Skip to main content
Pre-release

This release is a pre-release and may not be stable for production use.

NVIDIA NeMo Fabric Hermes Agent Adapter

License GitHub Release

Diagram showing NeMo Fabric connecting applications, evaluations, and reinforcement learning rollouts to Hermes, Codex, Claude, and Deep Agents, with results, artifacts, and telemetry as outputs.

nemo-fabric-adapters-hermes provides a NeMo Fabric adapter for use with Hermes Agent.

Install

Hermes Agent and this adapter require Python versions 3.11 through 3.13. Installation can be performed using the nemo-fabric meta package with the hermes-agent extra, or by installing the adapter and harness packages separately. The following table shows which components each installation provides:

Installation Runtime Adapter Harness NeMo Relay Python Package
pip install "nemo-fabric[hermes-agent]" Yes Yes Yes No
pip install "nemo-fabric[hermes-agent,relay]" Yes Yes Yes Yes
pip install "nemo-fabric-adapters-hermes[harness]" No Yes Yes No
pip install "nemo-fabric-adapters-hermes[full]" No Yes Yes Yes
pip install "nemo-fabric-adapters-hermes[relay]" No Yes No Yes
pip install nemo-fabric-adapters-hermes No Yes No No

NeMo Relay is optional for ordinary runs. NeMo Relay telemetry and streaming require one of the installations in the table that includes the NeMo Relay Python package.

Refer to the installation guide for more details.

Metadata

Release files for nemo-fabric-adapters-hermes 0.2.0a20260801

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for nemo-fabric-adapters-hermes 0.2.0a20260801
File Size Uploaded
nemo_fabric_adapters_hermes-0.2.0a20260801.tar.gz 5.5 kB Details

Release files / nemo_fabric_adapters_hermes-0.2.0a20260801.tar.gz

Download URL nemo_fabric_adapters_hermes-0.2.0a20260801.tar.gz
Size 5.5 kB
Tags Source
SHA-256 checksum
How to use checksums
5dfe10a3f13cc14d002dd06678b8432d9aa3660ada459e81b1e0dc5ccd546cf7
BLAKE2b-256 checksum
How to use checksums
17eec3ff30c157973890e5a4d68f295d3b8e89a58cdffe458f60a34a9decbc17
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/6.2.0 CPython/3.14.6

Release history Release notifications | RSS feed

0.5.0

1 release file

0.4.0

1 release file

0.3.0

1 release file

0.2.0

1 release file

This release

0.1.1

1 release file

0.1.0

1 release file

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page