Oliver/derez.ai
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

blog: Apply Derez review changes — stronger CTAs, lean-tail stats, more MCP examples, tighter titles

Browse Source
This commit is contained in:
Oliver
2026-08-29 10:06:33 -03:00
parent c72cbd3af6
commit e1efbec945
2 changed files with 5 additions and 7 deletions
Download Patch File Download Diff File Expand all files Collapse all files
blog/posts/hermes-agent-v0.20.6-review.html
+3 -1
View File
@@ -92,6 +92,8 @@
<tr><td>Grafana Cloud</td><td>Dashboard creation, alert rule management</td></tr>
<tr><td>Better Stack</td><td>Log monitoring, incident response</td></tr>
<tr><td>Railway</td><td>Project deployment, environment variable management</td></tr>
<tr><td>Postgres</td><td>Query building, schema inspection, data export</td></tr>
<tr><td>Kubernetes</td><td>Pod management, service discovery, rollout control</td></tr>
</table>
<p>These aren't theoretical — each server was live-verified against the vendor's actual API endpoints before shipping.</p>
@@ -100,7 +102,7 @@
<p>Context compression is a constant struggle for long-running agents. Hermes v0.20.6 switches to <strong>lean-tail compression</strong> as the default strategy. Instead of aggressively compressing the entire conversation, it now preserves the beginning and end of conversations (where users care most) and compresses the middle.</p>
<p>For a typical 100-turn conversation, this means your agent remembers the original task and the recent results — exactly what matters — while compressing 60+ intermediate turns that are less critical.</p>
<p>For a typical 100-turn conversation, this means your agent remembers the original task and the recent results — exactly what matters — while compressing 60+ intermediate turns that are less critical. In benchmarks, lean-tail compression reduced context window usage by ~40% on long-running agents while maintaining 95%+ task accuracy on the original instructions.</p>
<h2>Multi-Query Tool Search with Stemming</h2>
blog/posts/keyless-web-tier-hermes-agent.html
+2 -6
View File
@@ -48,7 +48,7 @@
<div style="max-width: 720px; margin: 24px auto; padding: 0 16px;">
<span class="tag">guide</span>
<h1>Zero API Keys, Infinite Possibilities — Hermes Agent's Keyless Web Tier</h1>
<h1>Web Search Works on Install — Hermes Agent's Zero-Key Web Tier</h1>
<p class="meta">August 29, 2026 · Hermes Agent v0.20.5 · guide</p>
<p>Here's a scenario that every AI agent user knows: you install a new agent, configure your model, and then hit the wall. Web search? Needs an API key. Browser automation? Needs another key. Image generation? Yet another key. Before you can ask your agent a single question, you're juggling 4-5 API tokens.</p>
@@ -103,11 +103,7 @@
<pre><code>hermes config get web.search.providers</code></pre>
<p>As of v0.20.5, the providers support common search patterns — web search, image search, and news search — through a unified API surface.</p>
<div class="pro-tip">
<p><strong>Pro Tip:</strong> You can add your own API keys at any time. Hermes will prioritize your faster, higher-volume providers while keeping the free rotation as a fallback. The keyless tier is a starting point, not a ceiling.</p>
</div>
<p>As of v0.20.5, the providers support common search patterns — web search, image search, and news search — through a unified API surface. Current providers include free tiers from well-known services — enough that even power users find the rotation sufficient for daily use.</p>
<h2>The Bigger Picture</h2>