github1s

I build the boring parts that make AI agents work I'm Siddhant Khare, a software engineer who has been building things since long before AI. Side projects, proofs of concept, open source. This video is the story so far: what I've built, what I've written, and why I keep doing it. In this video: • Where it started: side projects, POCs and open source • Gitpod / Ona: building developer environments (Ona, formerly Gitpod, was acquired by OpenAI) • Open source: OpenFGA (CNCF) and GitHub1s maintainer • The Agentic Engineering Guide: a free, open-source 33-chapter guide to building with AI agents • LLMTraceFX: a token-level LLM inference profiler for NVIDIA GPUs and Apple Silicon • My first peer-reviewed research paper (co-authored), published by Springer • "AI fatigue is real and nobody talks about it": the post that started a much bigger conversation • agent-trace and my other open-source tools • Why I do all of this Links: 🌐 Website: siddhantkhare.com 📘 The Agentic Engineering Guide: agents.siddhantkhare.com 📄 Paper: "Understanding GPU-Level Bottlenecks in Large Language Model Inference" (ICDEC 2025, Springer) doi.org 🧹 Distill: Siddhant-K-code/distill 🔍 agent-trace: Siddhant-K-code/agent-trace 🔬 LLMTraceFX: Siddhant-K-code/LLMTraceFX 🔐 OpenFGA: openfga/openfga ⚡ GitHub1s: conwnet/github1s 🐙 GitHub: github.com/Siddhant-K-code 𝕏 X: x.com LinkedIn: linkedin.com #AIAgents #OpenSource #SoftwareEngineering #LLM #AgenticEngineering

github1s now supports AI features. You can configure an LLM and chat with references to your code to help you understand it quickly. All data stays local in your browser. conwnet/github1s