Skip to content
View suhaasteja's full-sized avatar

Block or report suhaasteja

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
suhaasteja/README.md

About

Suhaas Teja Vijjagiri · AI/ML builder · based in San Jose CA

Building at the intersection of LLM agents, evaluation, and applied AI. Currently: [current project].

Tech: Python · TypeScript · LangChain · Ray · FastAPI · PyTorch · MCP · MERN · AWS · C++

Recent projects:

  • 🎬 playback — Agent session log visualizer
  • 🧠 claude-deck — Claude Code statusline with context + Spotify
  • ⚗️ gauntlet — Adversarial AI red-teaming CLI for PRDs
  • 🤖 reachy-rx — Embodied AI pharmacist robot (3rd @ Seeed hackathon)

📫 suhaastejav@gmail.com · linkedin.com/in/suhaas-teja

Pinned Loading

  1. SageMem SageMem Public

    multi agent memory harness inspired by gpu memory arch

    Python

  2. playback playback Public

    Playback turns raw agent session logs into a clear, step‑by‑step timeline so you can see what the user asked, what the agent did, which tools ran, and how the session progressed.

    JavaScript 2 1

  3. Flowdeck Flowdeck Public

    A browser-based Human-Machine Interface for a simulated UR5 robot arm

    JavaScript

  4. reachy-rx reachy-rx Public

    [SeeedStudio Embodied AI hack 3rd place] An embodied AI pharmacist robot that watches, reminds, and cares. Built for Reachy-mini robot.

    Python 1

  5. Lekha Lekha Public

    google-docs clone with inline ai commands to generate text, mermaid charts

    TypeScript

  6. lotus lotus Public

    Forked from lotus-data/lotus

    AI-Powered Data Processing: Use LOTUS to process all of your datasets with LLMs and embeddings. Enjoy up to 1000x speedups with fast, accurate query processing, that's as simple as writing Pandas code

    Python