hermes-agent/website/docs/user-guide/configuration.md

---
sidebar_position: 2
title: "Configuration"
description: "Configure Hermes Agent — config.yaml, providers, models, API keys, and more"
---

# Configuration

All settings are stored in the `~/.hermes/` directory for easy access.

## Directory Structure

```text
~/.hermes/
├── config.yaml     # Settings (model, terminal, TTS, compression, etc.)
├── .env            # API keys and secrets
├── auth.json       # OAuth provider credentials (Nous Portal, etc.)
├── SOUL.md         # Optional: global persona (agent embodies this personality)
├── memories/       # Persistent memory (MEMORY.md, USER.md)
├── skills/         # Agent-created skills (managed via skill_manage tool)
├── cron/           # Scheduled jobs
├── sessions/       # Gateway sessions
└── logs/           # Logs (errors.log, gateway.log — secrets auto-redacted)
```

## Managing Configuration

```bash
hermes config              # View current configuration
hermes config edit         # Open config.yaml in your editor
hermes config set KEY VAL  # Set a specific value
hermes config check        # Check for missing options (after updates)
hermes config migrate      # Interactively add missing options

# Examples:
hermes config set model anthropic/claude-opus-4
hermes config set terminal.backend docker
hermes config set OPENROUTER_API_KEY sk-or-...  # Saves to .env
```

:::tip
The `hermes config set` command automatically routes values to the right file — API keys are saved to `.env`, everything else to `config.yaml`.
:::

## Configuration Precedence

Settings are resolved in this order (highest priority first):

1. **CLI arguments** — e.g., `hermes chat --model anthropic/claude-sonnet-4` (per-invocation override)
2. **`~/.hermes/config.yaml`** — the primary config file for all non-secret settings
3. **`~/.hermes/.env`** — fallback for env vars; **required** for secrets (API keys, tokens, passwords)
4. **Built-in defaults** — hardcoded safe defaults when nothing else is set

:::info Rule of Thumb
Secrets (API keys, bot tokens, passwords) go in `.env`. Everything else (model, terminal backend, compression settings, memory limits, toolsets) goes in `config.yaml`. When both are set, `config.yaml` wins for non-secret settings.
:::

## Inference Providers

You need at least one way to connect to an LLM. Use `hermes model` to switch providers and models interactively, or configure directly:

| Provider | Setup |
|----------|-------|
| **Nous Portal** | `hermes model` (OAuth, subscription-based) |
| **OpenAI Codex** | `hermes model` (ChatGPT OAuth, uses Codex models) |
| **OpenRouter** | `OPENROUTER_API_KEY` in `~/.hermes/.env` |
| **z.ai / GLM** | `GLM_API_KEY` in `~/.hermes/.env` (provider: `zai`) |
| **Kimi / Moonshot** | `KIMI_API_KEY` in `~/.hermes/.env` (provider: `kimi-coding`) |
| **MiniMax** | `MINIMAX_API_KEY` in `~/.hermes/.env` (provider: `minimax`) |
| **MiniMax China** | `MINIMAX_CN_API_KEY` in `~/.hermes/.env` (provider: `minimax-cn`) |
| **Custom Endpoint** | `OPENAI_BASE_URL` + `OPENAI_API_KEY` in `~/.hermes/.env` |

:::info Codex Note
The OpenAI Codex provider authenticates via device code (open a URL, enter a code). Credentials are stored at `~/.codex/auth.json` and auto-refresh. No Codex CLI installation required.
:::

:::warning
Even when using Nous Portal, Codex, or a custom endpoint, some tools (vision, web summarization, MoA) use OpenRouter independently. An `OPENROUTER_API_KEY` enables these tools.
:::

### First-Class Chinese AI Providers

These providers have built-in support with dedicated provider IDs. Set the API key and use `--provider` to select:

```bash
# z.ai / ZhipuAI GLM
hermes chat --provider zai --model glm-4-plus
# Requires: GLM_API_KEY in ~/.hermes/.env

# Kimi / Moonshot AI
hermes chat --provider kimi-coding --model moonshot-v1-auto
# Requires: KIMI_API_KEY in ~/.hermes/.env

# MiniMax (global endpoint)
hermes chat --provider minimax --model MiniMax-Text-01
# Requires: MINIMAX_API_KEY in ~/.hermes/.env

# MiniMax (China endpoint)
hermes chat --provider minimax-cn --model MiniMax-Text-01
# Requires: MINIMAX_CN_API_KEY in ~/.hermes/.env
```

