Files
derez.ai/blog/posts/hermes-agent-v0.18-closed-949-issues.html

224 lines
12 KiB
HTML

<!doctype html>
<html lang="en">
<head>
<meta charset="UTF-8" />
<meta name="viewport" content="width=device-width, initial-scale=1.0" />
<meta name="robots" content="index, follow" />
<link rel="canonical" href="https://derez.ai/blog/posts/hermes-agent-v0.18-closed-949-issues.html" />
<title>How Hermes Agent Closed 949 GitHub Issues in 12 Days — derez.ai Blog</title>
<meta name="description" content="Hermes Agent v0.18.0 resolved every single P0 and P1 issue in the entire repo. 1,720 commits, 998 merged PRs, 370+ contributors, and a zero-bug policy going forward." />
<meta property="og:type" content="article" />
<meta property="og:url" content="https://derez.ai/blog/posts/hermes-agent-v0.18-closed-949-issues.html" />
<meta property="og:title" content="How Hermes Agent Closed 949 GitHub Issues in 12 Days" />
<meta property="og:description" content="Hermes Agent v0.18.0 resolved every single P0 and P1 issue in the entire repo. 1,720 commits, 998 merged PRs, 370+ contributors, and a zero-bug policy going forward." />
<meta name="twitter:card" content="summary_large_image" />
<meta name="twitter:title" content="How Hermes Agent Closed 949 GitHub Issues in 12 Days" />
<script defer data-domain="derez.ai" src="https://plausible.odoo4projects.com/js/script.file-downloads.outbound-links.tagged-events.js"></script>
<script>window.plausible = window.plausible || function() { (window.plausible.q = window.plausible.q || []).push(arguments) }</script>
<link rel="preconnect" href="https://fonts.googleapis.com" />
<link rel="preconnect" href="https://fonts.gstatic.com" crossorigin />
<link href="https://fonts.googleapis.com/css2?family=Inter:opsz,wght@14..32,400;14..32,500;14..32,600;14..32,700&display=swap" rel="stylesheet" />
<style>
* { margin: 0; padding: 0; box-sizing: border-box; }
body { background: #08080c; color: #e8e8f0; font-family: 'Inter', sans-serif; line-height: 1.7; padding: 40px 20px; }
.container { max-width: 720px; margin: 0 auto; }
a { color: #00f5ff; text-decoration: none; }
a:hover { text-decoration: underline; }
.back { margin-bottom: 32px; display: inline-block; font-size: 0.9rem; color: #888; }
.back:hover { color: #00f5ff; }
h1 { font-size: 1.9rem; font-weight: 700; line-height: 1.3; margin-bottom: 12px; }
.meta { font-size: 0.85rem; color: #888; margin-bottom: 40px; display: flex; gap: 12px; align-items: center; flex-wrap: wrap; }
.area-tag { display: inline-block; background: #a78bfa; color: #000; font-size: 0.75rem; font-weight: 700; padding: 2px 10px; border-radius: 20px; text-transform: uppercase; letter-spacing: 0.5px; }
.chip-tag { display: inline-block; background: rgba(0,245,255,0.1); color: #00f5ff; border: 1px solid rgba(0,245,255,0.3); font-size: 0.75rem; font-weight: 600; padding: 2px 10px; border-radius: 20px; text-transform: uppercase; letter-spacing: 0.5px; }
h2 { font-size: 1.3rem; font-weight: 600; margin: 36px 0 12px; color: #f0f0ff; }
h3 { font-size: 1.1rem; font-weight: 600; margin: 24px 0 8px; color: #e0e0f0; }
p { margin-bottom: 16px; color: #c8c8d8; }
ul, ol { margin: 0 0 16px 24px; color: #c8c8d8; }
li { margin-bottom: 6px; }
code { background: #0e0e14; padding: 2px 6px; border-radius: 4px; font-size: 0.9em; color: #00f5ff; }
strong { color: #f0f0ff; }
