Local AI assistant with optional integrations and mobile companion
an invention by livdywan
Updated 2 months ago. 1 hackers ♥️. 3 followers.

Description

Setup a local AI assistant for research, brainstorming and proof reading. Look into SurfSense, Open WebUI and possibly alternatives. Explore integration with services like openQA. There should be no cloud dependencies. Mobile phone support or an additional companion app would be a bonus. The goal is not to develop everything from scratch.

User Story

  • Allison Average wants a one-click local AI assistent on their openSUSE laptop.
  • Ash Awesome wants AI on their phone without an expensive subscription.

Goals

  • Evaluate a local SurfSense setup for day to day productivity
  • Test opencode for vibe coding and tool calling

Timeline

Day 1

  • Took a look at SurfSense and started setting up a local instance.
  • Unfortunately the container setup did not work well. Tho this was a great opportunity to learn some new podman commands and refresh my memory on how to recover a corrupted btrfs filesystem.

Day 2

  • Due to its sheer size and complexity SurfSense seems to have triggered btrfs fragmentation. Naturally this was not visible in any podman-related errors or in the journal. So this took up much of my second day.

Day 3

Day 4

  • Context size is a thing, and models are not equally usable for vibe coding.
  • Through arduous browsing for ollama models I did find some like myaniu/qwen2.5-1m:7b with 1m but even then it is not obvious if they are meant for tool calls.

Day 5

  • Whilst trying to make opencode usable I discovered ramalama which worked instantly and very well.

Outcomes

surfsense

I could not easily set this up completely. Maybe in part due to my filesystem issues. Was expecting this to be less of an effort.

opencode

Installing opencode and ollama in my distrobox container along with the following configs worked for me.

When preparing a new project from scratch it is a good idea to start out with a template.

opencode.json

{ "$schema": "https://opencode.ai/config.json", "theme": "catppuccin", "model": "ollama/qwen2.5-coder:1.5b", "mode": { "plan": { "temperature": 0.0 }, "build": { "temperature": 0.0 } }, "provider": { "ollama": { "npm": "[@ai-sdk](/users/ai-sdk)/openai-compatible", "name": "Ollama (local)", "options": { "baseURL": "http://localhost:11434/v1" }, "models": { "qwen2.5-coder:1.5b": { "name": "Qwem2.5-Coder" } } } }, "mcp": { "openqa": { "type": "remote", "enabled": true, "url": "https://openqa.opensuse.org/experimental/mcp", "headers": { "Authorization": "Bearer {env:OPENQA_USER}:{env:OPENQA_APIKEY}:{env:OPENQA_APISECRET}" } }, "gh_grep": { "type": "remote", "url": "https://mcp.grep.app" } } }

The models need to be ollama pulled first, and ollama needs to be serving.

AGENTS.md

Agents can be instruced per project or globally like so:

When you need to lookup openQA jobs or job groups, use `openqa` tools. If you are unsure how to do something, use `gh_grep` to search code examples from github.

Note: My results varied a lot between models. Available context length e.g. OLLAMA_CONTEXT_LENGTH=8192 ollama serve & gives it more wiggle room and lowering the temerature should also help, but I found myself tweaking the configuration a lot.

Horrible performance even with small models

Normally I don't hear the fan in this laptop much. Responses were processed so slowly by opencode that I barely got much done. Even figuring out why responses were unreliable took longer because I had to wait a lot for useless responses.

Airgapped models

While Investigating the horrible performance of opencode I stumbled upon ramalama which runs models in containers optimized for different cpu's which are also isolated:

ramalama serve --ctx-size 8192 -p 8080 -d kirito1/qwen3-coder:1.7b

I could not get it to work with opencode which just silently failed to communicate with it. Even so, ramalama is awesome.

Looking for hackers with the skills:

ai

This project is part of:

Hack Week 25

Activity

  • 2 months ago: livdywan added keyword "ai" to this project.
  • 2 months ago: livdywan started this project.
  • 3 months ago: rsimai liked this project.
  • 3 months ago: livdywan originated this project.


    • Comments

    Be the first to comment!

    Similar Projects

    Background Coding Agent by mmanno

    Description

    I had only bad experiences with AI one-shots. However, monitoring agent work closely and interfering often did result in productivity gains.

    Now, other companies are using agents in pipelines. That makes sense to me, just like CI, we want to offload work to pipelines: Our engineering teams are consistently slowed down by "toil": low-impact, repetitive maintenance tasks. A simple linter rule change, a dependency bump, rebasing patch-sets on top of newer releases or API deprecation requires dozens of manual PRs, draining time from feature development.

    So far we have been writing deterministic, script-based automation for these tasks. And it turns out to be a common trap. These scripts are brittle, complex, and become a massive maintenance burden themselves.

    Can we make prompts and workflows smart enough to succeed at background coding?

    Goals

    We will build a platform that allows engineers to execute complex code transformations using prompts.

    By automating this toil, we accelerate large-scale migrations and allow teams to focus on high-value work.

