Frona is configured through a YAML config file at data/config.yaml. You can change the path by setting the FRONA_CONFIG environment variable.

Environment variables with the FRONA_ prefix override values from the config file. For example, FRONA_SERVER_PORT=9999 overrides server.port in the YAML. See Configuration for the environment variable reference.

Server

General server settings.

server:
  port: 3001
  base_url: https://frona.example.com
  backend_url: http://localhost:3001
  frontend_url: http://localhost:3000
  static_dir: /app/static
  issuer_url: https://frona.example.com
  max_concurrent_tasks: 10
  sandbox_disabled: false
  sandbox_max_agent_cpu_pct: 95.0
  sandbox_max_agent_memory_pct: 80.0
  sandbox_max_total_cpu_pct: 98.0
  sandbox_max_total_memory_pct: 90.0
  sandbox_timeout_secs: 0
  sse_pending_events_secs: 60
  cors_origins: https://app.example.com
  max_body_size_bytes: 104857600
  shutdown_timeout_secs: 60

Field	Type	Default	Description
port	integer	3001	HTTP server port
base_url	string	--	Public-facing base URL, used for callbacks and links
backend_url	string	--	Override backend API URL
frontend_url	string	--	Override frontend URL
static_dir	string	/app/static	Directory serving the frontend static files
issuer_url	string	--	JWT token issuer URL
max_concurrent_tasks	integer	10	Maximum concurrent background tasks across all agents
sandbox_disabled	boolean	false	Disable CLI/Python/Node.js sandboxing. Not recommended for production
sandbox_max_agent_cpu_pct	float	95.0	Maximum CPU percentage a single agent can use
sandbox_max_agent_memory_pct	float	80.0	Maximum memory percentage a single agent can use
sandbox_max_total_cpu_pct	float	98.0	Maximum total CPU percentage all agents can use
sandbox_max_total_memory_pct	float	90.0	Maximum total memory percentage all agents can use
sandbox_timeout_secs	integer	0	Global sandbox execution timeout. 0 means no timeout
sse_pending_events_secs	integer	60	How long to buffer SSE events after client disconnects
cors_origins	string	--	Allowed CORS origins
max_body_size_bytes	integer	104857600 (100 MB)	Maximum HTTP request body size
shutdown_timeout_secs	integer	60	Graceful shutdown timeout

Auth

Authentication and token settings.

auth:
  encryption_secret: change-this-in-production
  access_token_expiry_secs: 900
  refresh_token_expiry_secs: 604800
  presign_expiry_secs: 86400

Field	Type	Default	Description
encryption_secret	string	dev-secret-change-in-production	Secret used to derive the AES-256 key that encrypts JWT signing keypairs at rest. Must be changed in production
access_token_expiry_secs	integer	900 (15 min)	How long access tokens are valid
refresh_token_expiry_secs	integer	604800 (7 days)	How long refresh tokens are valid
presign_expiry_secs	integer	86400 (24 hours)	How long pre-signed URLs are valid

:::caution[Change the encryption secret in production] encryption_secret is used to derive an AES-256 encryption key (via SHA-256) that protects the JWT signing keypairs stored in the database. It is not used directly for JWT signing — instead it encrypts the private keys that do the signing.

A built-in default is provided for local development, but you must set your own value in production. If the default is left in place and database files are ever exposed (backup leak, file traversal, shared host), an attacker could decrypt the signing keypairs and forge authentication tokens for any user.

Generate a strong random secret:

openssl rand -base64 32

:::

SSO

OpenID Connect single sign-on. Disabled by default.

sso:
  enabled: true
  authority: https://auth.example.com
  client_id: your-client-id
  client_secret: your-client-secret
  scopes: openid email
  disable_local_auth: false
  signups_match_email: true
  allow_unknown_email_verification: true
  client_cache_expiration: 0

Field	Type	Default	Description
enabled	boolean	false	Enable OIDC authentication
authority	string	--	OpenID Connect authority URL
client_id	string	--	OAuth client ID
client_secret	string	--	OAuth client secret
scopes	string	openid email	OpenID scopes to request
disable_local_auth	boolean	false	Force SSO-only authentication. Disables local login
signups_match_email	boolean	true	Match SSO signups to existing accounts by email
allow_unknown_email_verification	boolean	true	Accept emails not verified by the identity provider
client_cache_expiration	integer	0	Client metadata cache expiration in seconds

Database

database:
  path: data/db

Field	Type	Default	Description
path	string	data/db	Path to the SurrealDB data directory

