Skip to main content

Interface: AgencyOptions

Defined in: packages/agentos/src/api/types.ts:1642

Configuration for the agency() factory function. Extends BaseAgentConfig with a required agents roster and optional multi-agent orchestration settings.

Example​

import { agency, hitl } from '@framers/agentos';

const myAgency = agency({
  provider: 'openai',
  model: 'gpt-4o',
  strategy: 'sequential',
  agents: {
    researcher: { instructions: 'Find relevant papers.' },
    writer:     { instructions: 'Write a clear summary.' },
  },
  controls: { maxTotalTokens: 50_000, onLimitReached: 'warn' },
  hitl: {
    approvals: { beforeTool: ['delete-file'], beforeReturn: true },
    handler: hitl.autoApprove(),
    timeoutMs: 30_000,
    onTimeout: 'reject',
  },
  on: {
    agentStart: (e) => console.log(`[${e.agent}] started`),
    agentEnd: (e) => console.log(`[${e.agent}] done in ${e.durationMs}ms`),
  },
});

See​

agency -- the factory function that consumes this configuration. See BaseAgentConfig for the shared config surface inherited by this interface.

Extends​

  • BaseAgentConfig

Properties​

adaptive?​

optional adaptive: boolean

Defined in: packages/agentos/src/api/types.ts:1669

Whether the orchestrator may override strategy at runtime based on task complexity signals.

agents​

agents: Record<string, BaseAgentConfig | Agent>

Defined in: packages/agentos/src/api/types.ts:1647

Named roster of sub-agents. Each value is either a BaseAgentConfig object (the agency will instantiate it) or a pre-built Agent instance.

apiKey?​

optional apiKey: string

Defined in: packages/agentos/src/api/types.ts:1300

Override the provider API key instead of reading from environment variables.

Inherited from​

BaseAgentConfig.apiKey

avatar?​

optional avatar: AvatarConfig

Defined in: packages/agentos/src/api/types.ts:1440

Avatar visual presentation configuration.

Inherited from​

BaseAgentConfig.avatar

baseUrl?​

optional baseUrl: string

Defined in: packages/agentos/src/api/types.ts:1302

Override the provider base URL (useful for local proxies or Ollama).

Inherited from​

BaseAgentConfig.baseUrl

channels?​

optional channels: Record<string, Record<string, unknown>>

Defined in: packages/agentos/src/api/types.ts:1445

Channel adapter configurations keyed by channel name. Values are channel-specific option objects passed through opaquely.

Inherited from​

BaseAgentConfig.channels

cognitiveMechanisms?​

optional cognitiveMechanisms: CognitiveMechanismsConfig

Defined in: packages/agentos/src/api/types.ts:1492

Cognitive mechanisms config: the eight memory mechanisms of CognitiveMemoryManager (reconsolidation, retrieval-induced forgetting, involuntary recall, feeling of knowing, temporal gist, schema encoding, source-confidence decay and emotion regulation). Pass {} for the defaults, or override fields per mechanism.

The mechanisms run inside a CognitiveMemoryManager initialized with this config (CognitiveMemoryConfig.cognitiveMechanisms). agent() without runtime: 'gmi' and agency() construct no memory manager, so they log a warning and leave this field unused; agent({ runtime: 'gmi' }) with memory on passes it to the agent's memory manager. On the full runtime, a gmiManagerConfig.cognitiveMemoryFactory builds the manager for each GMI.

See​

Cognitive Memory

Inherited from​

BaseAgentConfig.cognitiveMechanisms

controls?​

optional controls: ResourceControls

Defined in: packages/agentos/src/api/types.ts:1467

Resource limits (tokens, cost, time). agency() and the full runtime enforce every field against the entire run. The lightweight agent() helper forwards two of them per call: maxTotalTokens caps each LLM call's completion output (mapped to maxTokens when no explicit maxTokens is set, NOT the prompt+completion run total) and maxDurationMs bounds each LLM request (mapped to requestTimeout). The remaining fields stay agency()-only.

Inherited from​

BaseAgentConfig.controls

customModelParams?​

optional customModelParams: Record<string, unknown>

Defined in: packages/agentos/src/api/types.ts:1410

Provider-specific TOP-LEVEL request-payload parameters forwarded verbatim on every generate/stream/session call via ModelCompletionOptions.customModelParams. Providers spread these onto the outgoing request body — the escape hatch for params the typed options don't model, e.g. OpenRouter provider-routing preferences:

customModelParams: { provider: { sort: 'throughput' } }

Inherited from​

BaseAgentConfig.customModelParams

dependsOn?​

optional dependsOn: string[]

Defined in: packages/agentos/src/api/types.ts:1474

Names of other agents in the agency that must complete before this agent runs. Used with strategy: 'graph' to build an explicit dependency DAG. Agents with no dependsOn are roots and run first.

Example​

`dependsOn: ['researcher']` — this agent waits for `researcher` to finish.

Inherited from​

BaseAgentConfig.dependsOn

discovery?​

optional discovery: DiscoveryConfig

Defined in: packages/agentos/src/api/types.ts:1422

Runtime capability discovery configuration.

