Description
Large language models like ChatGPT have demonstrated remarkable capabilities across a variety of applications. However, their potential for enhancing the Linux development and user ecosystem remains largely unexplored. This project seeks to bridge that gap by researching practical applications of LLMs to improve workflows in areas such as backporting, packaging, log analysis, system migration, and more. By identifying patterns that LLMs can leverage, we aim to uncover new efficiencies and automation strategies that can benefit developers, maintainers, and end users alike.
Goals
- Evaluate Existing LLM Capabilities: Research and document the current state of LLM usage in open-source and Linux development projects, noting successes and limitations.
- Prototype Tools and Scripts: Develop proof-of-concept scripts or tools that leverage LLMs to perform specific tasks like automated log analysis, assisting with backporting patches, or generating packaging metadata.
- Assess Performance and Reliability: Test the tools' effectiveness on real-world Linux data and analyze their accuracy, speed, and reliability.
- Identify Best Use Cases: Pinpoint which tasks are most suitable for LLM support, distinguishing between high-impact and impractical applications.
- Document Findings and Recommendations: Summarize results with clear documentation and suggest next steps for potential integration or further development.
Resources
- Local LLM Implementations: Access to locally hosted LLMs such as LLaMA, GPT-J, or similar open-source models that can be run and fine-tuned on local hardware.
- Computing Resources: Workstations or servers capable of running LLMs locally, equipped with sufficient GPU power for training and inference.
- Sample Data: Logs, source code, patches, and packaging data from openSUSE or SUSE repositories for model training and testing.
- Public LLMs for Benchmarking: Access to APIs from platforms like OpenAI or Hugging Face for comparative testing and performance assessment.
- Existing NLP Tools: Libraries such as spaCy, Hugging Face Transformers, and PyTorch for building and interacting with local LLMs.
- Technical Documentation: Tutorials and resources focused on setting up and optimizing local LLMs for tasks relevant to Linux development.
- Collaboration: Engagement with community experts and teams experienced in AI and Linux for feedback and joint exploration.
Looking for hackers with the skills:
This project is part of:
Hack Week 24
Activity
Comments
-
-
about 1 year ago by jiriwiesner | Reply
I would like to ask an LLM instance about the inner workings on the Linux kernel code. It is a common task of mine to look for a bug in a subsystem or a layer that can easily have tens of thousands of lines of code (e.g. bsc 1216813). I know having an understanding of the Linux code is what we do as developers but my understanding and knowledge is always limited because I simply do not have the time to read all of the code possibly involved in an issue. If the LLM was trained to process the source code of a specific version of Linux a developer could then ask involved questions about the code using the terms found in the code base. It should basically be something that allows a developer find the interesting parts of the code better than when using just grep.
-
about 1 year ago by anicka | Reply
Actually, it looks like that off-the-shelf ChatGPT 4 can be already quite helpful in such tasks.
But training something like code llama on our kernels is something I indeed want to look into next time because if there is any way how to leverage LLMs in our bugfixing or backporting, this is it.
-
Similar Projects
Self-Scaling LLM Infrastructure Powered by Rancher by ademicev0
Self-Scaling LLM Infrastructure Powered by Rancher
Description
The Problem
Running LLMs can get expensive and complex pretty quickly.
Today there are typically two choices:
- Use cloud APIs like OpenAI or Anthropic. Easy to start with, but costs add up at scale.
- Self-host everything - set up Kubernetes, figure out GPU scheduling, handle scaling, manage model serving... it's a lot of work.
What if there was a middle ground?
What if infrastructure scaled itself instead of making you scale it?
Can we use existing Rancher capabilities like CAPI, autoscaling, and GitOps to make this simpler instead of building everything from scratch?
Project Repository: github.com/alexander-demicev/llmserverless
What This Project Does
A key feature is hybrid deployment: requests can be routed based on complexity or privacy needs. Simple or low-sensitivity queries can use public APIs (like OpenAI), while complex or private requests are handled in-house on local infrastructure. This flexibility allows balancing cost, privacy, and performance - using cloud for routine tasks and on-premises resources for sensitive or demanding workloads.
A complete, self-scaling LLM infrastructure that:
- Scales to zero when idle (no idle costs)
- Scales up automatically when requests come in
- Adds more nodes when needed, removes them when demand drops
- Runs on any infrastructure - laptop, bare metal, or cloud
Think of it as "serverless for LLMs" - focus on building, the infrastructure handles itself.
