jdeng
Re:The agent harness belongs outside the sandbox
on Sunday May 03, 2026 @11:42AM (#47998078)
Good comparison of the 2 approaches of agent harness. Vita AI[0] also picked the outside model. We used the E2B sandbox solution, and fortunately it supports volume, so we just create volumes for personal skills and organization workspace, and mount them to the sandbox. This elegantly solves the "file system" problem you mentioned.
[0]: https://www.vita-ai.net (AI agent for content creation & social media management)
Re:DeepSeek v4
on Thursday April 23, 2026 @11:53PM (#47885300)
Excited that the long awaited v4 is finally out. But feel sad that it's not multimodal native.
Re:Show HN: Klaus – OpenClaw on a VM, batteries included
on Thursday March 12, 2026 @09:56AM (#47350591)
For openclaw to become helpful, you have to connect it to your personal email, access to your file etc. All of these requires user's manual setup right?. I do not get the point of "batteries included". Installing it is not the bottleneck right? The official docs has detail procedures for all deployment options.
The Three Eras of Applications: From Desktop to Cloud to AI-Native
Re:Show HN: Mog, a programming language for AI agents
on Friday March 06, 2026 @10:47PM (#47284292)
Good try. I had the idea before, but later realized all the agent ecosystem has already highly coupled with bash scripts including skills. Though bash is not a good programming language, it's indeed flexible for CLI apps. I also realized that what agent and skills really need is just a glue language, not a real programming language, so bash is not so bad in the case.
Re:Ask HN: What Are You Working On? (February 2026)
on Monday February 09, 2026 @09:41PM (#46954668)
Working on a Vibe Testing Agent (https://www.vita-ai.net/), a perfect companion of vibe coding. Now the loop is vibe coding <-> vibe testing.
Re:Kimi Released Kimi K2.5, Open-Source Visual SOTA-Agentic Model
on Tuesday January 27, 2026 @05:52AM (#46778313)
Glad to to see open source models are catching up and treat vision as first-class citizen (a.k.a native multimodal agentic model). GLM and Qwen models takes different approach, by having a base model and a vision variant (glm-4.6 vs glm-4.6v).
I guess after Kimi K2.5, other vendors are going to the same route?
Can't wait to see how this model performs on computer automation use cases like VITA AI Coworker.
Show HN: Vita AI Coworker – Autonomous agents for testing and desktop automation
I've been following the Claude Cowork discussion this week with interest. The "AI coworker" framing resonated—we've been building Vita AI around the same idea: agents that work independently, not assistants you supervise.We're focused on two main use cases: testing web apps and desktop automation. The key difference: our agents run in persistent cloud sandboxes instead of on your local...
Re:Cowork: Claude Code for the rest of your work
on Friday January 16, 2026 @11:11AM (#46648017)
Exciting to see Anthropic validate the "AI coworker" direction. We're building VITA AI (https://vita-ai.net) with similar philosophy but for enterprise QA testing.
One key architectural difference: Cowork runs sandboxed VMs on your local macOS machine, but we run sandboxes entirely in the cloud. This means:
- True isolation - agents never touch your local files or network, addressing the security concerns raised in this thread
- Actual autonomy - close your laptop, agent keeps working. Like delegating to a real coworker, not pairing with an assistant
- Scale - spin up 10 test agents without melting your CPU
The trade-off is latency and offline capability, but for testing workflows (our focus), asynchronous cloud execution is actually the desired model. You assign "test the checkout flow," go to lunch, come back to a full test report + artifacts.
Different use cases, different architectures. But the broader trend feels right - moving from conversational assistants to autonomous agents that operate independently.
Re:Ask HN: What Are You Working On? (Nov 2025)
on Monday November 10, 2025 @08:44PM (#45883178)
Sure. Join the waitlist below and I will note down that you need private demo. I will contact you once we got bandwidth on that (private demo).
Re:Ask HN: What Are You Working On? (Nov 2025)
on Monday November 10, 2025 @08:57AM (#45876057)
Working on an AI coworker (QA engineer) that can autonomously tests web app like your human QA colleagues. It has its own virtual desktop and runs as background agent.
