🤓 Latest Submissions
DeadCode - Delete with Evidence
Dead code accumulates in every growing software project: unused functions, classes, imports, legacy modules, and abandoned code paths. The difficult part is not identifying code that appears unused it is proving that removing it will not break the application. DeadCode is a deterministic developer tool designed to solve this problem. DeadCode scans Python repositories using AST-based static analysis and reference/dependency analysis. It identifies suspiciously unused code and classifies candidates into three states: PROVABLE, REVIEW, and ACTIVE. Each candidate is accompanied by structured evidence such as its definition, references, imports, test references, exports, and safety-related signals. The key difference is that DeadCode does not immediately delete a candidate. A PROVABLE candidate can first be passed through the proof engine. DeadCode creates an isolated Git worktree, removes the candidate there, runs available verification checks, and re-runs its analysis to confirm that the candidate has disappeared. Only after successful proof can the developer explicitly apply the removal to the working tree. When DeadCode encounters uncertainty such as framework registration, dynamic behavior, entry points, test discovery, or other safety-sensitive patterns it fails closed and classifies the candidate as REVIEW instead of assuming it is safe. The product is available as a developer CLI and as a browser-based demonstration interface. The live demo allows users to analyze a prepared Python repository or a public Python GitHub repository, inspect candidates, prove removals, and apply verified changes. DeadCode is intentionally deterministic at runtime: no LLM is used to make deletion decisions. The result is a safer and more explainable workflow for reducing codebase complexity: find it, prove it, remove it.
27 Sep 2026
Vaani: AI Voice Companion for Meaningful Calls
Vaani is a personal AI voice agent designed to help people stay connected with the people they care about, even when they are busy or far away. Instead of another chatbot that waits for you to open an app, Vaani can make a real phone call on your behalf and have a natural conversation with a loved one. Users can create profiles for their loved ones, choose the voice and conversational style, and tell Vaani what they want the conversation to focus on. During the call, Vaani communicates naturally and keeps the conversation centered around the user's priorities. After the call, Vaani transforms the conversation into useful information through a concise summary, important updates, things worth remembering, and suggestions for what may matter in the next call. Vaani also keeps a history of previous conversations and provides an editable memory layer so users can control what information is retained. The goal is not to replace human relationships, but to make staying connected easier when time, distance, or busy schedules get in the way. Vaani turns a simple AI phone call into a personal communication layer that helps users stay informed and remember the small things that matter.
30 Sep 2026
