Hacker News: Jayakumark

New comment by Jayakumark in "Show HN: Claw Patrol, a security firewall for agents"

Jayakumark — Thu, 11 Jun 2026 17:37:51 +0000

How will credentials be injected via Gateway for each user ? If we have 5 users with one gateway, how it knows whose github credential to inject ?

New comment by Jayakumark in "Show HN: Forge – Guardrails take an 8B model from 53% to 99% on agentic tasks"

Jayakumark — Wed, 20 May 2026 06:29:08 +0000

Probably in same league https://github.com/Doorman11991/smallcode

New comment by Jayakumark in "Google I/O"

Jayakumark — Tue, 19 May 2026 18:49:03 +0000

The reason they named it as AntiGravIty was based on this. The cli command to launch it is agi

New comment by Jayakumark in "Apple Silicon costs more than OpenRouter"

Jayakumark — Sun, 17 May 2026 13:26:31 +0000

OP is comparing against Gemma everywhere but concludes paying Anthropic make more sense. Anthropic is $15 per million output token which is 30-35x more expensive even in openrouter .

This is like comparing e-bike at home with e-bike rental and concluding therefore we need to rent Toyota since it can go at similar speeds. Getting tired of bad posts getting much attention .

New comment by Jayakumark in "GitHub Copilot is moving to usage-based billing"

Jayakumark — Mon, 27 Apr 2026 17:11:30 +0000

Does this mean you can only prompt "Hello" every morning for a month with Opus 4.7 ?

New comment by Jayakumark in "Show HN: Agent Vault – Open-source credential proxy and vault for agents"

Jayakumark — Thu, 23 Apr 2026 23:29:52 +0000

How is it different from Onecli ? And does it do credential stripping ? Will it support access SDK from Bitwarden and integrate with infiscal ?

New comment by Jayakumark in "Gemini Enterprise Agent Platform, powering the next wave of agents"

Jayakumark — Wed, 22 Apr 2026 20:08:10 +0000

The word agent is used 142 times in this single blog post, They are going overboard.

New comment by Jayakumark in "Workspace Agents in ChatGPT"

Jayakumark — Wed, 22 Apr 2026 18:54:20 +0000

Looks like ChatGPTs answer to claude managed agents, but using existing ChatGPT Business subscription and not API Keys. With one Caveat , it needs to be invoked from ChatGPT or Slack does not support invoking from APIs, so cannot embed it. Also google launched agent cli today to build own one and integrate with Gemini enterprise https://developers.googleblog.com/agents-cli-in-agent-platfo...

New comment by Jayakumark in "Workspace Agents in ChatGPT"

Jayakumark — Wed, 22 Apr 2026 18:51:19 +0000

In demo videos, it shows Memory under Files, so i assume it holds learnings and shared context.

New comment by Jayakumark in "Show HN: Broccoli, one shot coding agent on the cloud"

Jayakumark — Wed, 22 Apr 2026 17:05:46 +0000

Thanks for making it open source, Jira Support would be good

New comment by Jayakumark in "Claude Managed Agents"

Jayakumark — Mon, 13 Apr 2026 14:55:32 +0000

Thanks for considering it. So how are you doing it now ? Who is generating the plan inside of issue ex: https://github.com/jonwiggins/optio/issues/418

Do you just add the Issue Title like this "feat: CLI improvements — status dashboard, workflow commands, shell completions" and it generated the plan in issue body and started working on it OR is the plan generated by another ai agent and copied to issue body for pickup by optio ?

New comment by Jayakumark in "Claude Managed Agents"

Jayakumark — Thu, 09 Apr 2026 12:50:03 +0000

@jawiggins saw your repo it looks like openAI symphony but better as it works across multiple agents and issue trackers and the feedback loop is great . One feature request though - can you add plan mode ? Your issues are so detailed it becomes plan to implement (but I guess your plan mode is currently happening outside of GitHub issues ) but let’s say issue is “implement support for plan mode” there should be back and forth with agent with issue tags pointing to opus max and/or plan mode - so we can correct agents plan back and forth and once tag is removed it can start implementing or something similar ?

New comment by Jayakumark in "Your File System Is Already A Graph Database"

Jayakumark — Wed, 08 Apr 2026 17:53:57 +0000

Interesting approach but how do you download Google Docs, XLS and Slack threads etc.. and how is it saved in obsidian, are they all converted to markdown before saving or summarized to extract key topics and saved. What about images ?

New comment by Jayakumark in "Professional video editing, right in the browser with WebGPU and WASM"

Jayakumark — Sat, 21 Mar 2026 22:55:33 +0000

great project but non commercial license, makes me not to go near it.

New comment by Jayakumark in "MCP is dead; long live MCP"

Jayakumark — Sat, 14 Mar 2026 22:17:03 +0000

Can you please share source code for the Resources/Prompts example ?

New comment by Jayakumark in "Rust implementation of Mistral's Voxtral Mini 4B Realtime runs in your browser"

Jayakumark — Tue, 10 Feb 2026 03:43:43 +0000

Awesome work, Would be good to have it work with handy.computer. Also are there plans to support streaming ?

New comment by Jayakumark in "Claude is a space to think"

Jayakumark — Wed, 04 Feb 2026 20:06:51 +0000

Since you asked for it, here is my steelman argument : Everything can cause harm - it depends on who is holding it , how determined are they , how easy is it and what are the consequences. Open source will make this super easy and cheap. 1. We are already seeing AI Slop everywhere Social media Content, Fake Impersonation - if the revenue from whats made is larger than cost of making it , this is bound to happen, Open models can be run locally with no control, mostly it can be fine tuned to cause damage - where as closed source is hard as vendors might block it. 2. Less skilled person can exploit or create harmful code - who otherwise could not have. 3. Remove Guards from a open model and jailbreak, which can't be observed anymore (like a unknown zero day attack) since it may be running private. 4. Almost anything digital can be Faked/Manipulated from Original/Overwhelmed with false narratives so they can rank better over real in search.

New comment by Jayakumark in "Claude is a space to think"

Jayakumark — Wed, 04 Feb 2026 18:24:59 +0000

They are the most anti-opensource AI Weights company on the planet, they don't want to do it and don't want anyone else to do it. They just hide behind safety and alignment blanket saying no models are safe outside of theirs, they wont even release their decommissioned models. Its just money play - Companies don't have ethics , the policies change based on money and who runs it - look at google - their mantra once was Don't be Evil.

https://www.anthropic.com/news/anthropic-s-recommendations-o...

Also codex cli, Gemini cli is open source - Claude code will never be - it’s their moat even though 100% written by ai as the creator says it never will be . Their model is you can use ours be it model or Claude code but don’t ever try to replicate it.

New comment by Jayakumark in "Sandboxing AI Agents in Linux"

Jayakumark — Tue, 03 Feb 2026 21:04:34 +0000

Saw something last week using bubblewrap as well in hn github.com/Use-Tusk/fence

New comment by Jayakumark in "Moltworker: a self-hosted personal AI agent, minus the minis"

Jayakumark — Thu, 29 Jan 2026 20:03:57 +0000

Main problem to solve is Prompt Injection protection from Websites, emails. If cloudflare could proxy all the URLs outgoing from an agent, scrub away or block Prompt injection sites/pages/emails/chats , that's a product i might find valuable.