Laxmi Sai Maneesh Reddy Jupalle

All-in-one student platform for UIC with campus feed, marketplace, notes exchange, study matching, professor reviews, and an AI campus assistant.

• · Solo-built with Next.js 16, React 19, TypeScript, Supabase
• · 10+ workflows + Groq-powered Sparky AI for campus Q&A

Connects to Gmail, Google Calendar, and Slack, then opens to a synthesized "here is your day" briefing — what needs action, what's noise, in what order, and why. Opposite of cloud inbox tools: raw content never leaves the machine, and every briefed item carries a provenance handle to the exact source message or event.

• · Compile-time privacy: RawContent does not implement Serialize — raw payloads cannot enter outbound request bodies
• · Extraction via all-MiniLM-L6-v2 (ONNX/tract); synthesis via Qwen2.5-0.5B (candle GGUF) — both verified with the network physically disabled
• · Grounding enforced at four layers (memory, wire, disk, render); an ungrounded item is a hard pipeline failure, not a display glitch
• · Hybrid classifier (rules + embeddings); SQLite FK-grounded store; Tauri v2 shell consuming string DTOs only — never raw payloads

A keyboard-first workstation for the AI model market — mnemonic commands, multi-panel layouts, watchlists, two years of historical charts, and a unified entity model. Data from OpenRouter, LMArena, HuggingFace, arXiv, and lab feeds; normalized once on the server, served through a consistent REST + SSE API.

• · Entity resolver canonicalizes upstream naming (exact/alias/fuzzy tiers) and quarantines unresolvable rows instead of corrupting the entity table
• · Immutable snapshot history in SQLite (WAL) powers PX price charts and ARENA ELO/rank history — two-year backfill on first boot
• · Per-source pollers with independent cadence, backoff, and health — one dead feed goes stale in the status bar while everything else keeps ticking
• · 12 keyboard functions (TOP, DES, PX, ARENA, BENCH, WATCH, …) with ghost-text autocomplete and inline error bar

A single ~31 MB Rust binary that captures system loopback + microphone (no bot joining your calls), transcribes in real time through swappable STT backends, and exposes everything over REST/WebSocket. Bundled clients: an embedded web dashboard and an always-on-top copilot overlay that answers from the live transcript and whatever is on your screen. Privacy by default: with local Whisper, no audio leaves your machine.

• · Lock-free capture pipeline: WASAPI loopback + mic → Silero VAD → swappable STT (whisper-local, Deepgram, Groq, OpenAI-compat) → SQLite
• · Meeting notes: two-speaker live transcript, LLM auto-titles, summaries, full-text search, markdown export, optional synced audio playback
• · Copilot overlay (Tauri): hotkey captures active-window OCR + last 10 min of transcript and streams an SSE answer with context chips
• · No concealment, no continuous surveillance — screen capture only on explicit hotkey; localhost boundary defended against DNS rebinding

Ran a controlled fine-tuning study across three causal language models to answer one question: how much can fine-tuning alone improve a model, and what sets the ceiling? Built a complete QLoRA pipeline — base model → LoRA adapters → training → automated execution-based benchmarking → adapter merging → GGUF conversion → quantization → local deployment in Ollama.

• · Fine-tuned each model on the 75K-example Magicoder-OSS-Instruct dataset; measured coding ability with execution-based benchmarks against test cases
• · Qwen2.5-Coder-3B (modern, code-specialized): already saturated — fine-tuning barely moved the score, demonstrating the ceiling effect from the top
• · TinyLlama-1.1B (modern, general): 7/10 at baseline, modest clean gains
• · GPT-2-medium (2019, near-zero at code): 0/10 → 2/10, stayed at 2/10 even after 3× training — proving the plateau is a model-capacity limit, not a training limit
• · Adapted the pipeline to each architecture (GPT-2 Conv1D attention, missing chat template, 1024-token context); Drive-checkpointed training resilient to disconnects; solved BF16 vs FP16 and QLoRA-on-Conv1D issues
• · Key insight: pretraining sets the ceiling; fine-tuning helps you reach it — a modern 1.1B model out-scored a larger 2019 model with zero fine-tuning

Product layer on top of ByteDance's UI-TARS Desktop for safer, auditable, reproducible GUI agent execution — tamper-evident recording, human approval gates, dry-run simulation, and workflow export. Fully local; no data leaves the machine. Additive and opt-in; recording failures never break a live run.

• · Command safety gate + approval hook: evaluates run_command / run_script against destructive-action rules before execution
• · SHA-256 hash-chained Flight Recorder — append-only event log, content-addressed screenshots, integrity verification on read
• · Proof Pack export (shareable HTML evidence), Workflow Capsule, and Workflow Compiler with simulation-first guardrails
• · Simulation mode: agent observes and plans but skips real UI actions — dry-run workflows without touching the desktop
• · Team Workspace with roles, governance policies, and exportable audit reports
• · ~6.4k LOC across 9 commits; 19 new service tests passing; fully backward-compatible with existing agent control flow

Intelligent filesystem autopilot — watch, organize, deduplicate, and search your files automatically. Cross-platform desktop app with CLI, daemon, tray, and installers.

• · Shipped v0.2 with background agent, system tray, egui settings GUI, and one-click installers (.exe, .dmg, .deb).
• · Rust engine: real-time notify watcher, SHA-256 dedup, rule-based organize, and nucleo fuzzy search across 100k+ files in <50ms.

Privacy-first Chrome extension — browsing history becomes a local knowledge graph and searchable second brain.

• · Manifest V3 + IndexedDB memory layer
• · On-device semantic search with ONNX WASM embeddings

"Jest for prompts" — test-driven LLM prompt development with local-first execution and a self-hosted dashboard.

Zero-config MCP server for local-first codebase health analysis — complexity, dependencies, dead code, git health.

Privacy-first local cash flow forecasting and financial anomaly detection — 533 tests, fully on-device.

Ambulance pre-arrival system — 1st place, Microsoft-sponsored Hack with Chicago.

LLM-powered website using GPT-Nano/Gemini Flash with vector/graph search (Qdrant/Neo4j) to extract, compare, and simplify insurance documents.

Full-stack AI research assistant — upload papers, chat with summaries and Q&A.

YOLOv5 pipeline detecting potential assault incidents in CCTV footage.

Healthcare app using a CNN and chatbot for faster initial assessment.