---
title: "Agents Reference"
description: "Complete reference for all 36 OrchestKit agents."
canonical: "https://orchestkit.yonyon.ai/docs/reference/agents"
---

# Agents Reference

Complete reference for all 36 OrchestKit agents.

# Agents Reference

OrchestKit includes **36 specialized agents** — AI personas with curated tools, skills, and behavioral directives.

| Agent | Model | Description |
|-------|-------|-------------|
| [Accessibility Specialist](/docs/reference/agents/accessibility-specialist) | sonnet | Accessibility expert: WCAG 2.2 audits, screen reader compat, keyboard navigation, ARIA patterns, automated a11y testing |
| [Ai Safety Auditor](/docs/reference/agents/ai-safety-auditor) | opus | AI safety and security auditor for LLM systems. Red teaming, prompt injection, jailbreak testing, guardrail validation, and OWASP LLM compliance |
| [Backend System Architect](/docs/reference/agents/backend-system-architect) | inherit | Backend architect: REST/GraphQL APIs, database schemas, microservice boundaries, distributed systems, clean architecture |
| [Ci Cd Engineer](/docs/reference/agents/ci-cd-engineer) | inherit | CI/CD specialist: GitHub Actions, GitLab CI pipelines, deployment automation, build optimization, caching, security scanning |
| [Claude Design Orchestrator](/docs/reference/agents/claude-design-orchestrator) | sonnet | Parses claude.ai/design handoff bundles: validates schema, dedups proposed components against the codebase via component-search, reconciles tokens, and tracks bundle→PR provenance so design intent stays linked to shipped code |
| [Code Quality Reviewer](/docs/reference/agents/code-quality-reviewer) | inherit | Code quality reviewer: bug detection, security vulnerabilities, performance issues, linting, type checking, test coverage |
| [Component Curator](/docs/reference/agents/component-curator) | inherit | Component library curator: audits project component usage, searches 21st.dev registry for alternatives, tracks component freshness, and recommends upgrades for design consistency |
| [Data Pipeline Engineer](/docs/reference/agents/data-pipeline-engineer) | haiku | Data pipeline specialist: embeddings, chunking strategies, vector indexes, data transformation for AI consumption |
| [Database Engineer](/docs/reference/agents/database-engineer) | sonnet | PostgreSQL specialist: schema design, migrations, query optimization, pgvector/full-text search, Alembic migrations |
| [Debug Investigator](/docs/reference/agents/debug-investigator) | sonnet | Debug specialist: systematic root cause analysis, execution path tracing, log and stack trace analysis |
| [Demo Producer](/docs/reference/agents/demo-producer) | sonnet | Universal demo video producer that creates polished marketing videos for any content - skills, agents, plugins, tutorials, CLI tools, or code walkthroughs. Uses VHS terminal recording and Remotion composition |
| [Deployment Manager](/docs/reference/agents/deployment-manager) | haiku | Deployment specialist: production releases, rollback procedures, feature flags, blue-green/zero-downtime deployments |
| [Design Context Extractor](/docs/reference/agents/design-context-extractor) | inherit | Design context extraction: analyzes screenshots, URLs, or live apps to extract color palettes, typography, spacing, and component patterns as structured design tokens |
| [Design System Architect](/docs/reference/agents/design-system-architect) | inherit | Design system architect: token hierarchies, theming strategies, component library design, Figma-to-code pipelines, and design governance |
| [Emulate Engineer](/docs/reference/agents/emulate-engineer) | inherit | Stateful API emulation via Vercel emulate. Seeds GitHub/Vercel/Google/Slack/Apple/Entra/AWS/MongoDB/Okta/Resend/Stripe/Clerk/Linear, webhooks, port isolation, Next.js adapter. Use to replace flaky API mocks |
| [Eval Runner](/docs/reference/agents/eval-runner) | haiku | LLM evaluation specialist who runs structured eval datasets, computes quality metrics using DeepEval/RAGAS, tracks regression across model versions, and reports to Langfuse for tracing and scoring |
| [Event Driven Architect](/docs/reference/agents/event-driven-architect) | opus | Event-driven architecture specialist who designs event sourcing systems, message queue topologies, and CQRS patterns. Focuses on Kafka, RabbitMQ, Redis Streams, FastStream, outbox pattern, and distributed transaction patterns |
