> ## Documentation Index
> Fetch the complete documentation index at: https://docs.lowkey.run/llms.txt
> Use this file to discover all available pages before exploring further.

# Hermes: lightweight NousResearch CLI agent on Bedrock

> Deploy NousResearch's Hermes CLI on AWS via Amazon Bedrock. No API keys required, lighter than OpenClaw, and features a built-in self-improving skills loop.

Hermes is NousResearch's terminal-focused CLI agent. The Lowkey pack installs it and points it at bedrockify, a local OpenAI-compatible proxy that translates Hermes's API calls into Bedrock `InvokeModel` requests. You get Hermes's workflow — including its self-improving skills and learning loop — with Claude or other Bedrock models as the backing inference, and no API keys to manage.

<Note>
  **Experimental pack.** Hermes is under active development by NousResearch. Expect upstream changes between Lowkey versions.
</Note>

## What makes Hermes different

* **Self-improving skills.** Hermes has a built-in learning loop that improves the skills it uses over time, letting the agent get better at tasks it repeats.
* **Lightweight.** Hermes runs on a `t4g.medium` with no data volume. It's the right choice when you want a capable terminal agent without the resource overhead of OpenClaw.
* **Bedrock via bedrockify.** Hermes expects an OpenAI-compatible API. The pack configures it to talk to bedrockify at `http://localhost:8090/v1`, which translates its calls into Bedrock requests using the instance's IAM role.
* **OpenAI-style model IDs.** Hermes uses model IDs in the format `anthropic/claude-opus-4.6`, not Bedrock-style IDs like `us.anthropic.claude-opus-4-6-v1`. Bedrockify handles the translation.
* **No gateway, no memory service.** Unlike OpenClaw, Hermes is a pure CLI binary. Nothing runs in the background between sessions.

## Compatible profiles

| Profile              | IAM permissions          | Instance     | Use case                           |
| -------------------- | ------------------------ | ------------ | ---------------------------------- |
| `builder`            | AdministratorAccess      | `t4g.medium` | Build apps, deploy infra           |
| `account_assistant`  | ReadOnlyAccess + Bedrock | `t4g.medium` | Architecture review, cost analysis |
| `personal_assistant` | Bedrock only             | `t4g.medium` | Writing, research, coding help     |

## Prerequisites

* AWS CLI configured with admin access in a **dedicated sandbox account**
* Amazon Bedrock model access enabled in your target region (default: `us-east-1`)
* No API keys, Docker, or interactive login needed

## Install

```bash theme={null}
curl -sfL install.lowkey.run | bash -s -- -y \
  --pack hermes \
  --profile builder
```

The pack installs bedrockify as a dependency (if not already present), then downloads and runs NousResearch's official Hermes installer with `--skip-setup` to suppress interactive prompts. It writes `~/.hermes/config.yaml` and `~/.hermes/.env`, pointing Hermes at bedrockify on localhost.

## Connect and use

After the stack deploys, SSM into the instance and run `hermes` directly:

```bash theme={null}
# Open a session
aws ssm start-session --target <instance-id>

# Verify the install
hermes --version

# Start an interactive Hermes session
hermes
```

Bedrock authentication is handled by the instance's IAM role via bedrockify. There is nothing to log into.

## Configuration options

| Flag                | Default                     | Description                                      |
| ------------------- | --------------------------- | ------------------------------------------------ |
| `--region`          | `us-east-1`                 | AWS region for Bedrock                           |
| `--hermes-model`    | `anthropic/claude-opus-4.6` | Model ID in OpenAI-style format (via bedrockify) |
| `--bedrockify-port` | `8090`                      | Port where bedrockify listens                    |

<Info>
  Use `--hermes-model` to change the model, not the generic `--model` flag. The generic `--model` flag carries Bedrock-style IDs (e.g. `us.anthropic.claude-opus-4-6-v1`) from the bootstrap dispatcher, which Hermes does not accept. The pack ignores `--model` entirely and reads `--hermes-model` instead.
</Info>

**Available model IDs for `--hermes-model`:**

| Model                     | ID                            |
| ------------------------- | ----------------------------- |
| Claude Opus 4.6 (default) | `anthropic/claude-opus-4.6`   |
| Claude Sonnet 4.6         | `anthropic/claude-sonnet-4.6` |

Bedrockify translates these OpenAI-style IDs into their corresponding Bedrock model IDs at inference time.

## Resource requirements

|               | All profiles |
| ------------- | ------------ |
| Instance type | `t4g.medium` |
| Root volume   | 40 GB        |
| Data volume   | 0 GB         |

## Notes and limitations

* Hermes is a **pure CLI pack** — no background gateway service runs between sessions. Each `hermes` invocation is a fresh process.
* Hermes has no built-in persistent memory between sessions the way OpenClaw does. If you need cross-session continuity and multi-channel access, use [OpenClaw](/agents/openclaw) instead.
* The `--hermes-model` flag is Hermes-specific. You cannot use Bedrock ARNs or cross-region inference IDs directly — bedrockify maps the OpenAI-style ID to a Bedrock model ID internally.
* Tearing down the stack leaves no lingering state to clean up — the data volume is 0 GB and the instance has no persistent agent storage.