How It Works
A combination of open source tools working together:
Flow:
- Users interact with OpenWebUI (chat interface)
- Requests go to LiteLLM Gateway
- LiteLLM routes requests to:
- Ollama (Knative) for local model inference (auto-scales pods)
- Or cloud APIs for fallback
Try AI training with ROCm and LoRA by bmwiedemann
Description
I want to setup a Radeon RX 9600 XT 16 GB at home with ROCm on Slowroll.
Goals
I want to test how fast AI inference can get with the GPU and if I can use LoRA to re-train an existing free model for some task.
Resources
- https://rocm.docs.amd.com/en/latest/compatibility/compatibility-matrix.html
- https://build.opensuse.org/project/show/science:GPU:ROCm
- https://src.opensuse.org/ROCm/
- https://www.suse.com/c/lora-fine-tuning-llms-for-text-classification/
Results
got inference working with llama.cpp:
export LLAMACPP_ROCM_ARCH=gfx1200
HIPCXX="$(hipconfig -l)/clang" HIP_PATH="$(hipconfig -R)" \
cmake -S . -B build -DGGML_HIP=ON -DAMDGPU_TARGETS=$LLAMACPP_ROCM_ARCH \
-DCMAKE_BUILD_TYPE=Release -DLLAMA_CURL=ON \
-Dhipblas_DIR=/usr/lib64/cmake/hipblaslt/ \
&& cmake --build build --config Release -j8
m=models/gpt-oss-20b-mxfp4.gguf
cd $P/llama.cpp && build/bin/llama-server --model $m --threads 8 --port 8005 --host 0.0.0.0 --device ROCm0 --n-gpu-layers 999
Without the --device option it faulted. Maybe because my APU also appears there?
I updated/fixed various related packages: https://src.opensuse.org/ROCm/rocm-examples/pulls/1 https://src.opensuse.org/ROCm/hipblaslt/pulls/1 SR 1320959
benchmark
I benchmarked inference with llama.cpp + gpt-oss-20b-mxfp4.gguf and ROCm offloading to a Radeon RX 9060 XT 16GB. I varied the number of layers that went to the GPU:
- 0 layers 14.49 tokens/s (8 CPU cores)
- 9 layers 17.79 tokens/s 34% VRAM
- 15 layers 22.39 tokens/s 51% VRAM
- 20 layers 27.49 tokens/s 64% VRAM
- 24 layers 41.18 tokens/s 74% VRAM
- 25+ layers 86.63 tokens/s 75% VRAM (only 200% CPU load)
So there is a significant performance-boost if the whole model fits into the GPU's VRAM.
The Agentic Rancher Experiment: Do Androids Dream of Electric Cattle? by moio
Rancher is a beast of a codebase. Let's investigate if the new 2025 generation of GitHub Autonomous Coding Agents and Copilot Workspaces can actually tame it. 
The Plan
Create a sandbox GitHub Organization, clone in key Rancher repositories, and let the AI loose to see if it can handle real-world enterprise OSS maintenance - or if it just hallucinates new breeds of Kubernetes resources!
Specifically, throw "Agentic Coders" some typical tasks in a complex, long-lived open-source project, such as:
❥ The Grunt Work: generate missing GoDocs, unit tests, and refactorings. Rebase PRs.
❥ The Complex Stuff: fix actual (historical) bugs and feature requests to see if they can traverse the complexity without (too much) human hand-holding.
❥ Hunting Down Gaps: find areas lacking in docs, areas of improvement in code, dependency bumps, and so on.
If time allows, also experiment with Model Context Protocol (MCP) to give agents context on our specific build pipelines and CI/CD logs.
Why?
We know AI can write "Hello World." and also moderately complex programs from a green field. But can it rebase a 3-month-old PR with conflicts in rancher/rancher? I want to find the breaking point of current AI agents to determine if and how they can help us to reduce our technical debt, work faster and better. At the same time, find out about pitfalls and shortcomings.
The CONCLUSION!!!
A 
State of the Union document was compiled to summarize lessons learned this week. For more gory details, just read on the diary below! 
Multi-agent AI assistant for Linux troubleshooting by doreilly
Description
Explore multi-agent architecture as a way to avoid MCP context rot.
