---
title: "Hermes Agent | Ethical Stack"
url: https://ethicalstack.ai/harnesses/hermes-agent/
catalog_version: f6baff2119d0e9158520da7fbe4232011dac79f25bd08757436d7a1dbd593db2
---

# Hermes Agent

Open-source personal agent with terminal, browser, messaging, memory and task tools; the model and inference route are configurable.

Canonical profile: https://ethicalstack.ai/harnesses/hermes-agent/

Scope: Hermes client and locally stored agent state. Hosted or local model route, messaging platform, plugins, and permissions determine data handling and action reach.

Published overall: 5.4; 5/6 dimensions rated.

Round the equal-weight mean of available numerical ratings to one decimal; require at least four of six for an overall score. BDS status stays outside the mean; for eligible profiles, a boycott target caps the final score at 2/10 and a pressure target subtracts one point (minimum 1). Not listed and not checked do not adjust the score.

## Energy practices

Finding: 4/10

Assessment: https://ethicalstack.ai/harnesses/hermes-agent/#energy

Hermes exposes local-versus-hosted inference choice and configurable token/context ceilings; no electricity mix or per-task energy is reported.

Reason: 1 + 1 reporting + 0 electricity + 2 controls = 4/10. This grades documented practices and transparency.

Argument: Its documented route selection and token/context limits define operational boundaries and give operators controls over input and output volume. They do not measure energy savings, identify a serving facility, or report electricity sourcing, so this is a practices score rather than a footprint claim.

Type: argument; confidence: medium

Scope (dimension): Hermes client and locally stored agent state. Hosted or local model route, messaging platform, plugins, and permissions determine data handling and action reach.

Research reviewed: not recorded; evidence date: not recorded

Unknowns: Actual token counts, local hardware consumption, and hosted provider/model/region electricity are not reported for a task.

```json
{
  "method": "practices-transparency-v1",
  "scope": "Hermes client and locally stored agent state. Hosted or local model route, messaging platform, plugins, and permissions determine data handling and action reach.",
  "components": {
    "disclosure": {
      "score": 1,
      "reason": "Hermes documents both local-model execution and hosted provider routing, but gives no request-level energy or electricity disclosure.",
      "sourceUrls": [
        "https://hermes-agent.nousresearch.com/docs/user-guide/local-models",
        "https://hermes-agent.nousresearch.com/docs/integrations/providers"
      ]
    },
    "electricity": {
      "score": 0,
      "reason": "The local-versus-provider choice does not identify the electricity mix or facility serving any selected model route.",
      "sourceUrls": [
        "https://hermes-agent.nousresearch.com/docs/user-guide/local-models",
        "https://hermes-agent.nousresearch.com/docs/integrations/providers"
      ]
    },
    "demand": {
      "score": 2,
      "reason": "Documented absolute token compaction thresholds and context/file/output limits let an operator bound prompt and generated-token volume; these are controls, not measured energy reductions.",
      "sourceUrls": [
        "https://hermes-agent.nousresearch.com/docs/user-guide/configuration",
        "https://hermes-agent.nousresearch.com/docs/integrations/providers"
      ]
    }
  },
  "actualImpactMeasured": false
}
```

- [Local Models](https://hermes-agent.nousresearch.com/docs/user-guide/local-models) (primary; checked not recorded)

- [LLM and Model Providers](https://hermes-agent.nousresearch.com/docs/integrations/providers) (primary; checked not recorded)

- [Hermes Agent configuration and token/context limits](https://hermes-agent.nousresearch.com/docs/user-guide/configuration) (primary; checked not recorded)

## Training data

Finding: Depends on the model

Assessment: https://ethicalstack.ai/harnesses/hermes-agent/#training-rights

The product can route tasks through multiple models or providers, so no single training corpus applies to this agent entry.

Reason: Select and assess the exact model and provider route before assigning corpus rights; do not infer permission from a no-training-on-prompts control.

Argument: The product can route tasks through multiple models or providers, so no single training corpus applies to this agent entry. Model version, provider, and any fine-tuning or post-training sources must be checked for the selected route; a client privacy setting does not establish training-material permission.

Type: argument; confidence: medium

Scope (profile): Hermes client and locally stored agent state. Hosted or local model route, messaging platform, plugins, and permissions determine data handling and action reach.

