<rss version="2.0" xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Hacker News: jordanedev</title><link>https://news.ycombinator.com/user?id=jordanedev</link><description>Hacker News RSS</description><docs>https://hnrss.org/</docs><generator>hnrss v2.1.1</generator><lastBuildDate>Mon, 15 Jun 2026 08:43:10 +0000</lastBuildDate><atom:link href="https://hnrss.org/user?id=jordanedev" rel="self" type="application/rss+xml"></atom:link><item><title><![CDATA[New comment by jordanedev in "Show HN: Optio – Orchestrate AI coding agents in K8s to go from ticket to PR"]]></title><description><![CDATA[
<p>That's exactly what i did personnaly on my oss repo <a href="https://github.com/ysa-ai/ysa" rel="nofollow">https://github.com/ysa-ai/ysa</a><p>I want to run my agents fully isolated with headless mode. To achieve that safely you have to run a proxy</p>
]]></description><pubDate>Fri, 27 Mar 2026 15:55:45 +0000</pubDate><link>https://news.ycombinator.com/item?id=47544393</link><dc:creator>jordanedev</dc:creator><comments>https://news.ycombinator.com/item?id=47544393</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47544393</guid></item><item><title><![CDATA[Show HN: I sandboxed OpenAI's Symphony orchestrator in one file using YSA]]></title><description><![CDATA[
<p>YSA is an open source sandbox runtime for AI agents. 
Each task runs in an isolated Podman container with a network proxy that filters every outbound request.<p>This example repo shows how to connect it to Symphony (OpenAI's agent orchestrator) — the entire integration is one new file, runner/ysa.ts.<p>The demo shows an agent attempting to POST data to an external URL and getting blocked by the network proxy.<p>Demo Repo: <a href="https://github.com/ysa-ai/ysa-symphony-example" rel="nofollow">https://github.com/ysa-ai/ysa-symphony-example</a>
YSA: <a href="https://github.com/ysa-ai/ysa" rel="nofollow">https://github.com/ysa-ai/ysa</a></p>
<hr>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=47495199">https://news.ycombinator.com/item?id=47495199</a></p>
<p>Points: 2</p>
<p># Comments: 0</p>
]]></description><pubDate>Mon, 23 Mar 2026 21:14:20 +0000</pubDate><link>https://github.com/ysa-ai/ysa-symphony-example</link><dc:creator>jordanedev</dc:creator><comments>https://news.ycombinator.com/item?id=47495199</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47495199</guid></item><item><title><![CDATA[Show HN: YSA – Sandbox for AI agents with outbound network control]]></title><description><![CDATA[
<p>I've been running Claude CLI on production codebases and got uncomfortable not knowing what could leak outbound — especially in case of prompt injection.<p>YSA runs Claude CLI inside a rootless Podman container with a git worktree per task. Each container gets:
  - A MITM proxy (L7): TLS termination, GET-only enforcement, body blocked, URL length cap, outbound byte budget, rate limiting per domain
  - iptables rules via OCI hook (L3/L4): all outbound traffic blocked except through the proxy
  - seccomp whitelist, all capabilities dropped, read-only filesystem, no-new-privileges<p>The repo includes a basic dashboard to run tasks in parallel and visualize per-container network traffic in real time.<p>Early but functional — I use it daily.<p>Especially curious about feedback on the security model and proxy bypass detection.</p>
<hr>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=47261461">https://news.ycombinator.com/item?id=47261461</a></p>
<p>Points: 2</p>
<p># Comments: 0</p>
]]></description><pubDate>Thu, 05 Mar 2026 13:41:16 +0000</pubDate><link>https://github.com/ysa-ai/ysa</link><dc:creator>jordanedev</dc:creator><comments>https://news.ycombinator.com/item?id=47261461</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47261461</guid></item></channel></rss>