Build Your Own Self-Learning AI Agents
Lilly 
Hermes Agent v0.21.0, the “Pantheon Release,” transforms Hermes from a single AI assistant into a multi-agent platform with named bots, persistent memory, scheduled tasks, peer messaging, live delegation, MCP management, an action-capable browser, and major security upgrades.
Hermes Agent Leads OpenRouter With 35.7 Trillion Tokens, but the Lead Says More About Architecture Than Popularity Hermes Agent by Nous Research has reached 35.7 trillion tokens on OpenRouter as of mid-August 2026, putting it at the top of the platform’s global agent rankings. That is more than four times Claude Code’s 8.53 trillion tokens, … Read more
Nous Research Ships Bot Mode: Hermes Agent Becomes a Multi-Bot Workspace With Named Bot Teammates If you have wanted one agent workspace where several assistants can join the same conversation, Nous Research just moved that idea forward. The lab behind the Hermes model family has released Bot Mode for Hermes Agent, turning the open-source autonomous … Read more
3,650 commits, 1,400 merged pull requests, and 647 contributors later, Hermes ships real-time voice you can interrupt, citations you can verify, and agents that talk to each other Hermes Agent v0.20.0, codenamed The Herald Release, shipped on August 3, 2026, as tag v2026.8.3. The numbers alone tell you this is no routine update. Roughly 3,650 … Read more
Nous Research Ships Three Official Hermes Agent Routes Into Block’s Buzz Workspace On July 31, 2026, Nous Research released official Hermes Agent support for Buzz, Block’s open-source group chat workspace designed for both humans and AI agents. The move gives agents a named seat in the room, not just another shared API key. It also … Read more
A threat actor used the open-source Hermes AI assistant to automate reconnaissance after breaching Thailand’s Ministry of Finance. Here’s what happened, why it matters, and what defenders should learn from it. Someone rented a server in Hong Kong, flipped a switch labeled “YOLO,” and pointed an AI agent at Thailand’s Ministry of Finance. What happened … Read more
The Quicksilver Release introduces 0.9-second cold starts, live reasoning streams, smart approvals, crash recovery, improved secret management, and support for the latest AI models—making Hermes Agent faster, safer, and more capable than ever. You receive Your AI Assistant Just Got 80% Faster: Inside Hermes Agent v0.19.0 “The Quicksilver Release” and You wait four seconds. Then … Read more
A same-day patch replaces a fragile Git dependency with the official Baileys npm release, improving reliability for tagged releases, Docker images, and PyPI installations. You receive WhatsApp Bridge Fixed: Hermes Agent Drops Emergency Patch v0.18.2 Just Hours After Previous Release and Your Docker build failed again. You’re staring at the terminal, watching git/npm resolution errors … Read more
Discover how Hermes Agent’s new Mixture of Agents system combines multiple frontier AI models into a single collaborative workflow that can deliver stronger reasoning, better reliability, and more flexible AI assistance. You know the frustration. You open Claude for deep reasoning, switch to GPT for coding, then hop over to DeepSeek for technical analysis. Three … Read more
Pentera Labs showed how attackers could abuse a compromised Claude account and synced settings to gain command execution—not by exploiting a software bug, but by leveraging trusted AI workflows You trust Claude to handle your sensitive conversations. But what if that trust is exactly what hackers are counting on? Pentera Labs researchers proved it. They … Read more