Show HN: MCPBar – Open-Source Package Manager with Open Registry for MCP Servers
I've built MCPBar (https://www.mcp.bar), an open-source CLI tool that brings npm-like package management to the Model Context Protocol (MCP) ecosystem, solving the fragmentation problem for AI tools.What is MCPBar?- A package manager for discovering and installing MCP servers (which connect AI models to tools/APIs)- Uses a standardized mcp.json manifest format (similar to package.json) (link:...
Re:Show HN: Rabrain – AI Note Taking with Voice Input and Notion-Like ...
on Tuesday April 08, 2025 @10:49AM (#43622437)
Thanks! Voice input and AI assisted notes really save me. Whenever I have some spark, I just talk to AI and ask it to transform my thoughts into notes.
Show HN: Rabrain – AI Note Taking with Voice Input and Notion-Like Editor
Hello HN community!I'm thrilled to introduce Rabrain, a tool that redefines how you manage and recall information online. Rabrain combines the best of bookmark management and AI note-taking, featuring a Notion-like editor with powerful voice input capabilities.Key Features:One-Click Save: Easily save articles, PDFs, and web pages with our Chrome extension.AI Summarization: Get concise summaries...
Show HN: SnapDrop – An AirDrop alternative that works on any moderm web browsers
Recently snapdrop.net and sharedrop.io had been acquired (hijacked) by LimeWire. The widely used local file sharing feature had become "upload files". This is really annoying, since I have trusted the sites for years. Before I noticed the hijack, I even accidentally uploaded several secret files to it.To avoid others falling to the same trap as I was, I deployed this SnapDrop instance that is...
What do you think of a new language as better OCaml?
Re:Black Mirror: is deep thinking on the decline?
on Monday August 26, 2024 @09:21PM (#41363803)
>A bow is more powerful than a stick but also develops more motor skills, a bike develops the users body more than a car, and so on.
Totally agree. I like bike much more than car, however the trend of bike superseded by car cannot be reversed, given car's convenience and power.
IMO if we cannot reverse it, then embrace it. It applies to other tech advancement as well.
Re:Black Mirror: is deep thinking on the decline?
on Monday August 26, 2024 @08:39PM (#41363595)
The decline of deep thinking in the digital age is a pressing concern. While technology presents challenges to our cognitive faculties, it also offers unprecedented opportunities. By leveraging AI as a cognitive partner, we can counteract the negative effects of constant connectivity and revive our capacity for deep, meaningful thought.
Black Mirror: is deep thinking on the decline?
Re:I Pushed ChatGPT to Build a Minimal HTTP Server with Virtual Thread...
on Saturday October 28, 2023 @12:32AM (#38047157)
Thanks for the advice. Since the conversation itself is long, integrating it into the blog would dilute the article. I will try to make the link more accessible, and add a TL;DR section.
I Pushed ChatGPT to Build a Minimal HTTP Server with Virtual Threads in Java
Re:Ask HN: Do you search for awesome stuffs?
on Saturday August 05, 2017 @09:01AM (#14935484)
There is a ton of curated list of awesome stuffs, as you can explore on http://awesome.re. But I found it inconvenient to search by topics, or preview projects while browsing. Do you feel the same? Is the pain point serious enough for a search engine of curated awesome stuffs?
Ask HN: Do you search for awesome stuffs?
Re:Show HN: A prototype app based on the StateX architecture
on Saturday January 16, 2016 @07:06PM (#10917498)
I was searching for a usable/scalable way to develop cross platform native mobile app, but found limitations of current solutions.
Re:Show HN: A prototype app based on the StateX architecture
on Saturday January 16, 2016 @09:17AM (#10915303)
StateX (https://github.com/lilac/statex) is a cross platform native application architecture.
Show HN: A prototype app based on the StateX architecture
Re:
on Sunday October 25, 2015 @05:57PM (#10448620)
How do I move this to "show HN" list?