NousResearch/hermes-agent
Read the upstream summary on the left, browse the cached forks below it, and load each fork comparison into the right-hand panel.
NousResearch/hermes-agent
NousResearch/hermes-agent is an MIT-licensed Python/Node open source AI agent project focused on long-running, multi-channel assistant workflows. It appears active and mature, with 18,355 stars, 2,214 forks, and commits on 2026-03-30. Forks may be interesting if you care about agent tooling, messaging integrations, scheduled automations, or experimentation with self-improving/learning-loop behavior.
Jump straight into Discofork's strongest cached fork picks, or open a compare view in one click.
Choose a fork to inspect
Choose this fork if you want a more customized, Windows-friendly Hermes Agent and can tolerate being far from upstream. Stick with upstream if you need the widest integration coverage, faster access to recent fixes, or lower maintenance risk.
This fork is materially different enough that adopters should validate long-term maintenance and upgrade cost.
Choose this fork only if you want its custom model/default/runtime changes and are comfortable trading away upstream breadth and update velocity. For most adopters who need full Hermes Agent coverage across messaging, docs, and platform integrations, upstream is the safer choice.
Choose this fork if RabbitSync support is the reason you are adopting Hermes Agent. Choose upstream if you want the broadest set of current fixes, integrations, and ongoing maintenance.
Prefer this fork only if you specifically want a frozen upstream snapshot. For most adopters, upstream is the better choice because this fork adds nothing visible and is already behind active fixes and features.
Prefer upstream unless you specifically need this exact snapshot. For most adopters, the fork offers no added capability and is materially behind current upstream work.