    Our platform will consist of three main components:

    • "Change" Definition: Engineers will define a transformation as a simple, declarative manifest:
      • The target repositories.
      • A wrapper to run a "coding agent", e.g., "gemini-cli".
      • The task as a natural language prompt.
    • "Change" Management Service: A central service that orchestrates the jobs. It will receive Change definitions and be responsible for the job lifecycle.
    • Execution Runners: We could use existing sandboxed CI runners (like GitHub/GitLab runners) to execute each job or spawn a container.

    MVP

    • Define the Change manifest format.
    • Build the core Management Service that can accept and queue a Change.
    • Connect management service and runners, dynamically dispatch jobs to runners.
    • Create a basic runner script that can run a hard-coded prompt against a test repo and open a PR.

    Stretch Goals:

    • Multi-layered approach, Workflow Agents trigger Coding Agents:
      1. Workflow Agent: Gather information about the task interactively from the user.
      2. Coding Agent: Once the interactive agent has refined the task into a clear prompt, it hands this prompt off to the "coding agent." This background agent is responsible for executing the task and producing the actual pull request.
    • Use MCP:
      1. Workflow Agent gathers context information from Slack, Github, etc.
      2. Workflow Agent triggers a Coding Agent.
    • Create a "Standard Task" library with reliable prompts.
      1. Rebasing rancher-monitoring to a new version of kube-prom-stack
      2. Update charts to use new images
      3. Apply changes to comply with a new linter
      4. Bump complex Go dependencies, like k8s modules
      5. Backport pull requests to other branches
    • Add “review agents” that review the generated PR.

    See also

    Explore LLM evaluation metrics by thbertoldi

    Description

    Learn the best practices for evaluating LLM performance with an open-source framework such as DeepEval.

    Goals

    Curate the knowledge learned during practice and present it to colleagues.

    -> Maybe publish a blog post on SUSE's blog?

    Resources

    https://deepeval.com

    https://docs.pactflow.io/docs/bi-directional-contract-testing

    Backporting patches using LLM by jankara

    Description

    Backporting Linux kernel fixes (either for CVE issues or as part of general git-fixes workflow) is boring and mostly mechanical work (dealing with changes in context, renamed variables, new helper functions etc.). The idea of this project is to explore usage of LLM for backporting Linux kernel commits to SUSE kernels using LLM.

    Goals

    • Create safe environment allowing LLM to run and backport patches without exposing the whole filesystem to it (for privacy and security reasons).
    • Write prompt that will guide LLM through the backporting process. Fine tune it based on experimental results.
    • Explore success rate of LLMs when backporting various patches.

    Resources

    • Docker
    • Gemini CLI

    Repository

    Current version of the container with some instructions for use are at: https://gitlab.suse.de/jankara/gemini-cli-backporter

    Docs Navigator MCP: SUSE Edition by mackenzie.techdocs

    MCP Docs Navigator: SUSE Edition

    Description

    Docs Navigator MCP: SUSE Edition is an AI-powered documentation navigator that makes finding information across SUSE, Rancher, K3s, and RKE2 documentation effortless. Built as a Model Context Protocol (MCP) server, it enables semantic search, intelligent Q&A, and documentation summarization using 100% open-source AI models (no API keys required!). The project also allows you to bring your own keys from Anthropic and Open AI for parallel processing.

    Goals

    • [ X ] Build functional MCP server with documentation tools
    • [ X ] Implement semantic search with vector embeddings
    • [ X ] Create user-friendly web interface
    • [ X ] Optimize indexing performance (parallel processing)
    • [ X ] Add SUSE branding and polish UX
    • [ X ] Stretch Goal: Add more documentation sources
    • [ X ] Stretch Goal: Implement document change detection for auto-updates

    Coming Soon!

    • Community Feedback: Test with real users and gather improvement suggestions

    Resources

    Exploring Modern AI Trends and Kubernetes-Based AI Infrastructure by jluo

    Description

    Build a solid understanding of the current landscape of Artificial Intelligence and how modern cloud-native technologies—especially Kubernetes—support AI workloads.

    Goals

    Use Gemini Learning Mode to guide the exploration, surface relevant concepts, and structure the learning journey:

    • Gain insight into the latest AI trends, tools, and architectural concepts.
    • Understand how Kubernetes and related cloud-native technologies are used in the AI ecosystem (model training, deployment, orchestration, MLOps).

    Resources

    • Red Hat AI Topic Articles

      • https://www.redhat.com/en/topics/ai

    • Kubeflow Documentation

      • https://www.kubeflow.org/docs/

    • Q4 2025 CNCF Technology Landscape Radar report:

      • https://www.cncf.io/announcements/2025/11/11/cncf-and-slashdata-report-finds-leading-ai-tools-gaining-adoption-in-cloud-native-ecosystems/
      • https://www.cncf.io/wp-content/uploads/2025/11/cncfreporttechradar_111025a.pdf

    • Agent-to-Agent (A2A) Protocol

      • https://developers.googleblog.com/en/a2a-a-new-era-of-agent-interoperability/