Or set the provider permanently in `config.yaml`:
```yaml
model:
  provider: "zai"       # or: kimi-coding, minimax, minimax-cn
  default: "glm-4-plus"
```

Base URLs can be overridden with `GLM_BASE_URL`, `KIMI_BASE_URL`, `MINIMAX_BASE_URL`, or `MINIMAX_CN_BASE_URL` environment variables.

## Custom & Self-Hosted LLM Providers

Hermes Agent works with **any OpenAI-compatible API endpoint**. If a server implements `/v1/chat/completions`, you can point Hermes at it. This means you can use local models, GPU inference servers, multi-provider routers, or any third-party API.

### General Setup

Two ways to configure a custom endpoint:

**Interactive (recommended):**
```bash
hermes model
# Select "Custom endpoint (self-hosted / VLLM / etc.)"
# Enter: API base URL, API key, Model name
```

**Manual (`.env` file):**
```bash
# Add to ~/.hermes/.env
OPENAI_BASE_URL=http://localhost:8000/v1
OPENAI_API_KEY=your-key-or-dummy
LLM_MODEL=your-model-name
```

Everything below follows this same pattern — just change the URL, key, and model name.

---

### Ollama — Local Models, Zero Config

[Ollama](https://ollama.com/) runs open-weight models locally with one command. Best for: quick local experimentation, privacy-sensitive work, offline use.

```bash
# Install and run a model
ollama pull llama3.1:70b
ollama serve   # Starts on port 11434

# Configure Hermes
OPENAI_BASE_URL=http://localhost:11434/v1
OPENAI_API_KEY=ollama           # Any non-empty string
LLM_MODEL=llama3.1:70b
```

Ollama's OpenAI-compatible endpoint supports chat completions, streaming, and tool calling (for supported models). No GPU required for smaller models — Ollama handles CPU inference automatically.

:::tip
List available models with `ollama list`. Pull any model from the [Ollama library](https://ollama.com/library) with `ollama pull <model>`.
:::

---

### vLLM — High-Performance GPU Inference

[vLLM](https://docs.vllm.ai/) is the standard for production LLM serving. Best for: maximum throughput on GPU hardware, serving large models, continuous batching.

```bash
# Start vLLM server
pip install vllm
vllm serve meta-llama/Llama-3.1-70B-Instruct \
  --port 8000 \
  --tensor-parallel-size 2    # Multi-GPU

# Configure Hermes
OPENAI_BASE_URL=http://localhost:8000/v1
OPENAI_API_KEY=dummy
LLM_MODEL=meta-llama/Llama-3.1-70B-Instruct
```

vLLM supports tool calling, structured output, and multi-modal models. Use `--enable-auto-tool-choice` and `--tool-call-parser hermes` for Hermes-format tool calling with NousResearch models.

---

### SGLang — Fast Serving with RadixAttention

[SGLang](https://github.com/sgl-project/sglang) is an alternative to vLLM with RadixAttention for KV cache reuse. Best for: multi-turn conversations (prefix caching), constrained decoding, structured output.

```bash
# Start SGLang server
pip install sglang[all]
python -m sglang.launch_server \
  --model meta-llama/Llama-3.1-70B-Instruct \
  --port 8000 \
  --tp 2

# Configure Hermes
OPENAI_BASE_URL=http://localhost:8000/v1
OPENAI_API_KEY=dummy
LLM_MODEL=meta-llama/Llama-3.1-70B-Instruct
```

---

### llama.cpp / llama-server — CPU & Metal Inference

[llama.cpp](https://github.com/ggml-org/llama.cpp) runs quantized models on CPU, Apple Silicon (Metal), and consumer GPUs. Best for: running models without a datacenter GPU, Mac users, edge deployment.

```bash
# Build and start llama-server
cmake -B build && cmake --build build --config Release
./build/bin/llama-server \
  -m models/llama-3.1-8b-instruct-Q4_K_M.gguf \
  --port 8080 --host 0.0.0.0

# Configure Hermes
OPENAI_BASE_URL=http://localhost:8080/v1
OPENAI_API_KEY=dummy
LLM_MODEL=llama-3.1-8b-instruct
```