Research reviewed: not recorded; evidence date: not recorded

Unknowns: Exact model, version, provider, inherited base, and fine-tuning corpus vary by route or are not disclosed in the reviewed product sources.

```json
{
  "method": "training-rights-evidence-v1",
  "scope": "The stated training release or selected model",
  "components": null,
  "routeDependency": "Select and assess the exact model and provider route before assigning corpus rights; do not infer permission from a no-training-on-prompts control.",
  "modelReference": null
}
```

- [LLM and Model Providers](https://hermes-agent.nousresearch.com/docs/integrations/providers) (primary; checked not recorded)

- [NousResearch/hermes-agent official repository](https://github.com/NousResearch/hermes-agent) (primary; checked not recorded)

## Your data & privacy

Finding: 6/10

Assessment: https://ethicalstack.ai/harnesses/hermes-agent/#privacy

Hermes stores conversation history, memory, and skills locally; local inference can keep prompts on the device after model download, while cloud providers receive routed requests.

Reason: 6/10 is a middle-band judgment: locally stored agent state and an available local inference route support user control, while hosted providers, gateways, integrations and backups remain outside that boundary.

Argument: Hermes states it collects no telemetry and stores conversations, memory, and skills locally, and its managed local-model route can run without network access after downloads. Those controls apply to the client and local route; hosted provider, messaging integrations, plugins, and external memory change the boundary.

Type: argument; confidence: medium

Scope (profile): Hermes client and locally stored agent state. Hosted or local model route, messaging platform, plugins, and permissions determine data handling and action reach.

Research reviewed: not recorded; evidence date: not recorded

Unknowns: The selected provider, external plugins, gateway host, messaging platform, and backups determine other copies and retention.

- [FAQ and troubleshooting](https://hermes-agent.nousresearch.com/docs/reference/faq/) (primary; checked not recorded)

- [Local Models](https://hermes-agent.nousresearch.com/docs/user-guide/local-models) (primary; checked not recorded)

- [Persistent Memory](https://hermes-agent.nousresearch.com/docs/user-guide/features/memory/) (primary; checked not recorded)

## Openness

Finding: 9/10

Assessment: https://ethicalstack.ai/harnesses/hermes-agent/#openness

The NousResearch/hermes-agent repository is publicly available under MIT; connected model weights and services retain their own terms.

Reason: 9/10 reflects the public MIT-licensed, inspectable harness; model weights, provider services and integrations keep separate terms and are not made open by the client license.

Argument: The official repository links to NousResearch/hermes-agent and publishes an MIT license for the agent code. Users can inspect and modify the harness, but model weights, paid gateways, plugins, and connected services are licensed separately and do not become open through the client license.

Type: argument; confidence: medium

Scope (profile): Hermes client and locally stored agent state. Hosted or local model route, messaging platform, plugins, and permissions determine data handling and action reach.

Research reviewed: not recorded; evidence date: not recorded

Unknowns: Bundled assets and each selected model/provider have separate licenses and disclosure limits.

- [NousResearch/hermes-agent official repository](https://github.com/NousResearch/hermes-agent) (primary; checked not recorded)

- [Hermes Agent MIT license](https://github.com/NousResearch/hermes-agent/blob/main/LICENSE) (primary; checked not recorded)

## Worker protections

Finding: 1/10

Assessment: https://ethicalstack.ai/harnesses/hermes-agent/#labour

Public project licensing does not disclose workforce conditions or contractor protections.

Reason: 1 + 0 + 0 + 0 = 1/10. Documented worker protections; missing disclosure is an evidence gap.

Argument: The reviewed official repository and project documentation identify the software and its license, but do not provide pay, working-condition, worker-voice, contractor, or independent-assurance evidence. This is a disclosure gap, not evidence of poor treatment.

Type: argument; confidence: medium

Scope (profile): Hermes client and locally stored agent state. Hosted or local model route, messaging platform, plugins, and permissions determine data handling and action reach.

Research reviewed: not recorded; evidence date: not recorded

Unknowns: Nous Research workforce and outsourced annotation/moderation conditions were not established in the reviewed sources.

```json
{
  "method": "worker-safeguards-evidence-v1",
  "entity": "harnesses/hermes-agent",
  "company": "",
  "scope": "The named developer or operator",
  "components": {
    "conditions": {
      "score": 0,
      "reason": "Reviewed official project pages do not disclose a worker-conditions policy or workforce metrics.",
      "sourceUrls": [
        "https://github.com/NousResearch/hermes-agent"
      ]
    },
    "voice": {
      "score": 0,
      "reason": "No worker-voice or remedy disclosures were identified in the reviewed official project sources.",
      "sourceUrls": [
        "https://github.com/NousResearch/hermes-agent"
      ]
    },
    "assurance": {
      "score": 0,
      "reason": "No independent workforce assurance is published in the reviewed project sources.",
      "sourceUrls": [
        "https://github.com/NousResearch/hermes-agent"
      ]
    }
  },
  "disclosureLimited": true
}
```

- [NousResearch/hermes-agent official repository](https://github.com/NousResearch/hermes-agent) (primary; checked not recorded)

## Military ties

Finding: 7/10

Assessment: https://ethicalstack.ai/harnesses/hermes-agent/#military-contracts

No military relationship or product-specific restrictions are established in the reviewed official materials.

