Seven projects. Each one has a demo or results panel below — not marketing copy, just what the project actually does.
Most multi-agent AI frameworks hit a wall: each agent works in an isolated context window, repeating everything to every other agent until you hit token limits. NoteMind replaces that with a persistent semantic knowledge graph.
Each agent writes atomic Markdown notes stored in .brain/, embedded into ChromaDB,
indexed in MongoDB, and immediately searchable by every other agent in the swarm.
Instead of receiving a 40k-token dump of prior history, an agent gets the
3 most semantically relevant notes. Token cost stays O(k) regardless of swarm size.
Google Translate can translate text on a webpage — but it skips over images entirely. That's useless for manga, where the story is inside speech bubbles drawn on the image. MangaLens fixes that.
The Chrome extension detects text regions in manga images using Gemini Vision, fills speech bubbles with their estimated background colour, and overlays translated text in-place. Supports 18 languages, handles lazy-loaded images, builds a translation memory so character names stay consistent across pages.
A CNN + Transformer ensemble for stock price forecasting — but the actual point is the RAPID diagnostic framework built on top of it. RAPID scores Reliability, Accuracy, Precision, Interpretation, and Distribution to tell you objectively when the model's output should be trusted.
The output is three confidence bands (P10/P50/P90) rather than a single prediction. The question the project asks: "should we even trust this forecast?" — before you act on it.
Takes a resume and a job description, outputs a match score plus
which skills are present, which are missing, and why.
Uses a three-signal hybrid: TF-IDF (keyword matching),
sentence embeddings via all-MiniLM-L6-v2 (semantic similarity),
and Jaccard skill overlap.
Built with a Streamlit interface and hardware-aware OpenVINO inference (falls back to CPU automatically). Tested on 2,400 resumes and a LinkedIn job postings dataset.
TF-IDF + SVM pipeline trained on 5,000+ Supreme Court of India judgments. 93% classification accuracy across constitutional, criminal, civil, tax, and family law categories. The model highlights which specific keywords drove the classification — transparent reasoning, not a black box.
Smart attendance system combining face recognition with GPS geofencing. A student is marked present only when two conditions are met simultaneously: their face matches the enrolled records, and their device is within the classroom's GPS radius. No manual roll-call. No proxy attendance.
Published research in Advances in Decision Sciences (Q1 Scopus, CiteScore 8.3). Proposes a GF(3) — base-3 — Linear Feedback Shift Register for image encryption. Unlike binary LFSRs, the ternary feedback mechanism triples the keyspace per stage, making brute-force exponentially harder.
Validated across NPCR (98.04%), Shannon entropy (6.80 bits), UACI, and pixel correlation. Primary application: protecting sensitive medical images during transmission.