Browser

Headless Chrome configuration for browser automation. Optional. If not configured, browser tools are unavailable.

browser:
  ws_url: ws://browserless:3333
  profiles_path: /profiles
  connection_timeout_ms: 30000
  api_token: your-browserless-token

Field	Type	Default	Description
ws_url	string	--	WebSocket URL of the Browserless instance
profiles_path	string	/profiles	Directory for storing browser profiles
connection_timeout_ms	integer	30000 (30s)	Timeout for connecting to the browser service
api_token	string	--	Authentication token for the Browserless HTTP API

Search

Web search provider configuration. Optional. If not configured, search tools are unavailable.

search:
  provider: searxng
  searxng_base_url: http://searxng:8080

Field	Type	Default	Description
provider	string	--	Search provider: searxng, tavily, or brave
searxng_base_url	string	--	Base URL of the SearXNG instance

Vault

External vault provider configuration. Credentials set here create system-managed vault connections that sync automatically on startup. See Vault Providers for details.

vault:
  onepassword_service_account_token: ops_...
  onepassword_vault_id: abc123
  bitwarden_client_id: user.xxx
  bitwarden_client_secret: xxx
  bitwarden_master_password: xxx
  bitwarden_server_url: https://vault.example.com
  hashicorp_address: http://localhost:8200
  hashicorp_token: hvs.xxx
  hashicorp_mount: secret
  keepass_path: /path/to/vault.kdbx
  keepass_password: xxx
  keeper_app_key: xxx

Field	Type	Default	Description
onepassword_service_account_token	string	--	1Password service account token
onepassword_vault_id	string	--	1Password default vault ID
bitwarden_client_id	string	--	Bitwarden personal API key client ID
bitwarden_client_secret	string	--	Bitwarden personal API key client secret
bitwarden_master_password	string	--	Bitwarden master password
bitwarden_server_url	string	--	Bitwarden server URL (for self-hosted)
hashicorp_address	string	--	HashiCorp Vault server address
hashicorp_token	string	--	HashiCorp Vault auth token
hashicorp_mount	string	secret	HashiCorp Vault KV2 mount path
keepass_path	string	--	Path to KeePass .kdbx file
keepass_password	string	--	KeePass master password
keeper_app_key	string	--	Keeper Secrets Manager app key

Storage

File storage paths.

storage:
  workspaces_path: data/workspaces
  files_path: data/files
  shared_config_dir: resources
  skills_dir: data/skills
  cache_dir: data/system/cache

Field	Type	Default	Description
workspaces_path	string	data/workspaces	Directory for agent workspace files
files_path	string	data/files	Directory for file uploads and attachments
shared_config_dir	string	resources	Directory containing shared prompts and agent configurations
skills_dir	string	data/skills	Directory for installed shared skills
cache_dir	string	data/system/cache	Directory for system caches (skill registry, etc.)

Scheduler

Background job intervals.

scheduler:
  poll_secs: 60
  space_compaction_secs: 3600
  memory_compaction_secs: 7200

Field	Type	Default	Description
poll_secs	integer	60 (1 min)	How often the scheduler checks for due tasks
space_compaction_secs	integer	3600 (1 hour)	Interval for space context compaction
memory_compaction_secs	integer	7200 (2 hours)	Interval for memory compaction

Inference

LLM inference settings.

inference:
  max_tool_turns: 200
  default_max_tokens: 8192
  compaction_trigger_pct: 80
  history_truncation_pct: 90

Field	Type	Default	Description
max_tool_turns	integer	200	Maximum tool call iterations per agent response
default_max_tokens	integer	8192	Default max tokens for LLM responses
compaction_trigger_pct	integer	80	Context usage percentage that triggers message compaction
history_truncation_pct	integer	90	Context usage percentage that triggers history truncation

Voice

Twilio voice call configuration. Optional. If not configured, voice tools are unavailable.

voice:
  provider: twilio
  twilio_account_sid: your-account-sid
  twilio_auth_token: your-auth-token
  twilio_from_number: "+15551234567"
  twilio_voice_id: Polly.Matthew
  twilio_speech_model: enhanced
  callback_base_url: https://frona.example.com

Field	Type	Default	Description
provider	string	--	Voice provider. Currently only twilio is supported
twilio_account_sid	string	--	Twilio account SID
twilio_auth_token	string	--	Twilio auth token
twilio_from_number	string	--	Twilio phone number for outbound calls (E.164 format)
twilio_voice_id	string	--	Twilio voice ID for text-to-speech
twilio_speech_model	string	--	Twilio speech recognition model
callback_base_url	string	--	Public URL for Twilio callbacks. Overrides server.base_url for voice

