Skip to content
View eeshansrivastava89's full-sized avatar
🎯
Focusing
🎯
Focusing
24 followers · 20 following

Achievements

Achievement: Pull SharkAchievement: QuickdrawAchievement: YOLO

Achievements

Achievement: Pull SharkAchievement: QuickdrawAchievement: YOLO

Block or report eeshansrivastava89

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.

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
eeshansrivastava89/README.md

Hi, I'm Eeshan 👋

📍 Seattle | ☕ Sr. Data Science Manager @ Starbucks | 🤖 Local AI Nerd | ✍️ Writing at Asymptotic

Python Statistics Experimentation LLMs Astro Privacy

I have a computer science & data science background. Currently leading large-scale recommender systems & experimentation projects for a global consumer brand. In my spare time, I like exploring how to assess reliability & trust in LLMs, along with ultra-low cost implementations of LLMs in Data Science & ML use cases. I believe in human-centric approaches to using new technology, not replacing them.

LLM + Data Science & ML Use Cases

  • How I Prompt — analyze your prompting activity and language patterns for Claude, Codex, Pi, OpenCode etc.
  • A/B Testing Memory Game — live A/B test using a memory game puzzle concept, with always-on stats & python analysis
  • Weather App — weather explorer for US ZIP codes with current, historical, and forecast data

Local AI Execution, LLM Benchmarks & Evals

  • Local LLM Visual Bench — benchmarking local AI models such as Qwen 3.6 and Gemma 4 with visual / animation prompts

Some useful tools

  • age-vault - cli for encrypting / decrytping files using age (very useful for protecting files & folders from LLMs)
  • Quizzard - if you don't want to pay for Kahoot
  • Sidequests - track the health & get AI summaries of your slopware sidequests (maybe it helps you clean things up)

Reach Me | LinkedIn | Twitter / X | eeshans.com

Pinned Loading

  1. offgrid-ai offgrid-ai Public

    Privacy-first CLI for running local LLMs — discover, configure, run, benchmark

    JavaScript 1

  2. skills skills Public

    Agent skills for context management and guardrails — works with any coding agent harness.

    1 2

  3. howiprompt howiprompt Public

    A personal analytics dashboard for your AI conversations.

    TypeScript 4 3

  4. local-llm-visual-benchmark local-llm-visual-benchmark Public

    Run visual benchmarks for local or cloud LLMs

    TypeScript

  5. sidequests sidequests Public

    Too many side projects as a solo dev? Track them all - health, commit status and AI summaries - completely hands-off.

    TypeScript

  6. age-vault age-vault Public

    Passphrase-based file encryption CLI built on age — encrypt, decrypt, and inspect sensitive files

    JavaScript