Inherited from​

BaseAgentConfig.discovery

effort?​

optional effort: string

Defined in: packages/agentos/src/api/types.ts:1398

Reasoning-effort control forwarded to every generate/stream/session call. On effort-capable Claude models (Opus 4.5+, Sonnet 4.6, Fable/Mythos 5) the provider sends output_config.effort (low|medium|high|xhigh|max). On OpenAI reasoning models (o-series, GPT-5.x) the provider sends reasoning_effort (chat) / reasoning.effort (Responses), with max clamping to xhigh — OpenAI's ceiling — and a model-aware guard capping xhigh → high on ids not probe-verified for xhigh (gpt-5.5/5.6 families are verified). Independent of thinking; ignored on unsupported models/values. Works per-agent in agency() rosters — each sub-agent may pin its own depth.

Inherited from​

BaseAgentConfig.effort

emergent?​

optional emergent: EmergentConfig

Defined in: packages/agentos/src/api/types.ts:1436

Emergent agent synthesis configuration.

Inherited from​

BaseAgentConfig.emergent

guardrails?​

optional guardrails: string[] | GuardrailsConfig

Defined in: packages/agentos/src/api/types.ts:1428

Guardrail policy identifiers or structured config.

  • string[] — shorthand; applies to both input and output.
  • GuardrailsConfig — full control with separate input/output lists.

Inherited from​

BaseAgentConfig.guardrails

hitl?​

optional hitl: HitlConfig

Defined in: packages/agentos/src/api/types.ts:1434

Human-in-the-loop approval configuration.

Inherited from​

BaseAgentConfig.hitl

instructions?​

optional instructions: string

Defined in: packages/agentos/src/api/types.ts:1296

Free-form system instructions prepended to the system prompt.

Inherited from​

BaseAgentConfig.instructions

maxRounds?​

optional maxRounds: number

Defined in: packages/agentos/src/api/types.ts:1674

Maximum number of orchestration rounds before the run is terminated. Applies to iterative strategies like "debate" and "review-loop".

maxSteps?​

optional maxSteps: number

Defined in: packages/agentos/src/api/types.ts:1331

Maximum number of agentic steps (LLM calls) per invocation. Defaults to 5.

Inherited from​

BaseAgentConfig.maxSteps

maxTokens?​

optional maxTokens: number

Defined in: packages/agentos/src/api/types.ts:1364

Upper bound on completion tokens for each LLM call the agent makes. Forwarded to the underlying generateText / streamText call on every generate(), stream(), and session.send() invocation.

Caps tail spend when a model misbehaves and yaps past the intended output size. Omit to use the provider default — AnthropicProvider defaults to 16000 (set 2026-05-17; was 4096), OpenAIProvider defaults to 4096, GeminiProvider defaults to 8192. Set to ~2× the agent's typical response size so normal calls finish naturally and only runaway generations hit the cap.

Example​

// Cap a roleplay agent at 1024 — short turns, fast feedback.
const companion = agent({
  provider: 'anthropic',
  model: 'claude-sonnet-4-6',
  instructions: 'Reply in character. 2-3 sentences.',
  maxTokens: 1024,
});

// Tool-use agent emitting verbose JSON — go big so structured
// output doesn't truncate mid-token. Opus 4.7 supports 32000.
const codegen = agent({
  provider: 'anthropic',
  model: 'claude-opus-4-7',
  tools: { GenerateCode, RunTests, JudgeOutput },
  maxTokens: 16000,
});

Inherited from​

BaseAgentConfig.maxTokens

memory?​

optional memory: boolean | MemoryConfig

Defined in: packages/agentos/src/api/types.ts:1418

Memory configuration. agent() reads it only with runtime: 'gmi', where true or a MemoryConfig turns on cognitive memory for the agent's sessions (its embedding and consolidation fields are read) and false keeps it off, also under cognition: 'full'. A session's message history is set by history, not by this field.

Inherited from​

BaseAgentConfig.memory

model?​

optional model: string

Defined in: packages/agentos/src/api/types.ts:1289

Model identifier. Accepted in two formats:

  • Plain model name (e.g. "gpt-4o") when provider is also set. Preferred.
  • "provider:model" combined string (e.g. "openai:gpt-4o").

Inherited from​

BaseAgentConfig.model

name?​

optional name: string

Defined in: packages/agentos/src/api/types.ts:1298

Display name for the agent, injected into the system prompt.

Inherited from​

BaseAgentConfig.name

observability?​

optional observability: ObservabilityConfig

Defined in: packages/agentos/src/api/types.ts:1455

Observability and telemetry configuration.

Inherited from​

BaseAgentConfig.observability

on?​

optional on: AgencyCallbacks

Defined in: packages/agentos/src/api/types.ts:1457

Event callbacks fired at various lifecycle points during the run.

Inherited from​

BaseAgentConfig.on

output?​

optional output: unknown

Defined in: packages/agentos/src/api/types.ts:1451

Output schema for structured generation. Accepts a Zod schema at runtime; typed as unknown here to avoid a hard dependency on the zod package in the types layer.