Providers

LLM provider API keys and endpoints. Providers can also be auto-discovered from environment variables (e.g., ANTHROPIC_API_KEY, OPENAI_API_KEY).

providers:
  anthropic:
    api_key: sk-ant-...
    enabled: true
  openai:
    api_key: sk-...
    enabled: true
  ollama:
    base_url: http://localhost:11434/v1
    enabled: true

Field	Type	Default	Description
api_key	string	--	API key for the provider
base_url	string	--	Custom base URL (for self-hosted models like Ollama)
enabled	boolean	true	Whether this provider is active

Supported providers: anthropic, openai, groq, openrouter, deepseek, gemini, cohere, mistral, perplexity, together, xai, hyperbolic, moonshot, mira, galadriel, huggingface, ollama.

Models

Model groups define which LLM an agent uses. Each group is tagged with a provider and has a primary model, optional fallbacks, and provider-specific parameters.

Model groups cannot be set via environment variables. They must be configured in the config file.

Common fields

These fields are available for all providers:

Field	Type	Default	Description
provider	string	required	Provider name (see below)
model	string	required	Model ID (without provider prefix)
fallbacks	list	[]	Fallback model groups tried in order if the primary fails
max_tokens	integer	--	Maximum tokens to generate per response
temperature	float	--	Sampling temperature (0.0-2.0)
context_window	integer	--	Override context window size
retry.max_retries	integer	10	Maximum retry attempts on failure
retry.initial_backoff_ms	integer	1000 (1s)	Initial backoff between retries
retry.backoff_multiplier	float	2.0	Exponential backoff multiplier
retry.max_backoff_ms	integer	60000 (60s)	Maximum backoff duration

Anthropic

models:
  primary:
    provider: anthropic
    model: claude-sonnet-4-5-20250514
    max_tokens: 8192
    thinking:
      type: enabled
      budget_tokens: 10000
    top_p: 0.9
    top_k: 40

Additional fields: thinking (with type and budget_tokens), top_p, top_k, stop_sequences.

OpenAI, Groq, OpenRouter, DeepSeek, xAI, Together, Hyperbolic

These providers share the same parameter set:

models:
  coding:
    provider: openai
    model: gpt-4o
    max_tokens: 8192
    top_p: 0.9
    reasoning_effort: high

Additional fields: top_p, min_p, frequency_penalty, presence_penalty, seed, max_completion_tokens, reasoning_effort, logprobs, top_logprobs, stop.

Gemini

models:
  reasoning:
    provider: gemini
    model: gemini-2.5-pro
    thinking_config:
      thinking_budget: 10000
      include_thoughts: true

Additional fields: thinking_config (with thinking_budget and include_thoughts), top_p, top_k, stop_sequences, candidate_count.

Ollama

models:
  local:
    provider: ollama
    model: llama3.1
    num_ctx: 8192
    num_predict: 4096

Additional fields: think, num_ctx, num_predict, num_batch, num_keep, num_thread, num_gpu, top_k, top_p, min_p, repeat_penalty, repeat_last_n, frequency_penalty, presence_penalty, mirostat, mirostat_eta, mirostat_tau, tfs_z, seed, stop, use_mmap, use_mlock.

Generic

For any other provider. Only common fields are available.

models:
  custom:
    provider: generic
    model: my-model

Apps

Settings for agent-deployed applications.

app:
  port_range_start: 4000
  port_range_end: 4100
  health_check_timeout_secs: 30
  max_restart_attempts: 2
  hibernate_after_secs: 259200

Field	Type	Default	Description
port_range_start	integer	4000	Start of the port range for app allocation
port_range_end	integer	4100	End of the port range for app allocation
health_check_timeout_secs	integer	30	Maximum time to wait for an app to become healthy during deployment
max_restart_attempts	integer	2	How many times to restart a crashed app before marking it as failed
hibernate_after_secs	integer	259200 (3 days)	Inactivity duration before auto-hibernating an app

Cache

Entity caching settings.

cache:
  entity_ttl_secs: 300
  entity_max_capacity: 1000

Field	Type	Default	Description
entity_ttl_secs	integer	300 (5 min)	Time-to-live for cached entities
entity_max_capacity	integer	1000	Maximum number of cached entities

Sensitive values

These fields are automatically redacted in logs: auth.encryption_secret, sso.client_secret, voice.twilio_account_sid, voice.twilio_auth_token, all vault.* credential fields, and all providers[*].api_key values.