Skip to content
View ms-shashank's full-sized avatar
🎯
Focusing
🎯
Focusing

Organizations

@Cyborg-Network

Block or report ms-shashank

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
ms-shashank/README.md
Shashank M S. Lead AI engineer building OxCode. SWE-bench Verified: 410 of 500 issues fixed. Terminal-Bench 2.1: 73 of 89 solved.

LinkedIn     Email     X     Stack Overflow

What I work on

A recorded OxCode run in the real VS Code panel: asked why a login test fails, it searches, reads two files, finds that expiresAt is in seconds but compared to Date.now() in milliseconds, edits two files, asks before running npm test, and finishes with 14 of 14 tests passing

I lead engineering on OxCode, an AI software engineer for VS Code and the terminal. Version 0.9.0, the public launch, is live on the Visual Studio Marketplace and Open VSX.

My part spans the agent loop, the API gateway behind it, and the evaluation work that measures both. The run on the right is the real extension panel, recorded from its own webview: it finds a seconds versus milliseconds bug, fixes it, asks before running the tests, and stops when they pass.

Before OxCode I built the backend of Oxlo.ai, a serverless inference platform serving 45+ models across Azure AI Foundry, AWS Bedrock and our own GPUs.


Results you can check

Both runs are published with their predictions, reports and method in oxcode-evals.

  • SWE-bench Verified: 410 of 500 (82.0%), with the agent offline inside each issue's own environment. See the run
  • Terminal-Bench 2.1: 73 of 89, our best round. See the run

Systems I have built

  • Rate limiting in Redis, atomic per minute, hour and day, with concurrency limits
  • Priority queues per model, ordered by plan, so a burst waits instead of failing
  • GPU load balancing and autoscaling across T4 to H100 workers
  • Caching, from a Redis user cache on the hot path to prompt caching that took Claude calls from zero cache hits to a cached prompt
  • Retries and fallback routing across model providers in the OxCode gateway

Selected open source

Person Detection, Tracking and Re-Identification YOLOv8 detection, Deep SORT tracking and OSNet re-identification. Keeps a stable ID for each person through occlusion and re-entry.

AI Code Debugger A LangGraph workflow with parser, fixer and reviewer roles, iterative reasoning loops and model selection by cost.

Universal Document Intelligence Chatbot Answers across uploaded documents and live web search, routing each question to the source that can answer it, with citations.

PolicyPulse Scans documents and email for policy violations with configurable rules for personal data and confidential material.

Stack

  • Languages: Python, TypeScript, JavaScript, SQL, Bash
  • AI: coding agents, tool calling, RAG, prompt caching, LLM evaluation, LangGraph, PyTorch
  • Models: DeepSeek, Kimi, Qwen, GLM, Llama, Mistral, Claude and GPT, plus FLUX, Whisper and YOLO
  • Backend and infrastructure: FastAPI, Postgres, Redis, Docker Swarm, Azure, AWS Bedrock, RunPod

Pinned Loading

  1. Person-Detector-and-Tracking Person-Detector-and-Tracking Public

    This project implements a person detection and tracking system using YOLOv8 for real-time object detection, Deep SORT for object tracking, and OSNet for person re-identification. The model assigns …

    Python 8 2

  2. Sentiment-Analysis-of-a-product-by-web-scraping Sentiment-Analysis-of-a-product-by-web-scraping Public

    This repo gives you breif understanding of how web scraping really works and how to deal wtih requests and Data processing and Analyzing the reviews.

    Python 1 2

  3. Summarizer.io Summarizer.io Public

    A text-summarzing web-application using Spacy module

    Python 2 1

  4. AI-Agent-Task-Decomposer AI-Agent-Task-Decomposer Public

    Python

  5. AI-Code-Debugger AI-Code-Debugger Public

    Using LangGraph and Agents

    Python

  6. AskMyPDF-Pro---Advanced-AI-Document-Assistant AskMyPDF-Pro---Advanced-AI-Document-Assistant Public

    Forked from pavithra-hn/AskMyPDF-Pro---Advanced-AI-Document-Assistant

    Python