Skip to content
View sasharif87's full-sized avatar
1 follower · 3 following

Block or report sasharif87

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
sasharif87/README.md

Hi, I'm Shan

Sr. Ops Engineer who builds the tools that don't exist yet. My background is in data and operations, and I write code to close the gap between what a platform claims to do and what actually needs to happen at ground level.

Most of my work stays private — client work under contract, tools built for environments I can't share, or early-stage projects I may license. What's public here is what I can open.

Currently working on

Institutional Memory Engine (IME) — Self-hosted knowledge graph and RAG Q&A platform that mines revision history, comment threads, and edit deltas to surface cited answers with full provenance. Air-gapped by default (Ollama), optional Claude API hybrid mode. Deployed. Provisional patent filed.

Homelab — Self-hosted infrastructure on Proxmox with a Quadro RTX 5000 for GPU workloads. 21 Docker Compose service stacks, ZFS storage, GPU passthrough, Ollama for local LLMs. Datacenter-grade ops on consumer hardware.

Stack

Python · FastAPI · TypeScript · React · PostgreSQL · Docker · Ollama · SQL · Google Apps Script

Reach me

Pinned Loading

  1. dropin-AI-Toolkit dropin-AI-Toolkit Public

    A powerful, modular AI toolkit designed to be dropped into any project. It auto-detects your project structure and uses local LLMs to scaffold code, generate tests, and apply fixes.

    Python

  2. homelab homelab Public

    Self-hosted home server — Proxmox, ZFS, Docker, local AI. Compose files, automation scripts, and hard-won lessons shared for anyone building their own stack.

    Python