:::tip
Download GGUF models from [Hugging Face](https://huggingface.co/models?library=gguf). Q4_K_M quantization offers the best balance of quality vs. memory usage.
:::

---

### LiteLLM Proxy — Multi-Provider Gateway

[LiteLLM](https://docs.litellm.ai/) is an OpenAI-compatible proxy that unifies 100+ LLM providers behind a single API. Best for: switching between providers without config changes, load balancing, fallback chains, budget controls.

```bash
# Install and start
pip install litellm[proxy]
litellm --model anthropic/claude-sonnet-4 --port 4000

# Or with a config file for multiple models:
litellm --config litellm_config.yaml --port 4000

# Configure Hermes
OPENAI_BASE_URL=http://localhost:4000/v1
OPENAI_API_KEY=sk-your-litellm-key
LLM_MODEL=anthropic/claude-sonnet-4
```

Example `litellm_config.yaml` with fallback:
```yaml
model_list:
  - model_name: "best"
    litellm_params:
      model: anthropic/claude-sonnet-4
      api_key: sk-ant-...
  - model_name: "best"
    litellm_params:
      model: openai/gpt-4o
      api_key: sk-...
router_settings:
  routing_strategy: "latency-based-routing"
```

---

### ClawRouter — Cost-Optimized Routing

[ClawRouter](https://github.com/BlockRunAI/ClawRouter) by BlockRunAI is a local routing proxy that auto-selects models based on query complexity. It classifies requests across 14 dimensions and routes to the cheapest model that can handle the task. Payment is via USDC cryptocurrency (no API keys).

```bash
# Install and start
npx @blockrun/clawrouter    # Starts on port 8402

# Configure Hermes
OPENAI_BASE_URL=http://localhost:8402/v1
OPENAI_API_KEY=dummy
LLM_MODEL=blockrun/auto     # or: blockrun/eco, blockrun/premium, blockrun/agentic
```

Routing profiles:
| Profile | Strategy | Savings |
|---------|----------|---------|
| `blockrun/auto` | Balanced quality/cost | 74-100% |
| `blockrun/eco` | Cheapest possible | 95-100% |
| `blockrun/premium` | Best quality models | 0% |
| `blockrun/free` | Free models only | 100% |
| `blockrun/agentic` | Optimized for tool use | varies |

:::note
ClawRouter requires a USDC-funded wallet on Base or Solana for payment. All requests route through BlockRun's backend API. Run `npx @blockrun/clawrouter doctor` to check wallet status.
:::

---

### Other Compatible Providers

Any service with an OpenAI-compatible API works. Some popular options:

| Provider | Base URL | Notes |
|----------|----------|-------|
| [Together AI](https://together.ai) | `https://api.together.xyz/v1` | Cloud-hosted open models |
| [Groq](https://groq.com) | `https://api.groq.com/openai/v1` | Ultra-fast inference |
| [DeepSeek](https://deepseek.com) | `https://api.deepseek.com/v1` | DeepSeek models |
| [Fireworks AI](https://fireworks.ai) | `https://api.fireworks.ai/inference/v1` | Fast open model hosting |
| [Cerebras](https://cerebras.ai) | `https://api.cerebras.ai/v1` | Wafer-scale chip inference |
| [Mistral AI](https://mistral.ai) | `https://api.mistral.ai/v1` | Mistral models |
| [OpenAI](https://openai.com) | `https://api.openai.com/v1` | Direct OpenAI access |
| [Azure OpenAI](https://azure.microsoft.com) | `https://YOUR.openai.azure.com/` | Enterprise OpenAI |
| [LocalAI](https://localai.io) | `http://localhost:8080/v1` | Self-hosted, multi-model |
| [Jan](https://jan.ai) | `http://localhost:1337/v1` | Desktop app with local models |

```bash
# Example: Together AI
OPENAI_BASE_URL=https://api.together.xyz/v1
OPENAI_API_KEY=your-together-key
LLM_MODEL=meta-llama/Llama-3.1-70B-Instruct-Turbo
```

