Hermes Agent
Nous Research's open-source agent with persistent memory, messaging gateways and scheduled jobs.
0 members list Hermes Agent, unchanged over the last 12 weeks, data as of 17 November 2026
Members who list Hermes Agent in their Stack, by week.
Members who list Hermes Agent
Be the first to add Hermes Agent
Nobody on Stackness runs Hermes Agent yet. Add it to your stack and you're the first member running it.
Homebrew analytics installs: 2,386 installs (2026) to 2,595 installs (2026)
Imported from Homebrew analytics, last reading Oct 2026
About Hermes Agent
Hermes Agent is an open-source artificial intelligence agent developed by NousResearch that runs locally on a user's computer. It maintains persistent memory of conversations and learned skills, allowing it to build on previous interactions over time. The agent integrates with multiple messaging platforms including Telegram, Discord, Slack, WhatsApp, Signal, and email, as well as a command-line interface, providing a unified interface across different communication channels.
Developers can deploy Hermes Agent on various computing environments, from local machines to cloud infrastructure, with support for Docker, SSH, Singularity, and other backends. The tool offers capabilities such as web search, browser automation, task scheduling in natural language, and isolated sandboxed execution. Hermes Agent is distributed under the MIT license and is free to use. Optional paid services through Nous Portal provide access to additional models and hosted infrastructure, though users can configure their own model providers.
Checked 11 November 2026.
Nobody on Stackness runs Hermes Agent yet.
Sign up and add itPosts about Hermes Agent
- Access control for multi-user AI agents: the credential proxy, the usage cap and why an in-repo monitor is neither
A multi-user agent needs each call checked as the person it acts for, outside the agent's reach. A shared API key and a monitor in the repo fail that.
- DeepSeek Harness vs Claude Code: which harnesses lock you to one model, and what breaks when you switch
DeepSeek Harness runs any provider's model, Claude Code only Claude's. The lock-in sits in plugins, hooks, sessions and config, and those do not move.
- Can a decision model prune your coding agent's context? What fast-jev-compaction keeps, costs and drops
fast-jev-compaction prunes in a second, not 30. At its default threshold it keeps almost no tool results, and a scorer that always says no cuts as much.