Hermes Agent

Nous Research

Open Source

Self-improving open-source agent with persistent memory, built-in cron and a gateway to 20+ chat apps; runs on a laptop, VPS or cloud sandbox.

Curated by Tiberiu ArvaVerified

MITVersion 0.21.5Released 2026-09-24

Strengths

  • Learns and reuses its own skills
  • Cron jobs deliver to any chat platform
  • 7 terminal backends incl. Docker, SSH, Modal

Practitioner note

Use a container or remote sandbox backend with command approval on rather than the local terminal backend. Self-written skills and memory mean you should review what it has learned before trusting it with production credentials.

Governance posture

Reviewed 2026-09-30
YesData residency

Self-hosted; operator chooses where it runs (local, VPS, cloud sandbox). Model calls go to the configured provider.

Source
YesDeployment model

Self-hosted locally or on remote backends (Docker, SSH, Daytona, Singularity, Modal, Vercel Sandbox). (self-hosted)

Source
PartialAudit logging

Searchable session history and command approval; no dedicated audit log documented.

Source
N/ASOC 2

Self-hosted open-source agent; SOC 2 applies to the operator's infrastructure, not the package.

N/AISO 27001

Self-hosted open-source agent; ISO 27001 applies to the operator's ISMS, not the package.

N/AISO 42001

Self-hosted open-source agent; ISO 42001 applies to the deploying organisation.

N/AEU AI Act

Self-hosted open-source agent runtime, not an AI system placed on the market by the maintainer; obligations rest with the deployer. (role: not-applicable)

YesLicense risk

MIT (Copyright Nous Research) — permissive, OSI-approved. (low)

Source

EU AI Act obligations

Risk tier: Not applicable · as of 2026-08-23

Source-backed information mapped from Hermes Agent's tracked risk tier — not legal advice. Obligations depend on how your organisation deploys the system; see the full obligation reference and timeline.

This record's EU AI Act risk tier is marked not applicable, so no tier-specific obligations attach. Deployers embedding it in an AI system in scope of the Act should assess that system's own tier.

Explore the category

Compare this tool against the rest of its category and the cloud platform foundation layer.