← Directory

Hermes Agent

Hermes Agent is a local, self-improving AI agent built by Nous Research, with a built-in learning loop that creates skills from experience, improves them…

  • AI
  • Other
  • Productivity
  • Tools & Utilities
Hermes Agent is a local, self-improving AI agent built by Nous Research, with a built-in learning loop that creates skills from experience, improves them during use, and builds a deepening model of who you are across sessions. It runs on everything from a low-cost virtual private server (VPS) to a GPU cluster and is not tied to your laptop, so you can talk to it from services like Telegram while it works on a remote machine. It supports any model provider you want, including Nous Portal, OpenRouter, OpenAI, or your own endpoint.

Platform availability

Available on 6 of 6 install platforms

Also on Docker Hub and GitHub

Health score

73/100 Good

Maintained
70last commit 3 days ago
Popular
100251,654 GitHub stars
Easy to install
856 install platforms, install notes, Docker image
Light to run
208 GB minimum RAM, runs on ARM
How is this calculated?

A 0-100 score computed nightly from four factors: maintained (40%: recent commits and steady activity), popular (25%: GitHub stars, log scale), easy to install (20%: platforms, install notes, setup guides, Docker image) and light to run (15%: minimum RAM, ARM support). Factors without data are left out and the rest are rescaled.

Availability: platform listings confirmed today, links checked 9 days ago

GitHub stars
251,654
Open issues
47779
Last commit
2026-10-06
Latest release
v2026.9.24
License
MIT
Activity
stale

Checked 3 days ago - source: GitHub (NousResearch/hermes-agent)

Resources & Compatibility

Minimum requirements: 8 GB RAM. ARM (e.g. Raspberry Pi) is supported.

Checked 10 days ago - source: Docker Hub image tags and published docs

First-install notes

  • Check it works before using it The installer adds hermes to PATH (the list of places your terminal checks for commands), so open a terminal and run the built-in check hermes doctor, then test a simple message with hermes chat -q 'Hello'. If the command is not found or the test chat fails, the install or model connection is not finished. source
  • Unraid template configuration The Unraid template runs the agent's Gateway and Dashboard, exposing the Dashboard web user interface on port 9119 and the API on port 8642. Set HERMES_UID and HERMES_GID to your own user and group IDs; the template also uses a shared volume to store Hermes sources. source

Fetched 3 days ago - each note links to its source

Alternatives (10)

  • Goose OSS - An Open Source AI Agent (think Claude CoWork) that help you to automates engineering tasks seamlessly with local execution, customization,…
  • Khoj - Open-source platform supporting local and cloud AI chat, semantic search, document retrieval, and image generation across multiple devices…
  • Kimi - AI tool for reasoning across math, coding, and image analysis, processing up to 128k tokens, handling visual data, benchmarks, and chain-of…
  • Maid (AI) - Maid is a cross-platform Flutter app for interfacing with GGUF / llama.cpp models locally, and with Ollama and OpenAI models remotely.
  • Manus - Transforms thoughts into actions with personalized travel itineraries, stock analysis, and educational content while autonomously completin…
  • Odysseus - Self-hosted AI workspace with chat, agents, deep research, documents, email, calendar, and model Cookbook.
  • OpenClaw - OpenClaw is a self-hosted AI assistant gateway that connects Claude and other large language models (LLMs) to messaging platforms such as D…
  • Poe - Poe is a web-based AI platform that hosts multiple assistant bots—including Claude and various GPT and image/audio models—to provide conver…
  • Together Chat - Together Chat is a next-generation consumer app designed to let you interact seamlessly with today's most popular open-source models, inclu…
  • nanoclaw - NanoClaw is a lightweight, secure personal AI assistant that runs each agent in its own isolated container on your own server.

Checked 7 days ago - source: AlternativeTo

Common questions

How can I confirm the Hermes Agent terminal install worked?

After installing, open a terminal and run hermes doctor, then test a simple message with hermes chat -q 'Hello'. If the command is not found or the test chat fails, the install or model connection is not finished.

How do I connect a model and the Tool Gateway tools in one step?

Run hermes setup --portal, which uses one OAuth to cover a model plus web search, image generation, TTS, and browser tools.

Can I reach Hermes Agent from messaging apps rather than only the CLI?

Yes, it connects to Telegram, Discord, Slack, WhatsApp, Signal, and CLI from a single gateway process.

Can I use a model endpoint other than Nous Portal?

You can use OpenRouter, OpenAI, your own endpoint, or other supported providers, and switch with hermes model.

Can I run unattended scheduled tasks with Hermes Agent?

The built-in cron scheduler can run natural-language automations such as daily reports, nightly backups, and weekly audits with delivery to any platform.

Answers sourced from github.com, hermes-agent.nousresearch.com, hermes-agent.nousresearch.com

Community

Collected 10 days ago - public community threads