| FazBrowse GitHub Viewer | Trending | | Home |
| Tools: [Original HTTPS Page] |
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.
Contact GitHub support about this user’s behavior. Learn more about reporting abuse.
Report abuseAI Research Engineer working across knowledge graphs, retrieval systems, disinformation ML, and LLM inferencing, with applications in healthcare and defence. MSc Data Science with Distinction, University of Birmingham. Currently building AI systems at Valent in London. Unicorn Mafia Hackathon winner. I play chess and have a serious interest in fashion design, two disciplines that, like AI, reward both intuition and rigorous thinking.
graphify - AI coding assistant skill that turns any folder of code, docs, papers, images, or video into a queryable knowledge graph. Works with Claude Code, Codex, Gemini CLI, Cursor, Aider, Kiro, and 10+ more. 71.5x fewer tokens per query vs raw context.
Went viral 48 hours after Andrej Karpathy posted his LLM Knowledge Bases workflow. Covered across LinkedIn, Instagram, TikTok, YouTube, Medium, Analytics Vidhya, Towards AI, and blogs — all organic.
Instagram & TikTok - reels reaching 50K+ likes on a single post
YouTube - 10+ independent tutorials including:
Articles - 12+ independent pieces:
How to Use Graphify: Turn Any Folder Into a Knowledge Graph · Ana Bildea, Agentic Builders
Stop Wasting Tokens: My 71.5x Cheaper Claude Code Workflow · Level Up Coding
Supercharging Claude Code DX: Solving Context Bloat with Graphify · Renjith Ravindranathan
From 0 Insight to Infinite Connections: How Graphify Rewires Your Knowledge · Towards AI
Graphify: Build a Knowledge Graph From Your Entire Codebase · Mustafa Genc, GoPenAI
From Karpathy's LLM Wiki to Graphify: AI Memory Layers · Riya Bansal, Analytics Vidhya
Graphify vs. Caveman: Two Tools That Make AI Coding Assistants Smarter · Soumil Shah
Rootly AI Labs built rootly-graphify-importer - turns Rootly incidents, alerts, and teams into a queryable knowledge graph using graphify
Press: Analytics Vidhya · Towards AI · AI in Plain English · LinkedIn Pulse · Hacker News
| Highlight | Detail |
|---|---|
| Unicorn Mafia Hackathon (3rd / 120+ people, 47 teams) | FirstSight - real-time first-aid guidance on Meta Ray-Ban glasses, stroke detection + contactless heart rate via computer vision |
| OSS Distribution | graphify - 40k+ stars, 450k+ PyPI downloads |
| Organic Coverage | 12+ articles, 10+ YouTube videos, Instagram/TikTok reels (50K+ likes), Analytics Vidhya, Towards AI, Hacker News - zero paid |
| Research | Oral presentation at MICAD 2025 (Springer LNEE) - multimodal KG-augmented retrieval for medical diagnosis |
| Writing | The Memory Layer - book on persistent memory for AI agents |
| Building | graphifylabs.ai - enterprise knowledge graph engine |
The Memory Layer - a book on building persistent memory for AI agents using knowledge graphs. How graphify works under the hood, and how to design memory systems that grow smarter over time.
MICAD 2025 · Oral Presentation · Springer LNEE
MSc Data Science (Distinction) · University of Birmingham · 2025
Thesis: Knowledge-Graph-Based Hybrid RAG System for Academic Search
Knowledge Graphs · Retrieval-Augmented Generation · Explainable AI · Medical AI
Multi-modal Deep Learning · Defence Tech · Online Manipulation & Disinformation
Meta Ray-Ban first-aid guidance: contactless heart rate (rPPG), facial droop detection, and Gemini voice agent with JRCALC 2022 clinical GraphRAG. 🏆 3rd place UnicornMafia To The Americas 2026.
Multi Modal Knowledge Graph Augmented Retrieval for Explainable Mycetoma Diagnosis - MICAD 2025
| Back | FazBrowse Home | New Git URL |