An AI-native Markdown indexing system and MCP server that structurally maps documents into section trees, allowing LLM agents to fetch specific contexts instead of consuming entire files, drastically reducing token usage and improving accuracy.
Blogs (6)
Follow on XEvery week, I document and articulate my thoughts and learnings on Backend Internals, Distributed Systems, and Engineering Explorations. Here are all blogs I wrote to date.
If you find my writings helpful and interesting, consider following me on X (Twitter) for updates.
- • Jul 24, 2026 : Ways to optimize your Agents
- • Jul 23, 2026 : Log masking is a bigger challenge than it seems
- • Mar 30, 2026 : "Make No Mistakes", Threats Really Helps ??
- • Mar 08, 2026 : Mistakes* By Programming Languages : Part 1
- • Feb 07, 2026 : Claude Wrote a Compiler. Are we Cooked?
- • Dec 20, 2025 : Ngrok: How to Expose Localhost to the Internet
Fintech (0)
An exploration into the architecture of financial systems. Here I document everything I learn about payment gateways, ledgers, compliance, and core banking infrastructure.
Projects
Distributed locking library on top of RDBMS, published to npm. Exposes Spring Boot auto-configuration so teams can drop it in without boilerplate.
A local LLM orchestration system where specialized models take on distinct roles — each validating the other’s output — to produce results rivaling frontier models like Claude Opus, without sending data to the cloud.