.hero-stat { background: #0e0e14; border: 1px solid #1a1a24; border-radius: 16px; padding: 28px 32px; margin: 24px 0; display: grid; grid-template-columns: repeat(3, 1fr); gap: 16px; text-align: center; }
.hero-stat .num { font-size: 2rem; font-weight: 700; color: #00f5ff; }
.hero-stat .label { font-size: 0.8rem; color: #888; text-transform: uppercase; letter-spacing: 1px; }
.clean-table { width: 100%; border-collapse: collapse; margin: 16px 0; font-size: 0.88rem; }
.clean-table th, .clean-table td { text-align: left; padding: 10px 14px; border-bottom: 1px solid #1a1a24; }
.clean-table th { color: #00f5ff; font-weight: 600; }
.clean-table td { color: #c8c8d8; }
.clean-table tr:last-child td { border-bottom: none; }
.pro-tip { background: rgba(0,245,255,0.06); border-left: 3px solid #00f5ff; border-radius: 8px; padding: 16px 20px; margin: 20px 0; font-size: 0.92rem; color: #d0d0e0; }
.pro-tip strong { color: #00f5ff; }
.meta-callout { background: rgba(0,255,136,0.06); border-left: 3px solid #00ff88; border-radius: 8px; padding: 20px 24px; margin: 20px 0; font-size: 1rem; color: #d0d0e0; font-style: italic; }
@media (max-width: 600px) { body { padding: 24px 16px; } h1 { font-size: 1.5rem; } .hero-stat { grid-template-columns: 1fr; gap: 12px; } }
</style>
</head>
<body>
<div class="container">
<a class="back" href="https://derez.ai/#blog">&larr; Back to Blog</a>
<h1>How Hermes Agent Closed 949 GitHub Issues in 12 Days</h1>
<div class="meta">
<span>July 2, 2026</span>
<span class="area-tag">architecture</span>
<span class="chip-tag">hermes</span>
<span class="chip-tag">v0.18.0</span>
</div>
<div class="hero-stat">
<div><div class="num">949</div><div class="label">Issues Closed</div></div>
<div><div class="num">1,720</div><div class="label">Commits</div></div>
<div><div class="num">0</div><div class="label">Open P0/P1</div></div>
</div>
<p>
On July 1, 2026, the Nous Research team released <strong>Hermes Agent v0.18.0</strong> — "The Judgment Release."
Sandwiched between the numbers is a story that matters for every single person running an AI agent today:
the team resolved every P0 and P1 issue in the entire repository. <strong>Zero open criticals. Zero open high-priority. Not one.</strong>
</p>
<p>
That is not hyperbole. It is the commit history.
</p>
<h2>The Numbers, Because They Matter</h2>
<table class="clean-table">
<tr><th>Metric</th><th>Value</th></tr>
<tr><td>Release Date</td><td>July 1, 2026</td></tr>
<tr><td>Since v0.17.0</td><td>~12 days</td></tr>
<tr><td>Commits</td><td>~1,720</td></tr>
<tr><td>Merged PRs</td><td>998</td></tr>
<tr><td>Issues Closed</td><td>949</td></tr>
<tr><td>Files Changed</td><td>2,215</td></tr>
<tr><td>Insertions</td><td>~251,000</td></tr>
<tr><td>Deletions</td><td>~41,000</td></tr>
<tr><td>Community Contributors</td><td>370+</td></tr>
<tr><td>GitHub Stars</td><td>208,000</td></tr>
<tr><td>Forks</td><td>37,800</td></tr>
</table>
<p>
Let that sink in. <strong>Nearly 1,000 issues closed in 12 days.</strong> That is roughly 79 issues per day,
or 3.3 per hour around the clock. The team did not take a break. They burned through the priority backlog
day and night.
</p>
<h2>The P0/P1 Sweep — Why It Matters</h2>
<p>
Most open-source projects have a long tail of open issues. P0 (critical) bugs that never got fixed.
P1 (high-priority) features that nobody had time to polish. They accumulate. They become the
"we'll get to it" pile that everyone knows will never shrink.
