Hermes Agent

license

MIT(OSI)

source

public(github.com/NousResearch/hermes-agent)

core features withheld

no

Fully MIT-licensed, complete public source, self-hosted by design, no proprietary core; top openness.

• https://github.com/NousResearch/hermes-agent recorded 2026-08-13

  MIT license badge and README statement "License - MIT, see LICENSE"; full public Python source for the self-improving multi-channel agent; 230.0k stars, 45.5k forks

• https://hermes-agent.nousresearch.com recorded 2026-09-29

  The product FAQ says "Hermes Agent is free and open source under the MIT license." and that "cloud hosting is optional", so the agent is not gated behind a paid tier.

• https://raw.githubusercontent.com/NousResearch/hermes-agent/main/LICENSE recorded 2026-09-29

  The repository LICENSE file is the standard permissive text: "MIT License" and "Copyright (c) 2025 Nous Research".

• https://raw.githubusercontent.com/NousResearch/hermes-agent/main/README.md recorded 2026-09-29

  The README states "MIT — see [LICENSE](LICENSE)." and invites public contributions: "We welcome contributions! See the [Contributing Guide]" for development setup, with no edition or paid-tier split mentioned.

Hermes Agent's usage is measured by inference token volume on OpenRouter, where it ranks first globally and in the productivity and coding-agent categories. That figure is the best available proxy for an installed base Nous Research does not otherwise disclose.

• https://chatforest.com/builders-log/hermes-agent-nous-research-openrouter-number-one-self-improving-builder-guide/ recorded 2026-08-13

  aggregator detail on the MIT self-hosted agent and its star growth (corroborating)

• https://github.com/NousResearch/hermes-agent recorded 2026-08-13

  230.0k stars, 45.5k forks, active releases (corroborating, not the basis)

• https://openrouter.ai/apps/hermes-agent recorded 2026-08-13

  PRIMARY - OpenRouter app page reports total tokens 35.8T, daily global rank #1, active since Mar 2026, 417 models used, #1 in Productivity and #1 in Coding Agents

• https://x.com/NousResearch/status/2052904761087729897 recorded 2026-08-13

  PRIMARY - Nous Research: "Hermes Agent is now #1 on the Global @OpenRouter token rankings."

Distinctive autonomy - a self-improvement loop, persistent memory and subagent delegation - and very broad tool and channel coverage place it high among feature-based peers; with no published benchmark, it sits just below the products a verified benchmark places at the ceiling.

• https://github.com/NousResearch/hermes-agent recorded 2026-08-13

  self-improving skills, persistent memory, 40+ tools, subagents, natural-language cron and sandboxing; no benchmark figure published

• https://openrouter.ai/apps/hermes-agent recorded 2026-09-29

  The OpenRouter app page describes Hermes Agent as "open-source, self-improving AI agent by Nous Research that runs persistently with memory across sessions" with "web search, browser automation, and vision, plus scheduled automations and subagents".

• https://raw.githubusercontent.com/NousResearch/hermes-agent/main/README.md recorded 2026-09-29

  The README describes "Agent-curated memory with periodic nudges. Autonomous skill creation after complex tasks. Skills self-improve during use." and "Spawn isolated subagents for parallel workstreams." and a "Built-in cron scheduler" plus "40+ tools".