---

### Choosing the Right Setup

| Use Case | Recommended |
|----------|-------------|
| **Just want it to work** | OpenRouter (default) or Nous Portal |
| **Local models, easy setup** | Ollama |
| **Production GPU serving** | vLLM or SGLang |
| **Mac / no GPU** | Ollama or llama.cpp |
| **Multi-provider routing** | LiteLLM Proxy or OpenRouter |
| **Cost optimization** | ClawRouter or OpenRouter with `sort: "price"` |
| **Maximum privacy** | Ollama, vLLM, or llama.cpp (fully local) |
| **Enterprise / Azure** | Azure OpenAI with custom endpoint |
| **Chinese AI models** | z.ai (GLM), Kimi/Moonshot, or MiniMax (first-class providers) |

:::tip
You can switch between providers at any time with `hermes model` — no restart required. Your conversation history, memory, and skills carry over regardless of which provider you use.
:::

## Optional API Keys

| Feature | Provider | Env Variable |
|---------|----------|--------------|
| Web scraping | [Firecrawl](https://firecrawl.dev/) | `FIRECRAWL_API_KEY` |
| Browser automation | [Browserbase](https://browserbase.com/) | `BROWSERBASE_API_KEY`, `BROWSERBASE_PROJECT_ID` |
| Image generation | [FAL](https://fal.ai/) | `FAL_KEY` |
| Premium TTS voices | [ElevenLabs](https://elevenlabs.io/) | `ELEVENLABS_API_KEY` |
| OpenAI TTS + voice transcription | [OpenAI](https://platform.openai.com/api-keys) | `VOICE_TOOLS_OPENAI_KEY` |
| RL Training | [Tinker](https://tinker-console.thinkingmachines.ai/) + [WandB](https://wandb.ai/) | `TINKER_API_KEY`, `WANDB_API_KEY` |
| Cross-session user modeling | [Honcho](https://honcho.dev/) | `HONCHO_API_KEY` |

### Self-Hosting Firecrawl

By default, Hermes uses the [Firecrawl cloud API](https://firecrawl.dev/) for web search and scraping. If you prefer to run Firecrawl locally, you can point Hermes at a self-hosted instance instead.

**What you get:** No API key required, no rate limits, no per-page costs, full data sovereignty.

**What you lose:** The cloud version uses Firecrawl's proprietary "Fire-engine" for advanced anti-bot bypassing (Cloudflare, CAPTCHAs, IP rotation). Self-hosted uses basic fetch + Playwright, so some protected sites may fail. Search uses DuckDuckGo instead of Google.

**Setup:**

1. Clone and start the Firecrawl Docker stack (5 containers: API, Playwright, Redis, RabbitMQ, PostgreSQL — requires ~4-8 GB RAM):
   ```bash
   git clone https://github.com/mendableai/firecrawl
   cd firecrawl
   # In .env, set: USE_DB_AUTHENTICATION=false
   docker compose up -d
   ```

2. Point Hermes at your instance (no API key needed):
   ```bash
   hermes config set FIRECRAWL_API_URL http://localhost:3002
   ```

You can also set both `FIRECRAWL_API_KEY` and `FIRECRAWL_API_URL` if your self-hosted instance has authentication enabled.

## OpenRouter Provider Routing

When using OpenRouter, you can control how requests are routed across providers. Add a `provider_routing` section to `~/.hermes/config.yaml`:

```yaml
provider_routing:
  sort: "throughput"          # "price" (default), "throughput", or "latency"
  # only: ["anthropic"]      # Only use these providers
  # ignore: ["deepinfra"]    # Skip these providers
  # order: ["anthropic", "google"]  # Try providers in this order
  # require_parameters: true  # Only use providers that support all request params
  # data_collection: "deny"   # Exclude providers that may store/train on data
```

**Shortcuts:** Append `:nitro` to any model name for throughput sorting (e.g., `anthropic/claude-sonnet-4:nitro`), or `:floor` for price sorting.

