{"passport":{"unfragile":{"@version":"1.0","version":"2026-05","artifact":{"id":"crewai-template","slug":"crewai-template","name":"CrewAI Template","type":"template","url":"https://github.com/crewAIInc/crewAI-examples","page_url":"https://unfragile.ai/crewai-template","categories":["app-builders"],"tags":[],"pricing":{"model":"free","free":true,"starting_price":null},"status":"active","verified":false},"capabilities":[{"id":"crewai-template__cap_0","uri":"capability://planning.reasoning.role.based.multi.agent.crew.orchestration.with.yaml.configuration","name":"role-based multi-agent crew orchestration with yaml configuration","description":"Defines crews as collections of specialized agents with distinct roles, goals, and backstories, orchestrated through a Crew → Agent → Task hierarchy. Agents are configured via YAML files (e.g., gamedesign.yaml) that specify agent personality, tools, and task dependencies, enabling declarative composition of multi-agent workflows without code changes. The framework handles agent sequencing, context passing between agents, and collaborative task execution through a centralized crew coordinator.","intents":["I want to define a team of AI agents with different roles (researcher, writer, reviewer) that work together on a project","I need to configure agent behavior and capabilities through configuration files rather than hardcoding agent definitions","I want agents to pass context and results between tasks in a structured workflow"],"best_for":["teams building multi-agent systems for content creation, research, or analysis","developers who prefer declarative configuration over imperative agent setup","projects requiring role-based agent specialization with clear task dependencies"],"limitations":["YAML configuration approach scales linearly with crew complexity; large crews (20+ agents) require careful task dependency management","No built-in conflict resolution when multiple agents produce contradictory outputs","Agent communication is task-based only; no direct inter-agent messaging or negotiation patterns"],"requires":["Python 3.9+","crewAI framework 0.130.0 or later","YAML configuration files for agent and task definitions","LLM API access (OpenAI, Anthropic, or compatible provider)"],"input_types":["YAML configuration files","natural language task descriptions","structured agent role definitions"],"output_types":["structured task results","agent execution logs","collaborative workflow outputs"],"categories":["planning-reasoning","automation-workflow"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"crewai-template__cap_1","uri":"capability://automation.workflow.flow.based.workflow.with.conditional.routing.and.human.in.the.loop.decision.points","name":"flow-based workflow with conditional routing and human-in-the-loop decision points","description":"Implements advanced workflow orchestration using CrewAI Flow framework with state machines, conditional branching, and asynchronous processing. Workflows support human oversight checkpoints (e.g., Lead Score Flow approval gates) where humans review and approve agent decisions before proceeding. The flow system manages complex state transitions, parallel task execution, and interactive decision routing based on agent outputs, enabling workflows like lead scoring with approval, email auto-response, and book writing with chapter reviews.","intents":["I need to build a workflow where AI agents make recommendations but humans must approve before taking action","I want to route workflow execution conditionally based on agent analysis results (e.g., high-score leads vs low-score leads)","I need to orchestrate multi-step processes with async tasks and state management across agent handoffs"],"best_for":["business processes requiring human oversight (lead scoring, hiring, content approval)","workflows with conditional logic based on agent outputs","teams building complex multi-step automation with interactive checkpoints"],"limitations":["Human-in-the-loop checkpoints introduce latency; no built-in timeout handling for approval delays","State management requires external persistence for production use; in-memory state is lost on process restart","Conditional routing logic must be defined in Python; no visual workflow builder for non-technical users"],"requires":["Python 3.9+","crewAI framework 0.130.0+ with Flow support","async/await runtime support","optional: external state store (Redis, database) for persistence"],"input_types":["structured workflow definitions","agent output results","human approval decisions"],"output_types":["workflow execution state","conditional routing decisions","final workflow results with audit trail"],"categories":["automation-workflow","planning-reasoning"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"crewai-template__cap_10","uri":"capability://text.generation.language.book.writing.workflow.with.multi.chapter.composition.and.human.review","name":"book writing workflow with multi-chapter composition and human review","description":"Implements a structured book writing system using CrewAI Flow where agents collaborate on chapter composition, outline generation, and content review. The Book Writing Flow demonstrates how agents can work sequentially on different chapters, maintain narrative consistency, and incorporate human feedback at review checkpoints. The workflow manages chapter dependencies, ensures thematic coherence, and allows human editors to approve or request revisions before proceeding to the next chapter.","intents":["I want to generate a multi-chapter book with AI agents while maintaining narrative consistency","I need human editors to review and approve chapters before proceeding to the next","I want to manage dependencies between chapters and ensure thematic coherence across the book"],"best_for":["content creation teams producing long-form written content","publishers wanting to accelerate book production with AI assistance","educational organizations creating structured learning materials"],"limitations":["Maintaining narrative consistency across chapters requires careful prompt engineering and context management","Human review checkpoints introduce latency; no built-in deadline management","Generated content requires significant editing; AI-generated text often needs refinement for publication quality"],"requires":["Python 3.9+","crewAI framework 0.130.0+ with Flow support","LLM with strong writing capabilities","human reviewers for approval checkpoints"],"input_types":["book outline","chapter specifications","thematic guidelines"],"output_types":["generated chapters","narrative consistency analysis","review feedback"],"categories":["text-generation-language","automation-workflow"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"crewai-template__cap_11","uri":"capability://data.processing.analysis.lead.scoring.and.qualification.workflow.with.approval.gates","name":"lead