Skip to content
View Shri2007's full-sized avatar
😴
😴

Block or report Shri2007

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. 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
Shri2007/README.md

Shri Charan Sriram. I build AI systems you can check, not just trust.

I'm a CS and Stats student at UC Berkeley. Most of what I build is about one question: how do you know an AI did the right thing? So my projects tend to come with a test harness, a replay, or a benchmark attached.

🏆 1st place, AIE x MLH Hackathon @ Code Summit (Nov 2026) for Muscle Memory

Website · X / Twitter · Berkeley, CA


Things I've built

Project What it does
Accord · live map A map of 24,063 perfumes placed by their ingredients. Find what smells like what you love, and a cheaper bottle with the same notes.
Muscle Memory · 🏆 1st place An editor that cleans up AI-written code. It reasons slowly at first, then turns calls it keeps getting right into instant Semgrep rules. Every cut is checked against hidden tests.
inference-bench When does speculative decoding actually speed up vLLM? N-gram vs draft-model speculation on code edits vs open-ended text, across batch sizes.
Airlock · replay Forks microVM sandboxes to find the exact conditions where an AI tool leaks secrets, then tests fixes.
Clean Room An AI that rebuilds software by watching it run, then proves the copy behaves the same on tests it never saw.
Probation A strict backtester a trading agent has to pass before it touches real money. No lookahead, real fees, realistic fills.

What I work with

  • Languages: Python · TypeScript · C++ · SQL
  • AI: vLLM · Gemini · Claude · agent tooling and evals
  • Web: React · Next.js · Expo · Convex · Vercel

Currently building at hackathons around SF most weekends. Always up for talking about evals, agents, or weird data sets.

Pinned Loading

  1. accord accord Public

    A map of 24,063 perfumes by their ingredients: find what smells like what you love, what it costs, and a cheaper bottle with the same notes.

    TypeScript 1

  2. muscle-memory-aie-mlh muscle-memory-aie-mlh Public

    A software factory that turns slow thinking into reflexes. Jev (System One) + Gemini (System 2) + learned Semgrep rules. AIE x MLH Hackathon.

    Python 2

  3. probation probation Public

    Python

  4. IndexCheck IndexCheck Public

    JavaScript

  5. cleanroom cleanroom Public

    JavaScript