config-hermes/config.yaml

model:
  default: qwen3-30b-a3b
  provider: custom
  base_url: http://100.104.252.1:18080/v1
  api_key: your-secret-key
  context_length: 65536
providers: {}
fallback_providers: []
credential_pool_strategies: {}
toolsets:
- hermes-cli
agent:
  max_turns: 90
  gateway_timeout: 1800
  restart_drain_timeout: 60
  service_tier: ''
  tool_use_enforcement: auto
  gateway_timeout_warning: 900
  gateway_notify_interval: 600
terminal:
  backend: local
  modal_mode: auto
  cwd: .
  timeout: 180
  env_passthrough: []
  docker_image: nikolaik/python-nodejs:python3.11-nodejs20
  docker_forward_env: []
  docker_env: {}
  singularity_image: docker://nikolaik/python-nodejs:python3.11-nodejs20
  modal_image: nikolaik/python-nodejs:python3.11-nodejs20
  daytona_image: nikolaik/python-nodejs:python3.11-nodejs20
  container_cpu: 1
  container_memory: 5120
  container_disk: 51200
  container_persistent: true
  docker_volumes: []
  docker_mount_cwd_to_workspace: false
  persistent_shell: true
browser:
  inactivity_timeout: 120
  command_timeout: 30
  record_sessions: false
  allow_private_urls: false
  cdp_url: ''
  camofox:
    managed_persistence: false
checkpoints:
  enabled: true
  max_snapshots: 50
file_read_max_chars: 100000
compression:
  enabled: true
  threshold: 0.5
  target_ratio: 0.2
  protect_last_n: 20
bedrock:
  region: ''
  discovery:
    enabled: true
    provider_filter: []
    refresh_interval: 3600
  guardrail:
    guardrail_identifier: ''
    guardrail_version: ''
    stream_processing_mode: async
    trace: disabled
smart_model_routing:
  enabled: false
  max_simple_chars: 160
  max_simple_words: 28
  cheap_model: {}
auxiliary:
  vision:
    provider: auto
    model: ''
    base_url: ''
    api_key: ''
    timeout: 120
    download_timeout: 30
  web_extract:
    provider: auto
    model: ''
    base_url: ''
    api_key: ''
    timeout: 360
  compression:
    provider: auto
    model: ''
    base_url: ''
    api_key: ''
    timeout: 120
    context_length: 65536
  session_search:
    provider: auto
    model: ''
    base_url: ''
    api_key: ''
    timeout: 30
  skills_hub:
    provider: auto
    model: ''
    base_url: ''
    api_key: ''
    timeout: 30
  approval:
    provider: auto
    model: ''
    base_url: ''
    api_key: ''
    timeout: 30
  mcp:
    provider: auto
    model: ''
    base_url: ''
    api_key: ''
    timeout: 30
  flush_memories:
    provider: auto
    model: ''
    base_url: ''
    api_key: ''
    timeout: 30
  title_generation:
    provider: auto
    model: ''
    base_url: ''
    api_key: ''
    timeout: 30
display:
  compact: false
  personality: kawaii
  resume_display: full
  busy_input_mode: interrupt
  bell_on_complete: false
  show_reasoning: false
  streaming: false
  inline_diffs: true
  show_cost: false
  skin: default
  interim_assistant_messages: true
  tool_progress_command: false
  tool_progress_overrides: {}
  tool_preview_length: 0
  platforms: {}
dashboard:
  theme: default
privacy:
  redact_pii: false
tts:
  provider: edge
  edge:
    voice: en-US-AriaNeural
  elevenlabs:
    voice_id: pNInz6obpgDQGcFmaJgB
    model_id: eleven_multilingual_v2
  openai:
    model: gpt-4o-mini-tts
    voice: alloy
  xai:
    voice_id: eve
    language: en
    sample_rate: 24000
    bit_rate: 128000
  mistral:
    model: voxtral-mini-tts-2603
    voice_id: c69964a6-ab8b-4f8a-9465-ec0925096ec8
  neutts:
    ref_audio: ''
    ref_text: ''
    model: neuphonic/neutts-air-q4-gguf
    device: cpu
stt:
  enabled: true
  provider: local
  local:
    model: base
    language: ''
  openai:
    model: whisper-1
  mistral:
    model: voxtral-mini-latest
voice:
  record_key: ctrl+b
  max_recording_seconds: 120
  auto_tts: false
  silence_threshold: 200
  silence_duration: 3.0
human_delay:
  mode: 'off'
  min_ms: 800
  max_ms: 2500
context:
  engine: compressor
memory:
  memory_enabled: true
  user_profile_enabled: true
  memory_char_limit: 2200
  user_char_limit: 1375
  provider: ''
delegation:
  model: ''
  provider: ''
  base_url: ''
  api_key: ''
  max_iterations: 50
  reasoning_effort: ''
prefill_messages_file: ''
skills:
  external_dirs: []
honcho: {}
timezone: ''
discord:
  require_mention: true
  free_response_channels: ''
  allowed_channels: ''
  auto_thread: true
  reactions: true
  channel_prompts: {}
whatsapp: {}
telegram:
  channel_prompts: {}
slack:
  channel_prompts: {}
mattermost:
  channel_prompts: {}
approvals:
  mode: manual
  timeout: 60
command_allowlist:
- delete in root path
- stop/restart system service
- in-place edit of system config
- overwrite system config
quick_commands: {}
personalities: {}
security:
  redact_secrets: true
  tirith_enabled: true
  tirith_path: tirith
  tirith_timeout: 5
  tirith_fail_open: true
  website_blocklist:
    enabled: false
    domains: []
    shared_files: []
cron:
  wrap_response: true
logging:
  level: INFO
  max_size_mb: 5
  backup_count: 3
network:
  force_ipv4: false
_config_version: 18

# ── Fallback Model ────────────────────────────────────────────────────
# Automatic provider failover when primary is unavailable.
# Uncomment and configure to enable. Triggers on rate limits (429),
# overload (529), service errors (503), or connection failures.
#
# Supported providers:
#   openrouter   (OPENROUTER_API_KEY)  — routes to any model
#   openai-codex (OAuth — hermes auth) — OpenAI Codex
#   nous         (OAuth — hermes auth) — Nous Portal
#   zai          (ZAI_API_KEY)         — Z.AI / GLM
#   kimi-coding  (KIMI_API_KEY)        — Kimi / Moonshot
#   kimi-coding-cn (KIMI_CN_API_KEY)   — Kimi / Moonshot (China)
#   minimax      (MINIMAX_API_KEY)     — MiniMax
#   minimax-cn   (MINIMAX_CN_API_KEY)  — MiniMax (China)
#
# For custom OpenAI-compatible endpoints, add base_url and api_key_env.
#
# fallback_model:
#   provider: openrouter
#   model: anthropic/claude-sonnet-4
#
# ── Smart Model Routing ────────────────────────────────────────────────
# Optional cheap-vs-strong routing for simple turns.
# Keeps the primary model for complex work, but can route short/simple
# messages to a cheaper model across providers.
#
# smart_model_routing:
#   enabled: true
#   max_simple_chars: 160
#   max_simple_words: 28
#   cheap_model:
#     provider: openrouter
#     model: google/gemini-2.5-flash