| [Expect Agent](/docs/reference/agents/expect-agent) | sonnet | Browser test execution: runs diff-aware test plans via agent-browser with ARIA selectors, status protocol, and 6-category failure classification |
| [Frontend Performance Engineer](/docs/reference/agents/frontend-performance-engineer) | sonnet | Performance engineer who optimizes Core Web Vitals, analyzes bundles, profiles render performance, and sets up RUM |
| [Frontend Ui Developer](/docs/reference/agents/frontend-ui-developer) | inherit | Frontend developer: React 19/TypeScript components, optimistic updates, Zod-validated APIs, design system tokens, animation/motion, modern 2026 patterns |
| [Genui Architect](/docs/reference/agents/genui-architect) | inherit | Generative UI and json-render catalog specialist. Designs Zod-typed catalogs, selects shadcn components, constrains props for AI safety |
| [Git Operations Engineer](/docs/reference/agents/git-operations-engineer) | haiku | Git operations: branch management, rebases, merges, stacked PRs, recovery operations, clean commit history |
| [Infrastructure Architect](/docs/reference/agents/infrastructure-architect) | inherit | Infrastructure as Code specialist who designs Terraform modules, Kubernetes manifests, and cloud architecture. Focuses on AWS/GCP/Azure patterns, networking, security groups, and cost optimization |
| [Llm Integrator](/docs/reference/agents/llm-integrator) | sonnet | LLM integration: OpenAI/Anthropic/Ollama APIs, prompt templates, function calling, streaming, token cost optimization |
| [Market Intelligence](/docs/reference/agents/market-intelligence) | haiku | Market research: competitive landscapes, market trends, TAM/SAM/SOM sizing, threat/opportunity analysis |
| [Monitoring Engineer](/docs/reference/agents/monitoring-engineer) | haiku | Observability and monitoring specialist. Prometheus metrics, Grafana dashboards, alerting rules, distributed tracing, log aggregation, and SLOs/SLIs |
| [Multimodal Specialist](/docs/reference/agents/multimodal-specialist) | sonnet | Vision, audio, image and video generation, and multimodal processing specialist. Integrates Claude Opus 4.8, GPT-5, Gemini 2.5/3, GPT Image 2, Nano Banana Pro, Kling 3.0, Sora 2 and Veo 3.1 for analysis, generation, transcription and multimodal RAG |
| [Product Strategist](/docs/reference/agents/product-strategist) | inherit | Product strategist: value proposition validation, feature-business alignment, build/buy/partner decisions, go/no-go |
| [Python Performance Engineer](/docs/reference/agents/python-performance-engineer) | inherit | Python performance: profiling, memory optimization, async performance, database query optimization, caching, load testing |
| [Release Engineer](/docs/reference/agents/release-engineer) | haiku | Release and versioning specialist who manages GitHub releases, milestones, changelogs, and semantic versioning. Handles release automation and project tracking |
| [Security Auditor](/docs/reference/agents/security-auditor) | opus | Security auditor: vulnerability scanning, dependency audits, OWASP Top 10 compliance, secrets detection, remediation |
| [Security Layer Auditor](/docs/reference/agents/security-layer-auditor) | opus | Security layer auditor who verifies defense-in-depth implementation across 8 security layers, from edge to storage, ensuring comprehensive protection |
| [System Design Reviewer](/docs/reference/agents/system-design-reviewer) | opus | System design reviewer who evaluates implementation plans against scale, data, security, UX, and coherence criteria before code is written |
| [Test Generator](/docs/reference/agents/test-generator) | inherit | Test specialist: coverage gap analysis, unit/integration test generation, fixtures, API mocking (MSW), HTTP recording |
| [Web Research Analyst](/docs/reference/agents/web-research-analyst) | sonnet | Web research: browser automation, Tavily API, competitive intelligence, documentation capture, technical recon |
| [Workflow Architect](/docs/reference/agents/workflow-architect) | opus | Multi-agent workflow: LangGraph pipelines, supervisor-worker patterns, state/checkpointing, RAG orchestration |