Skip to content
View Daemon-VI's full-sized avatar

Block or report Daemon-VI

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Content in all repositories owned by your account will be closed.
Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
Daemon-VI/README.md

Rithik Krishna T

B.Tech CSE (Data Science) at MGIT Hyderabad and BS in Data Science & Applications at IIT Madras, both graduating May 2027. AI/ML intern at HCLTech, Sep 2025 – Jan 2026.

I build complete systems and measure them. Every number below comes from the project's own results file or its device-verification log, and where something is unverified the repo says so.

Public work

Project What it is Stack
AegisToolkit 31-tool Android security toolkit, no root required. Packet capture over VpnService (162 real flows parsed live on a stock Android 15 phone), TLS chain inspector, APK/tracker analyser, hardware-Keystore vault with RFC 6238 TOTP. No accounts, ads or telemetry. Kotlin · Jetpack Compose · GPL-3.0
Cascade Drag-and-drop automation builder for Android in the spirit of iOS Shortcuts: 154 actions across 14 categories, 18 trigger types, nested control flow (If / Repeat / While / Try), zero third-party runtime dependencies. Kotlin · Jetpack Compose
optivision-rag Visual-token compression for vision-language document retrieval: 448 KB → 3.95 KB per page (113.5×) while keeping 86.7 % of baseline nDCG@5; peak query RAM held at 239 MB regardless of corpus size. The written review that found one of its own experiments confounded, and what replaced it, is in docs/. Python · PyTorch · Qdrant · Hugging Face Space
carpool Ride-cost settlement for a shared commute: one React Native codebase on iOS, Android and web; each month's balances reduced to the fewest payments; Postgres row-level security tested against a real database, so the anon key in the bundle grants nothing on its own. Expo · TypeScript · Supabase
multimodal-rag-colpali OCR-free document QA: ColPali late-interaction retrieval over Qdrant, Gemini for answers, Streamlit front end. Python · Streamlit · Qdrant

In the workshop (private, or not yet pushed)

  • Personal Assistant — local-first Android assistant built on one rule: deterministic code owns facts, the model owns language. Structured questions answered from SQL in 7–12 ms with no model loaded; Qwen2.5-1.5B on-device through a vendored llama.cpp at 14.4 tok/s; a full turn cut from 48.7 s to 9.3 s after profiling; 542 unit tests.
  • Tessera — a personal compute fabric across my own phone, laptop and desktop, with a planner that explains every placement decision ("Desktop — model warm, est. 6 s vs 90 s here").
  • Meridian — a local-first health OS for Android. Photo food logging is built on published VLM error rates rather than asking a model for grams; 1,234 tests.
  • Whetstone — two-app DSA trainer (Tauri + Rust desk, Android pocket client) over one content model; the FSRS scheduler is implemented three times and checked against shared golden vectors.
  • JARVIS — fully offline Windows voice assistant: 24 tools behind 30 deterministic rules so that the 3.4 tok/s local model stays off the latency-critical path.
  • Umbra — privacy browser for Android with embedded Tor and WireGuard, EasyList shields and a kill switch.

How I work

  • Claims are measured, not asserted. Each project carries a PROJECT_STATE.md that records observed output rather than intent, and tags every feature VERIFIED, IMPLEMENTED or PLANNED.
  • Deterministic code owns facts; the model owns language. Anything that is really a SQL query stays a SQL query, whatever the front end.
  • Duplicated logic gets parity tests. Where a scheduler or a cost model exists in more than one language, the same golden vectors run against all of them.
  • Hardware is a design input. Most of this runs on an 8 GB single-channel laptop and a mid-range phone, and the numbers above were taken there.

Contact

LinkedIn · trithikkrishna@gmail.com

Pinned Loading

  1. AegisToolkit AegisToolkit Public

    31-tool Android security toolkit, no root: VpnService packet capture, TLS chain inspector, APK/tracker analyser, Keystore vault + TOTP. Kotlin, Jetpack Compose, GPL-3.0.

    Kotlin 1

  2. optivision-rag optivision-rag Public

    Visual-token compression for VLM document retrieval: 448 KB to 3.95 KB per page (113.5x) at 86.7% of baseline nDCG@5. ColPali/ColSmol, PyTorch, Qdrant.

    Python 1

  3. multimodal-rag-colpali multimodal-rag-colpali Public

    OCR-free document QA: ColPali late-interaction retrieval over Qdrant, Gemini 2.5 Flash for answers, Streamlit UI.

    Python 1

  4. Multi-Disease-Detection Multi-Disease-Detection Public

    Keras CNNs for tuberculosis (chest X-ray) and diabetic retinopathy (fundus) screening, served by a Streamlit app or a Next.js + Express pair. Course project, 2025.

    JavaScript 1

  5. Cascade Cascade Public

    Drag-and-drop automation builder for Android in the spirit of iOS Shortcuts: 154 actions, 18 trigger types, nested control flow, zero third-party runtime dependencies.

    Kotlin 1

  6. carpool carpool Public

    Ride-cost settlement for a shared commute: one React Native codebase on iOS, Android and web; month-end balances reduced to the fewest payments; Postgres RLS tested against a real database.

    TypeScript 1