{"id":"jnmetacode-agency-orchestrator","name":"agency-orchestrator","af_score":65.2,"security_score":47.5,"reliability_score":40.0,"what_it_does":"agency-orchestrator is a TypeScript multi-agent orchestration engine that runs YAML-defined DAG workflows using prebuilt role prompts (186 roles). It can execute steps in parallel based on dependencies, pass outputs between steps via variables, and supports execution via multiple LLM providers/CLIs (including subscription-based “no API key” flows) as well as an MCP server mode for tool-calling from AI coding clients.","best_when":"You want to compose multi-agent workflows quickly (YAML DAGs), reuse prebuilt role prompts, and run within the capabilities of supported providers/CLIs or via MCP from IDE/coding agents.","avoid_when":"You need strict, auditable enterprise security controls, fine-grained authorization scopes, or a clearly documented stable public HTTP API for integration.","last_evaluated":"2026-03-30T13:50:45.377651+00:00","has_mcp":true,"has_api":false,"auth_methods":["Provider-specific subscription/CLI authentication (e.g., claude-code, gemini-cli, copilot-cli, codex-cli, openclaw-cli)","API-key based providers via environment variables (OPENAI_API_KEY, ANTHROPIC_API_KEY, DEEPSEEK_API_KEY, and OpenAI-compatible base_url/api_key)","Local model via Ollama (typically local runtime authorization/none)"],"has_free_tier":true,"known_gotchas":["Behavior depends heavily on the selected provider/CLI; provider-specific rate limits and auth errors may surface differently.","DAG parallelism may expose race conditions if steps have implicit dependencies not captured via depends_on/variables.","Resuming relies on prior output files/metadata.json; using incorrect directories may lead to missing variables or partial reruns.","When using MCP from IDE tools, ensure the command/args match the installed package version and runtime environment."],"error_quality":0.0}