Speakers
Description
Modern Ubuntu systems offer powerful tools like systemd, LXD, and various CLI utilities, but these often remain fragmented and require significant command-line expertise to operate efficiently. In this talk, we will present a system that enables natural language control of Ubuntu using a fully local AI Model, our system contains:
- A local LLM for intent interpretation
- A lightweight orchestration layer
- Tool adapters connected to Ubuntu components (systemd, LXD, logs)
Instead of relying on cloud services, this system uses a local LLM combined with a structured tool interface to safely and predictably interact with system components. This allows users to monitor performance, manage services, control LXD containers, and summarize logs using conversational commands.
Summary
This talk demonstrates a practical system for controlling Ubuntu using a local LLM. It shows how natural language can safely interact with various system components. Our live demo will highlight real world implementation and key trade offs.
Biography
Shivay Sharma is an engineer who gravitates toward complex systems, understanding how they operate at scale, where they fail, and how to make them more reliable and intelligent.
He works across backend, distributed systems, and applied AI, building production grade services and data-driven pipelines. With experience spanning microservices, cloud infrastructure, and machine learning, he focuses on designing systems that are not only scalable and secure but also efficient and maintainable.
Laksh Gambhir is a builder at heart who enjoys getting unreasonably deep into systems, figuring out how they work, where they break, and how to make them smoother.
He works on electronic system-level modelling, virtual prototyping, and low-level tooling, often around Linux workflows and automation. Having worked in visual design as well, he tends to obsess over making systems cleaner, simpler, and nicer to use.
What audience can learn
Attendees will gain a practical understanding of how to integrate local LLMs into Ubuntu systems to automate real tasks. They will learn how to design structured tool interfaces for safe AI-driven system control, and how to connect AI models with components like systemd, LXD, and system logs.
The session will also provide insights into real-world trade-offs, including latency, reliability, and security considerations when running AI locally. By the end of the talk, participants will have a clear mental model and implementation approach for building their own local, privacy preserving AI workflows on Ubuntu.
Things to know or prepare for this session
Basic familiarity with the Linux command line and Ubuntu system tools (such as systemd and containers) is helpful but not required.
| Language | English |
|---|---|
| Difficulty level | Begineer |