nezhar
Re:Show HN: pi pod – run your pi coding agent in sandboxes on your own...
on Saturday October 03, 2026 @03:40PM (#49947112)
Hi, creator of VibePod here (https://github.com/VibePod/vibepod-cli)
I spent lots of time on this topic, and had a similar path. Meanwhile the tool also supports a quick way to add custom or local providers to agents: https://vibepod.dev/news/vibepod-cli-0-24/
Re:Show HN: Offrun – manage every coding agent from one workspace
on Saturday October 03, 2026 @03:25PM (#49946991)
There is a Task mode availalbe: https://vibepod.dev/docs/agents/#managing-tasks
Workers and Boards are in the making
Re:Show HN: Offrun – manage every coding agent from one workspace
on Saturday October 03, 2026 @01:00PM (#49945907)
Nice, would https://vibepod.dev/ also be a fit for the list?
Re:DeepSeek Harness Desktop for macOS and Windows
on Friday October 02, 2026 @02:18AM (#49930363)
Thanks, was wondering why this is in the feed.
Re:Tell HN: Codex Is Down [fixed]
on Friday September 25, 2026 @07:04PM (#49851167)
A good time for reading
VibePod CLI 0.24: bring your own model provider
Re:OUI-1: world's first model for Generative UI
on Tuesday September 08, 2026 @02:09PM (#49614259)
OpenAI, OpenAPI and now OpenUI. Explain this to a non tech person...
Re:VMware migration reduces Tottenham Hotspur's licensing fees by 85 p...
on Monday September 07, 2026 @09:42AM (#49598356)
Reminds me of https://news.ycombinator.com/item?id=42682671
Show HN: I Have Been Clawed – Index of coding agent incidents
Re:Claude Fable 5.1 and Claude Mythos 5.1
on Tuesday September 01, 2026 @04:17PM (#49527541)
Sonnet is the new haiku
Re:Claude Fable 5.1 and Claude Mythos 5.1
on Tuesday September 01, 2026 @02:04PM (#49525536)
This time it came with a usage reset
Re:Qwen3.8 27B
on Friday August 14, 2026 @09:40AM (#49298548)
Yeah, same with the latest releases of meta and NVIDIA. It's like everybody is expected to have 32 GB of RAM
Re:Qwen3.8 27B
on Friday August 14, 2026 @09:37AM (#49298513)
It feels so strange that we now have countdowns for model releases
Re:Meta Muse Glimmer – open weights 30B local coding model
on Monday August 10, 2026 @02:59PM (#49248112)
I tried to run it with lemonade by installing it via hf but did not succeed, it gets some weird 500 errors. I also see that ollama has currently only an mlx version available.
Anybody here succeed to run this on AMD?
Re:Docker Sandboxes – Disposable, isolated sandboxes for AI agents
on Monday August 10, 2026 @02:54PM (#49248039)
Sure, I added an issue for this, so it will follow in one of the next releases
Re:Docker Sandboxes – Disposable, isolated sandboxes for AI agents
on Monday August 10, 2026 @02:48AM (#49240154)
You design the sandbox so the agent starts in that layer. The next thing you can do is to limit the network access, this is what I'm working on right now.
Or do you mean something else?
Re:Docker Sandboxes – Disposable, isolated sandboxes for AI agents
on Monday August 10, 2026 @02:38AM (#49240066)
Open source alternative with podman support and local telemetry collection https://github.com/VibePod/vibepod-cli
Re:Mistral's Shieldstral: 3B open-weights model for multimodal moderation
on Tuesday August 04, 2026 @02:15PM (#49172645)
Re:Claude Opus 5
on Saturday July 25, 2026 @06:28AM (#49046345)
Re:Claude Opus 5
on Saturday July 25, 2026 @06:25AM (#49046337)
It's always like this, that's probably why they are pushing new models every few weeks.
Re:Claude Opus 5
on Saturday July 25, 2026 @06:23AM (#49046326)
Using `/model claude-opus-5[1m]` you can also use the model with older versions of Claude Code
Unified CLI for running AI coding agents in isolated Docker or Podman containers
Re:Grok CLI uploaded the whole home directory to GCS
on Monday July 13, 2026 @11:26AM (#48894163)
This is particularly the whole reason why I created https://github.com/VibePod/vibepod-cli
If someone wants to contribute the Grok CLI I'm happy to support it.
Re:Hy3 – 295B MoE model (21B active, 192 experts)
on Tuesday July 07, 2026 @05:51AM (#48815616)
Announcement https://hy.tencent.com/research/hy3
Free for two weeks on OpenRouter https://openrouter.ai/tencent/hy3:free
Hy3 – 295B MoE model (21B active, 192 experts)
Re:Knowledge Should Not Be Gated
on Monday July 06, 2026 @04:10AM (#48801941)
Still looking for this, the OpenKB project look promising.