Hermes Agent – Open-source AI agent with persistent memory
Nous Research’s Hermes Agent is a self-hosted open-source AI agent with persistent local memory.
Hermes Agent is an open-source autonomous agent by Nous Research, designed to run on your own server or machine with persistent local memory. It offers messaging gateways, scheduled automations, browser control, parallel sub-agents, reusable skills, and multiple LLM provider options. The project also targets MLOps and research workflows, including tool-calling trajectory generation, RL experiments, and exportable fine-tuning data.
Hermes Agent is an open-source autonomous AI agent released by Nous Research. It is not positioned as a simple chatbot or an IDE-bound coding copilot, but rather as a personal agent that can be installed on your own server or local machine and run continuously over time. Its core selling point is persistent memory: it remembers user preferences, project context, and execution environment, so subsequent tasks don't require re-explaining the background from scratch. The official site also emphasizes that data is stored locally on the user's machine under ~/.hermes/, with no tracking or data collection, and it is MIT-licensed — making it particularly appealing to developers who value auditability and data sovereignty.
Free shows the 3-line summary; Pro unlocks the full deep summary (~300 words) so you never have to click through.
See Pro plans →Want the original English / full article?
Read on Hacker News (AI keywords) →Related
Summaries are AI-generated; the original article is authoritative.