A Competitor to OpenClaw Emerges

2026-06-18 · Source: The Information · Field: Technology & Digital — Artificial Intelligence & Machine Learning, Software Development & Engineering, Emerging Technologies & & Innovation · Depth: Novice, quick

Summary

Hermes, an AI agent software developed by Nous Research, has emerged as a significant competitor to OpenClaw, an established open-source AI agent. Hermes runs locally on user devices, automating tasks such as code writing, web searches, and message sending. Its key differentiator is the ability to teach itself tasks over time by automatically generating "skills" or instructional manuals. This self-learning occurs when it completes complex tasks requiring more than five "tool calls" or discovers solutions after encountering dead ends. According to ClawCharts, Hermes recently surpassed OpenClaw in new GitHub contributors over the last 30 days, indicating strong developer engagement. This growth, coupled with OpenClaw's ongoing challenges in evolving into reliable software, positions Hermes and other alternatives like Nvidia's NemoClaw for potential breakthrough. Nous Research, founded in 2023, has secured \$70 million in funding from investors including Paradigm, OSS Capital, and Distributed Global.

Key takeaway

For AI Engineers evaluating open-source agent software, Hermes presents a compelling alternative to OpenClaw. Its self-teaching "skills" generation capability offers a more adaptive automation solution for local tasks like coding or web searches. You should consider exploring Hermes, especially given its recent surge in GitHub contributors and OpenClaw's reliability challenges. Integrating such an agent could streamline your development workflows and enhance task automation efficiency.

Key insights

Hermes is a self-teaching AI agent that automates local tasks, gaining developer traction as an OpenClaw alternative.

Principles

• AI agents can self-teach by writing "skills" from task execution.
• Complex tasks (e.g., >5 tool calls) trigger skill generation.
• Developer engagement indicates open-source project vitality.

Method

Hermes's method involves automatically writing "skills" (instruction manuals) when it completes complex tasks (e.g., >5 tool calls) or finds working solutions after dead ends, enabling self-teaching.

In practice

• Automate local tasks like coding or web searching.
• Use agents that self-learn from complex interactions.
• Monitor GitHub contributor growth for project viability.

Topics

• AI Agents
• Hermes
• OpenClaw
• Open-source Software
• Task Automation
• Self-learning AI

Best for: Machine Learning Engineer, AI Product Manager, Product Manager, AI Engineer, Director of AI/ML, Tech Journalist

Related on AIssential

• Hermes Agent The 24/7 Self-Evolving AI Agent! — Hermes Agent is a self-improving AI that learns from interactions, builds skills, and adapts without explicit fine-tuning.
• OpenClaw + OpenCode Turns Your AI Into a Full Autonomous Engineering Team! Automate Your Code! — Combining OpenClaw and OpenCode creates an autonomous AI engineering workflow, with Agent Trust Hub mitigating local execution risks.
• My Most INSANE AI Agent Ever (OpenClaw Clone) — A simplified AI agent system automates complex tasks, including video creation, by integrating browser-based interactions and scheduled jobs.
• From skeptic to true believer: How OpenClaw changed my life | Claire Vo — Specialized AI agents, though challenging to set up, offer profound utility by offloading diverse tasks and enhancing personal and professional efficiency.
• OpenClaw Goes to OpenAI — OpenClaw's rapid growth and creator's move to OpenAI signal a major shift towards practical, autonomous AI agents.
• I Gave an AI Agent the Keys to My Life (Here's What Happened) — Radek Sienkiewicz (@velvetshark-com) — Incremental integration of AI agents, starting small and building trust, leads to sophisticated personal automation.

Open in AIssential →

Editorial summary, takeaway, and curation by AIssential. Original article published by The Information.