Having one agent with many tools bloats the context with low-level details about tool descriptions, parameter schemas etc which hurts LLM performance. Instead have many specialised agents, each with just the tools it needs for its role. A top level supervisor agent takes the user prompt and delegates to appropriate sub-agents.
Goals
Create an AI assistant with some sub-agents that are specialists at troubleshooting Linux subsystems, e.g. systemd, selinux, firewalld etc. The agents can get information from the system by implementing their own tools with simple function calls, or use tools from MCP servers, e.g. a systemd-agent can use tools from systemd-mcp.
Example prompts/responses:
user$ the system seems slow
assistant$ process foo with pid 12345 is using 1000% cpu ...
user$ I can't connect to the apache webserver
assistant$ the firewall is blocking http ... you can open the port with firewall-cmd --add-port ...
Resources
Language Python. The Python ADK is more mature than Golang.
https://google.github.io/adk-docs/
https://github.com/djoreilly/linux-helper
SUSE Observability MCP server by drutigliano
Description
The idea is to implement the SUSE Observability Model Context Protocol (MCP) Server as a specialized, middle-tier API designed to translate the complex, high-cardinality observability data from StackState (topology, metrics, and events) into highly structured, contextually rich, and LLM-ready snippets.
This MCP Server abstract the StackState APIs. Its primary function is to serve as a Tool/Function Calling target for AI agents. When an AI receives an alert or a user query (e.g., "What caused the outage?"), the AI calls an MCP Server endpoint. The server then fetches the relevant operational facts, summarizes them, normalizes technical identifiers (like URNs and raw metric names) into natural language concepts, and returns a concise JSON or YAML payload. This payload is then injected directly into the LLM's prompt, ensuring the final diagnosis or action is grounded in real-time, accurate SUSE Observability data, effectively minimizing hallucinations.
Goals
- Grounding AI Responses: Ensure that all AI diagnoses, root cause analyses, and action recommendations are strictly based on verifiable, real-time data retrieved from the SUSE Observability StackState platform.
- Simplifying Data Access: Abstract the complexity of StackState's native APIs (e.g., Time Travel, 4T Data Model) into simple, semantic functions that can be easily invoked by LLM tool-calling mechanisms.
- Data Normalization: Convert complex, technical identifiers (like component URNs, raw metric names, and proprietary health states) into standardized, natural language terms that an LLM can easily reason over.
- Enabling Automated Remediation: Define clear, action-oriented MCP endpoints (e.g., execute_runbook) that allow the AI agent to initiate automated operational workflows (e.g., restarts, scaling) after a diagnosis, closing the loop on observability.
Hackweek STEP
- Create a functional MCP endpoint exposing one (or more) tool(s) to answer queries like "What is the health of service X?") by fetching, normalizing, and returning live StackState data in an LLM-ready format.
Scope
- Implement read-only MCP server that can:
- Connect to a live SUSE Observability instance and authenticate (with API token)
- Use tools to fetch data for a specific component URN (e.g., current health state, metrics, possibly topology neighbors, ...).
- Normalize response fields (e.g., URN to "Service Name," health state DEVIATING to "Unhealthy", raw metrics).
- Return the data as a structured JSON payload compliant with the MCP specification.
Deliverables
- MCP Server v0.1 A running Golang MCP server with at least one tool.
- A README.md and a test script (e.g., curl commands or a simple notebook) showing how an AI agent would call the endpoint and the resulting JSON payload.
Outcome A functional and testable API endpoint that proves the core concept: translating complex StackState data into a simple, LLM-ready format. This provides the foundation for developing AI-driven diagnostics and automated remediation.
Resources
- https://www.honeycomb.io/blog/its-the-end-of-observability-as-we-know-it-and-i-feel-fine
- https://www.datadoghq.com/blog/datadog-remote-mcp-server
- https://modelcontextprotocol.io/specification/2025-06-18/index
- https://modelcontextprotocol.io/docs/develop/build-server
Basic implementation
- https://github.com/drutigliano19/suse-observability-mcp-server
Results
Successfully developed and delivered a fully functional SUSE Observability MCP Server that bridges language models with SUSE Observability's operational data. This project demonstrates how AI agents can perform intelligent troubleshooting and root cause analysis using structured access to real-time infrastructure data.
Example execution