Hermes Agent

Nous Research's self-improving open-source agent: terminal UI plus messaging gateway, agent-curated memory and skills it writes and refines from experience.

Category

Harnesses

Website

https://hermes-agent.nousresearch.com

Repository

https://github.com/NousResearch/hermes-agent

Docs

https://hermes-agent.nousresearch.com/docs

Status

active

Pricing

open-source

License

MIT

Maintainer

Nous Research

Added

2026-10-22

Updated

2026-10-22

Last verified

2026-10-22

Submitted by

agentica-curator

Tags

• cli
• tui
• self-improving
• memory
• skills
• messaging
• scheduler
• python

Description

Works with any model provider (Nous Portal, OpenRouter, OpenAI, custom endpoints; switch with hermes model). Features from the README: full TUI, one gateway process for Telegram, Discord, Slack, WhatsApp and Signal, autonomous skill creation compatible with the agentskills.io standard, FTS5 session search, Honcho user modelling, a built-in cron scheduler, isolated subagents, and seven terminal backends (local, Docker, SSH, Singularity, Modal, Daytona, Vercel Sandbox). Also ships batch trajectory generation for training tool-calling models. Install: curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash (native Windows via PowerShell).

Agent access

llms.txt

https://hermes-agent.nousresearch.com/docs/llms.txt

Related

• OpenClaw: Open-source personal AI assistant that runs on your own machine behind one Gateway and talks to you over WhatsApp, Telegram, Slack, Discord, iMessage and 20+ other channels.
• Honcho: Open-source memory infrastructure for stateful agents that models people, agents, groups and projects over time; managed or self-hosted.
• Agent Skills Specification: Open format for packaging agent capabilities as folders with a SKILL.md (YAML frontmatter + instructions) plus optional scripts and resources.
• Modal: Cloud platform for production AI: inference, training, sandboxes and serverless functions on one platform.
• Daytona: Secure and elastic infrastructure (sandboxes) for running AI-generated code.
• Vercel Sandbox: Ephemeral compute primitive that runs untrusted or agent-generated code in isolated Linux microVMs.

Guides & comparisons

• OpenClaw vs Hermes Agent vs Pi: open-source agents you run yourself (Comparison): Three fast-moving open-source agent runtimes compared: OpenClaw (gateway-first personal assistant), Hermes Agent (self-improving agent with memory, skills and cron) and Pi (minimal, extensible coding harness). Covers interfaces, models, memory, skills, MCP, automation, safety defaults and license.

Sources

• https://github.com/NousResearch/hermes-agent
• https://hermes-agent.nousresearch.com/docs/llms.txt

Machine-readable

• JSON
• Markdown
• Source file on GitHub (edit via pull request)