Inherited from​

BaseAgentConfig.output

permissions?​

optional permissions: PermissionsConfig

Defined in: packages/agentos/src/api/types.ts:1432

Fine-grained tool and resource permission overrides.

Inherited from​

BaseAgentConfig.permissions

personality?​

optional personality: Partial<{ agreeableness: number; conscientiousness: number; emotionality: number; extraversion: number; honesty: number; honesty_humility: number; honestyHumility: number; openness: number; opennessToExperience: number; }>

Defined in: packages/agentos/src/api/types.ts:1310

HEXACO-inspired personality trait overrides (0–1 scale). Encoded as a human-readable trait string appended to the system prompt. The SOUL.md spellings honestyHumility / honesty_humility and opennessToExperience are accepted for honesty and openness; when both spellings are given, the canonical key wins.

Inherited from​

BaseAgentConfig.personality

provenance?​

optional provenance: AgencyProvenanceConfig

Defined in: packages/agentos/src/api/types.ts:1453

Provenance and audit-trail configuration.

Inherited from​

BaseAgentConfig.provenance

provider?​

optional provider: string

Defined in: packages/agentos/src/api/types.ts:1294

Provider name (e.g. "openai", "anthropic", "ollama"). Auto-detected from environment API keys when omitted.

Inherited from​

BaseAgentConfig.provider

quorum?​

optional quorum: AgencyQuorumConfig

Defined in: packages/agentos/src/api/types.ts:1659

Minimum viable panel for the parallel strategy, checked AFTER the fan-out against the agents that actually SUCCEEDED (HITL-rejected and errored agents don't count): minAgents = successful agents required; minProviders = distinct providers among them — provider diversity is what makes a multi-model panel meaningful, and a panel that quietly collapsed to one vendor must not synthesize a false consensus. Shortfall throws AgencyQuorumError by default; set onShortfall: 'proceed' to log a warning and synthesize anyway. Ignored by strategies other than parallel.

rag?​

optional rag: RagConfig

Defined in: packages/agentos/src/api/types.ts:1420

Retrieval-Augmented Generation configuration.

Inherited from​

BaseAgentConfig.rag

security?​

optional security: object

Defined in: packages/agentos/src/api/types.ts:1430

Security tier controlling permitted tools and capabilities.

tier​

tier: SecurityTier

Inherited from​

BaseAgentConfig.security

strategy?​

optional strategy: AgencyStrategy

Defined in: packages/agentos/src/api/types.ts:1664

Orchestration strategy for coordinating sub-agents. Defaults to "sequential" when omitted.

thinking?​

optional thinking: false | { budgetTokens: number; }

Defined in: packages/agentos/src/api/types.ts:1385

Extended-thinking switch forwarded to Claude models on every generate() / stream() / session call this agent makes. Any positive budgetTokens turns adaptive thinking on (the number itself is not sent). false turns thinking off with the model's own off shape; Opus 5.5, Fable and Mythos always think. Omitted keeps the model's default: thinking on for Opus 5 and later, Sonnet 5 and later, Fable and Mythos, off for older models. Other providers ignore it.

Example​

const codegen = agent({
  provider: 'anthropic',
  model: 'claude-opus-5',
  tools: { GenerateCode, RunTests, JudgeOutput },
  maxTokens: 24000,
  thinking: { budgetTokens: 8000 },
});

Inherited from​

BaseAgentConfig.thinking

tools?​

optional tools: AdaptableToolInput

Defined in: packages/agentos/src/api/types.ts:1329

Tools available to the agent on every call.

Accepts:

  • a named high-level tool map
  • an ExternalToolRegistry (Record, Map, or iterable)
  • a prompt-only ToolDefinitionForLLM[]

Inherited from​

BaseAgentConfig.tools

verifyCitations?​

optional verifyCitations: VerifyCitationsConfig

Defined in: packages/agentos/src/api/types.ts:1525

Auto-verify citations after every generation.

When set, the agent retrieves sources for each user input, runs generation, then scores each atomic claim in the response against the retrieved sources via CitationVerifier. The resulting VerifiedResponse is attached to the generation result's grounding field — no separate verifier.verify(text, sources) call needed.

Pass a config object with the embedding function and the source retriever the verifier should use:

Example​

const docsAgent = agent({
  provider: 'openai',
  model: 'gpt-4o',
  verifyCitations: {
    embedFn:  (texts) => embeddingManager.embedBatch(texts),
    retrieve: (query) => retriever.search(query),
  },
});

const result = await docsAgent.generate('How do I configure a guardrail?');
console.log(result.text);
console.log(result.grounding?.overallGrounded);
for (const claim of result.grounding?.claims ?? []) {
  if (claim.verdict !== 'supported') console.warn(claim.text);
}

Inherited from​

BaseAgentConfig.verifyCitations

voice?​

optional voice: VoiceConfig

Defined in: packages/agentos/src/api/types.ts:1438

Voice interface configuration.

Inherited from​

BaseAgentConfig.voice