## Terminal Backend Configuration

Configure which environment the agent uses for terminal commands:

```yaml
terminal:
  backend: local    # or: docker, ssh, singularity, modal, daytona
  cwd: "."          # Working directory ("." = current dir)
  timeout: 180      # Command timeout in seconds
```

See [Code Execution](features/code-execution.md) and the [Terminal section of the README](features/tools.md) for details on each backend.

## Memory Configuration

```yaml
memory:
  memory_enabled: true
  user_profile_enabled: true
  memory_char_limit: 2200   # ~800 tokens
  user_char_limit: 1375     # ~500 tokens
```

## Context Compression

```yaml
compression:
  enabled: true
  threshold: 0.85    # Compress at 85% of context limit
```

## Reasoning Effort

Control how much "thinking" the model does before responding:

```yaml
agent:
  reasoning_effort: ""   # empty = medium (default). Options: xhigh (max), high, medium, low, minimal, none
```

When unset (default), reasoning effort defaults to "medium" — a balanced level that works well for most tasks. Setting a value overrides it — higher reasoning effort gives better results on complex tasks at the cost of more tokens and latency.

## TTS Configuration

```yaml
tts:
  provider: "edge"              # "edge" | "elevenlabs" | "openai"
  edge:
    voice: "en-US-AriaNeural"   # 322 voices, 74 languages
  elevenlabs:
    voice_id: "pNInz6obpgDQGcFmaJgB"
    model_id: "eleven_multilingual_v2"
  openai:
    model: "gpt-4o-mini-tts"
    voice: "alloy"              # alloy, echo, fable, onyx, nova, shimmer
```

## Display Settings

```yaml
display:
  tool_progress: all    # off | new | all | verbose
  personality: "kawaii"  # Default personality for the CLI
  compact: false         # Compact output mode (less whitespace)
```

| Mode | What you see |
|------|-------------|
| `off` | Silent — just the final response |
| `new` | Tool indicator only when the tool changes |
| `all` | Every tool call with a short preview (default) |
| `verbose` | Full args, results, and debug logs |

## Speech-to-Text (STT)

```yaml
stt:
  provider: "openai"           # STT provider
```

Requires `VOICE_TOOLS_OPENAI_KEY` in `.env` for OpenAI STT.

## Human Delay

Simulate human-like response pacing in messaging platforms:

```yaml
human_delay:
  mode: "off"                  # off | natural | custom
  min_ms: 500                  # Minimum delay (custom mode)
  max_ms: 2000                 # Maximum delay (custom mode)
```

## Code Execution

Configure the sandboxed Python code execution tool:

```yaml
code_execution:
  timeout: 300                 # Max execution time in seconds
  max_tool_calls: 50           # Max tool calls within code execution
```

## Delegation

Configure subagent behavior for the delegate tool:

```yaml
delegation:
  max_iterations: 50           # Max iterations per subagent
  default_toolsets:             # Toolsets available to subagents
    - terminal
    - file
    - web
```

## Clarify

Configure the clarification prompt behavior:

```yaml
clarify:
  timeout: 120                 # Seconds to wait for user clarification response
```

## Context Files (SOUL.md, AGENTS.md)

Drop these files in your project directory and the agent automatically picks them up:

| File | Purpose |
|------|---------|
| `AGENTS.md` | Project-specific instructions, coding conventions |
| `SOUL.md` | Persona definition — the agent embodies this personality |
| `.cursorrules` | Cursor IDE rules (also detected) |
| `.cursor/rules/*.mdc` | Cursor rule files (also detected) |

- **AGENTS.md** is hierarchical: if subdirectories also have AGENTS.md, all are combined.
- **SOUL.md** checks cwd first, then `~/.hermes/SOUL.md` as a global fallback.
- All context files are capped at 20,000 characters with smart truncation.

## Working Directory

| Context | Default |
|---------|---------|
| **CLI (`hermes`)** | Current directory where you run the command |
| **Messaging gateway** | Home directory `~` (override with `MESSAGING_CWD`) |
| **Docker / Singularity / Modal / SSH** | User's home directory inside the container or remote machine |

Override the working directory:
```bash
# In ~/.hermes/.env or ~/.hermes/config.yaml:
MESSAGING_CWD=/home/myuser/projects    # Gateway sessions
TERMINAL_CWD=/workspace                # All terminal sessions
```