characters and filtering common programming keywords, but maintainers must always review confidence scores. samples/wake.json and samples/cors.json . True real-time local scanning is intended for developers running npm run dev or docker-compose up on their own machines. Code is written by humans. Every deleted file represented someone's late night, an architecture that served its time, or a lesson learned the hard way. Wake treats code history not as an untangled pile of diffs, but as a dignified cemetery. And when you exorcise that final lingering ghost from your README.md or package.json , you give that deleted line the peace it deserves.