HNHacker News
TopNewBestAskShowJobs

nezhar

90 karma · joined May 29, 2023

I'm Harald Nezbeda, a Python developer and technical lead at Anexia, based in Klagenfurt, Austria.

I build open-source tools for developer workflows. Currently working on VibePod, which runs AI coding agents in Docker or Podman containers with traffic logging and local analytics. I also work on VoiceVault (conversation transcription and summaries) and SnyPy (a self-hosted code snippet manager).

Interested in Python, APIs, self-hosting, local LLMs, and understanding what coding agents actually do.

Blog: https://nezhar.com/ GitHub: https://github.com/nezhar VibePod: https://vibepod.dev/

submissionscomments
nezhar··on Claude Opus 4.6 extra usage promo
There is also an Auto-reload option, I think it is off by default.
nezhar··on Claude Opus 4.6 extra usage promo
You can use this if you started your Pro or Max subscription before Wednesday, February 4, 2026 at 11:59 PM PT.

Go to https://claude.ai/settings/usage, turn on extra usage and enable the promo from the notification afterwards.

I received €42, top up was not required and auto-reload is off.

nezhar··on The browser is the sandbox
Good question! Since this is an extension of input, I'm not sure if this is defined: https://developer.mozilla.org/en-US/docs/Web/API/HTMLInputEl....

On my desktop Chrome on Ubuntu, it seems to be persistent, but on my Android phone in Chrome, it loses the directory if I refresh.

nezhar··on The browser is the sandbox
I see this as a way to build apps with agentic flows where the original files don't need manipulation; instead, you create something new. Whether it's summarizing, answering questions, or generating new documents, you can use a local/internal LLM and feel relatively safe when tool calling is also restricted.
nezhar··on The browser is the sandbox
Related https://news.ycombinator.com/item?id=12098338
nezhar··on The browser is the sandbox
I like the perspective used to approach this. Additionally, the fact that major browsers can accept a folder as input is new to me and opens up some exciting possibilities.
nezhar··on Isolating Claude Code
Distributing pre-built images can help minimize this: https://hub.docker.com/r/nezhar/claude-container/tags.

I'm not sure how large the image becomes on the VM or if the distribution process is straightforward.

nezhar··on Isolating Claude Code
I also had the same idea when I built https://github.com/nezhar/claude-container.

What I was also curious about is what is actually sent and received by the agent, so I included this feature and created a CLI to make integration easier in a developer workflow.

Since I started doing this for other agents as well, I considered the idea of using a VM with Vagrant. However, I want the setup to remain minimal, so I still believe there is room for improvement.

nezhar··on On Programming with Agents
The first rule covers it best: it is crucial that you know what you are doing in order to benefit from these tools.

Regarding the second and third rules, I like to work with two terminals. One is for my agent, isolated in a container, and the other one I use for `git`. This way, I can assess whether my changes are moving in the right direction.

The PLAN.md files have also proven to be a good approach. I'm still trying to figure out the best way to keep them aligned with the application without polluting the context, but they hold significant value for documentation purposes.

nezhar··on OpenAI Partners with Cerebras
It's really hard to follow them; it feels like the Spider-Man meme.
nezhar··on Ask HN: Share your personal website
https://nezhar.com/
nezhar··on Cowork: Claude Code for the rest of your work
This is a great example of why network restrictions on an application are not sufficient.
nezhar··on Cowork: Claude Code for the rest of your work
In my opinion, having a container is currently the best trade-off in terms of performance and maintainability of the setup.
nezhar··on Cowork: Claude Code for the rest of your work
Looks interesting. How does this compare to a container?
nezhar··on Cowork: Claude Code for the rest of your work
The isolation pattern is a good starting point.
nezhar··on Cowork: Claude Code for the rest of your work
I believe the detection pattern may not be the best choice in this situation, as a single miss could result in significant damage.
nezhar··on Cowork: Claude Code for the rest of your work
I built https://github.com/nezhar/claude-container for exactly this reason - it's easy to make mistakes with these agents even for technical users, especially in yolo mode.
nezhar··on Claude Container 1.3.0 – Dockerized Claude Code with API Proxy and Datasette
Author here. This release adds two features I've found useful for understanding Claude Code behavior:

1. API Proxy - Transparently logs all interactions with the Anthropic API. Every request/response is captured without modifying Claude Code itself.

2. Datasette Integration - Lets you query and visualize the captured API data with SQL. Useful for tracking token usage, analyzing prompt patterns, or debugging unexpected behavior.

The container itself provides isolation from the host system while maintaining persistent credentials and workspace access via bind mounts.

Happy to answer questions about the implementation or use cases.

nezhar··on Show HN: Docker container for Claude Code with complete host isolation
You still need to connect to Anthropic and obtain an authorization token.

The isolation here refers to the workspace. Since you run the CLI in a container, the process can only access what you have mapped inside. This is helpful if you want to avoid issues like this: https://hackaday.com/2025/07/23/vibe-coding-goes-wrong-as-ai...

nezhar··on Speech Condenser: A tool for summarizing dialogues from videos or audio
Here's how it works:

* Audio Extraction: First, it extracts the audio from the video. * Speaker Diarization: It then identifies the different speakers in the audio. * Split Audio: The audio is split into smaller chunks based on the identified speakers. * Speech to Text: Each chunk is transcribed into text. * Combine ASR and Diarization: The transcriptions (from Automatic Speech Recognition) are combined with the diarization results to provide a structured, text-based dialogue for each identified speaker. * Summarization: Finally, the dialogue is condensed into a summary for a quick overview.

The entire process is containerized to ensure seamless and efficient operation. I'd love to get feedback or suggestions.

nezhar··on [dead]
In my article, I delve into two distinct strategies for preventing migration conflicts in Django during development. The first involves the django-linear-migrations package, which is an extension to the makemigrations command. The second uses GitLab's merge pipelines and merge trains to catch migration conflicts using CI. Both strategies aim to streamline the development process and minimize deployment errors. I welcome your thoughts and suggestions.
← PreviousPage 2 of 2