DAG Orchestration
Declarative JSON-based directed acyclic graphs with parallel lanes, hard barriers, and supervisor checkpoints — zero boilerplate.
Learn more →Features
Everything you need to build, deploy, and operate production AI workflows — from a single JSON file to fully compliance-ready multi-tenant orchestration.
Declarative JSON-based directed acyclic graphs with parallel lanes, hard barriers, and supervisor checkpoints — zero boilerplate.
Learn more →Automatically selects the optimal model tier (Haiku → Sonnet → Opus) based on task complexity and remaining budget.
Learn more →Exponential-backoff retry, per-provider circuit breakers, and graceful fallbacks keep workflows running through transient failures.
Learn more →Token-by-token LLM output streamed live to stdout — every provider, including the built-in Mock provider.
Learn more →Role-based access control with RS256/ES256 JWT validation. Every run is principal-tagged and GDPR-ready.
Learn more →Hash-chained tamper-proof audit logs for every agent action — compliance-ready out of the box.
Learn more →Hard filesystem and runtime isolation per tenant — each run lives in its own scoped directory tree.
Learn more →Automatic regex-based detection and redaction of emails, phone numbers, SSNs, and API keys before they reach LLM providers.
Learn more →Full-featured command-line tool — init, sync, check, run DAGs, plan entire projects, visualise graphs.
Learn more →Native Model Context Protocol bridge — connect ai-agencee directly to Claude Desktop or VS Code Copilot.
Learn more →Fluent, fully type-safe DSL for constructing DAGs in code — no JSON required.
Learn more →Subscribe to real-time DAG lifecycle events — token streams, cost updates, lane status — with full TypeScript typing.
Learn more →