Reason: 7 base + 0 safeguard adjustment = 7/10 (0 of 9 safeguard points; every 3 adds 1). No military relationship was established in the cited sources. This ranks above known defense ties without claiming a verified clean record.

Argument: This research found no official project disclosure establishing defense work or military safeguards for Hermes Agent. A configurable open-source harness can be paired with many model providers and deployments, so absence of a project disclosure does not establish how every user deploys it.

Type: argument; confidence: medium

Scope (profile): Hermes client and locally stored agent state. Hosted or local model route, messaging platform, plugins, and permissions determine data handling and action reach.

Research reviewed: not recorded; evidence date: not recorded

Unknowns: Nous Research commercial relationships and downstream user deployments were not exhaustively audited.

```json
{
  "method": "military-ties-priority-v2",
  "entity": "harnesses/hermes-agent",
  "company": "",
  "scope": "The named developer or operator",
  "components": {
    "restrictions": {
      "score": 0,
      "reason": "The reviewed official repository and tool documentation do not state a binding military-use restriction.",
      "sourceUrls": [
        "https://github.com/NousResearch/hermes-agent",
        "https://hermes-agent.nousresearch.com/docs/user-guide/security"
      ]
    },
    "oversight": {
      "score": 0,
      "reason": "No military-specific enforcement or oversight outcomes are stated in the reviewed sources.",
      "sourceUrls": [
        "https://github.com/NousResearch/hermes-agent"
      ]
    },
    "transparency": {
      "score": 0,
      "reason": "No military relationship disclosure was located in the reviewed official project sources.",
      "sourceUrls": [
        "https://github.com/NousResearch/hermes-agent"
      ]
    }
  },
  "disclosureLimited": true,
  "relationship": "not-established",
  "relationshipReason": "The reviewed official project sources do not establish a defense contract, military deployment, or customer relationship.",
  "score": 7,
  "baseScore": 7,
  "safeguardPoints": 0,
  "safeguardAdjustment": 0,
  "rawScore": 7,
  "cap": null
}
```

- [NousResearch/hermes-agent official repository](https://github.com/NousResearch/hermes-agent) (primary; checked not recorded)

- [LLM and Model Providers](https://hermes-agent.nousresearch.com/docs/integrations/providers) (primary; checked not recorded)

- [Security and approvals](https://hermes-agent.nousresearch.com/docs/user-guide/security) (primary; checked not recorded)

## BDS targets

Finding: Not listed

Assessment: https://ethicalstack.ai/harnesses/hermes-agent/#israel-palestine

Nous Research is not named in the reviewed BNC consumer guide or No Tech campaign.

Reason: Campaign category, excluded from numerical scoring.

Argument: The official BNC guide and technology campaign contain named company targets; Nous Research does not appear in the reviewed target listings. This limited check is not an endorsement and does not establish supplier or investor relationships.

Type: argument; confidence: medium

Scope (profile): Hermes client and locally stored agent state. Hosted or local model route, messaging platform, plugins, and permissions determine data handling and action reach.

Research reviewed: not recorded; evidence date: not recorded

Unknowns: This is limited to the two official BNC campaign sources; it does not cover every local campaign, supplier, investment, or future change.

- [BNC consumer boycott and pressure guide](https://bdsmovement.net/Guide-to-BDS-Boycott) (primary; checked not recorded)

- [BNC No Tech campaign](https://bdsmovement.net/no-tech-oppression-apartheid-or-genocide) (primary; checked not recorded)

## Reading the evidence

- Assessments are provisional editorial judgments. Cite the profile and the underlying sources, and retain confidence, scope and unknowns.

- Unknown, not-applicable and model-dependent are different states. Missing evidence does not establish good or bad conduct.

- Company-level evidence does not establish use of a particular product or model. Account plan, model, host and route can change an assessment.

- Energy scores describe documented practices and transparency, not measured request emissions. Zero component points can mean an evidence gap.

- Published overall scores require at least four of six numerical dimensions. Preserve coverage and BDS adjustments; BDS itself is categorical.

- No named BDS target found is limited to the reviewed campaign sources and is not approval. Personalized priorities do not change the published overall score.

- Review and source-check dates describe the research, not this deployment. Fetch current primary sources when the decision requires current verification.

Methodology: https://ethicalstack.ai/methodology/