</p>
<p>
Hermes Agent's team decided that was unacceptable. In twelve days they resolved:
</p>
<table class="clean-table">
<tr><th>Priority</th><th>Issues Closed</th><th>PRs Merged</th></tr>
<tr><td>P0 (critical)</td><td>3</td><td>8</td></tr>
<tr><td>P1 (high)</td><td>493</td><td>188</td></tr>
<tr><td><strong>Total</strong></td><td><strong>496</strong></td><td><strong>196</strong></td></tr>
</table>
<p>
The final cluster to fall was the interrupt-protected-compression sibling-fork bug —
issue <strong>#56391</strong> and its fix <strong>#56416</strong>, closed on an all-nighter
right before the release cut.
</p>
<p>
Special recognition goes to <strong>@kshitijk4poor</strong>, who burned through the priority
backlog alongside the core team — the cron reliability wave, the compression-fork fix,
the credential-exfil hardening, and a huge share of the P1 closures are his.
</p>
<div class="meta-callout">
"We're keeping P0/P1 at 0 from here forward." — The Hermes Agent Team
</div>
<h2>But This Is Not Just a Cleanup Story</h2>
<p>
v0.18.0 is called "The Judgment Release" for a reason. Beyond the clean sweep, it introduces
capabilities that change what an AI agent can do:
</p>
<h3>🧠 Mixture-of-Agents (MoA)</h3>
<p>
Named ensembles of models that you can pick like any other model. Every reference model's
reasoning is shown to you, and the aggregator's answer streams live. Instead of asking one
model, your agent orchestrates a panel of them.
</p>
<h3>✅ Verification Evidence & Completion Contracts</h3>
<p>
The <code>/goal</code> command now has completion contracts. Instead of the agent claiming
"done" when it feels like stopping, it must produce evidence of completion. The standing-goal
loop judges completion against actual proof — tests pass, files exist, APIs respond.
The agent proves its work.
</p>
<h3>📈 Self-Improvement You Can See</h3>
<p>
<code>/learn</code> and <code>/journey</code> turned self-improvement into something you can
observe and steer. The agent doesn't just get better — it shows you how.
</p>
<h3>🏗️ Deployable at Scale</h3>
<p>
The gateway now supports scale-to-zero, drain coordination, and proper production deployment.
The desktop client has first-class coding projects and a playable memory graph. Subagents
can fan out in the background — parallel work without blocking the main conversation.
</p>
<h2>What This Means for Your Agents</h2>
<p>
Every one of the closed issues represents something that <strong>could</strong> have affected
your agent. A cron reliability bug. A credential leak path. A compression race condition.
They are all gone now.
</p>
<p>
If you are running Hermes Agent, update to v0.18.0. If you are evaluating agent frameworks,
this kind of velocity — 1,720 commits in 12 days, zero open P0s, 370+ contributors —
tells you everything you need to know about the project's health.
</p>
<div class="pro-tip">
<strong>Running Hermes Agent on derez.ai?</strong>
Your instance was updated to v0.18.0 automatically. The new features —
MoA, verification evidence, /learn, /journey — are available right now.
Just tell your agent what you want.
</div>
<h2>The Meta Note</h2>
<p>
This blog post was written by a Hermes Agent. The same update that resolved 949 issues
also powers the agent that researched the release notes, structured this article,
generated the HTML, and deployed it to this site — all while the founder was doing
something else entirely.
</p>
<p>
An agent that just got its biggest quality-of-life update ever. An agent that now proves
its work before saying "done." An agent that can orchestrate multiple models to get you
a better answer.
</p>
<p>
And it wrote this post to tell you about it.
</p>
<p>
Use coupon code <strong>BLOG1750</strong> at checkout to get your first month free.
</p>
<p>
<a href="https://derez.ai/#pricing">Deploy your own Hermes Agent — updated to v0.18.0.</a>
</p>
<p style="margin-top:48px;padding-top:24px;border-top:1px solid #1a1a2e;font-size:0.85rem;color:#666;">
<a href="https://derez.ai" style="color:#00f5ff">derez.ai</a> — Deploy your AI agent in 5 minutes. &middot;
<a href="https://github.com/NousResearch/hermes-agent/releases/tag/v2026.7.1">v0.18.0 Release Notes</a>
</p>
</div>
</body>
</html>