scoring and qualification workflow with approval gates","description":"Implements a lead qualification system using CrewAI Flow that analyzes lead data, scores prospects based on predefined criteria, and routes high-value leads through approval gates before action. The Lead Score Flow demonstrates conditional routing where leads above a score threshold proceed to different agents than lower-scoring leads. Human reviewers can approve or reject scoring decisions, and the workflow generates personalized follow-up actions based on lead quality and approval status.","intents":["I want to automatically score and qualify leads while maintaining human oversight of high-value prospects","I need to route leads to different follow-up agents based on qualification score","I want to ensure high-value leads receive appropriate attention with human approval before outreach"],"best_for":["sales teams managing high-volume lead pipelines","B2B companies requiring qualified lead routing","organizations wanting to automate lead qualification while maintaining human judgment"],"limitations":["Lead scoring accuracy depends on training data quality; biased training data produces biased scores","Approval gate latency may delay lead follow-up; no built-in SLA management","Scoring criteria must be regularly updated; static criteria become stale"],"requires":["Python 3.9+","crewAI framework 0.130.0+ with Flow support","lead data with historical qualification outcomes","human reviewers for approval gates"],"input_types":["lead data (company info, contact details, engagement history)","scoring criteria"],"output_types":["lead score","qualification decision","routing decision","follow-up action"],"categories":["data-processing-analysis","automation-workflow"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"crewai-template__cap_12","uri":"capability://text.generation.language.meeting.assistant.workflow.with.agenda.generation.and.action.item.extraction","name":"meeting assistant workflow with agenda generation and action item extraction","description":"Implements a meeting support system using CrewAI Flow that processes meeting transcripts or notes, generates structured agendas, extracts action items, and identifies key decisions. The Meeting Assistant Flow demonstrates how agents can analyze unstructured meeting content, identify participants, extract decisions and commitments, and generate follow-up action items with ownership. The workflow supports both pre-meeting agenda generation and post-meeting analysis.","intents":["I want to automatically generate meeting agendas from discussion notes or transcripts","I need to extract action items and decisions from meetings automatically","I want to identify who is responsible for each action item and track follow-up"],"best_for":["teams managing high-volume meetings with distributed participants","organizations wanting to improve meeting documentation and follow-up","companies needing automated action item tracking"],"limitations":["Transcript quality affects analysis accuracy; poor audio quality or transcription errors propagate","Action item extraction may miss implicit commitments; requires explicit language for reliable extraction","No built-in integration with calendar or task management systems"],"requires":["Python 3.9+","crewAI framework 0.130.0+ with Flow support","meeting transcripts or notes","optional: audio transcription service"],"input_types":["meeting transcript or notes","participant list","meeting context"],"output_types":["structured agenda","action items with owners","key decisions","follow-up summary"],"categories":["text-generation-language","data-processing-analysis"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"crewai-template__cap_13","uri":"capability://text.generation.language.landing.page.generation.workflow.with.template.based.layout.composition","name":"landing page generation workflow with template-based layout composition","description":"Implements an automated landing page creation system using CrewAI where agents collaborate on copywriting, design specification, and layout composition. The Landing Page Generation Flow demonstrates how agents can generate marketing copy, define page structure, select design templates, and compose HTML/CSS based on specifications. The workflow supports A/B testing variants and enables rapid iteration on landing page designs.","intents":["I want to automatically generate landing pages with marketing copy and design specifications","I need to create multiple landing page variants for A/B testing without manual design work","I want to rapidly iterate on landing page designs based on performance feedback"],"best_for":["marketing teams creating high-volume landing pages","SaaS companies running A/B testing campaigns","agencies needing to rapidly prototype landing pages"],"limitations":["Generated copy may require editing for brand voice consistency","Design templates limit customization; complex designs require manual adjustment","No built-in analytics integration; requires external tools for performance tracking"],"requires":["Python 3.9+","crewAI framework 0.130.0+","design templates or CSS framework","marketing copy guidelines"],"input_types":["product/service description","target audience","marketing objectives","design preferences"],"output_types":["marketing copy","page layout specification","HTML/CSS code","design variant"],"categories":["text-generation-language","automation-workflow"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"crewai-template__cap_2","uri":"capability://automation.workflow.sequential.task.execution.with.context.preservation.across.agent.handoffs","name":"sequential task execution with context preservation across agent handoffs","description":"Executes tasks in a defined sequence where each agent receives the output of previous agents as context, enabling knowledge accumulation across the workflow. The framework maintains a shared context object that flows through the agent chain (e.g., Game Builder Crew: game concept → design document → implementation plan). Each task's output becomes input to the next task, with the crew coordinator managing context passing, preventing information loss, and ensuring agents build on prior work rather than starting from scratch.","intents":["I want agents to build on each other's work in sequence, where the writer uses the researcher's findings","I need to ensure context from earlier agents is available to later agents without manual passing","I want to create workflows where output of one agent becomes the input specification for the next"],"best_for":["content creation pipelines (research → writing → editing)","design workflows (concept → detailed design → implementation)","analysis pipelines where each agent refines previous results"],"limitations":["Sequential execution prevents parallelization; workflows with independent tasks cannot run concurrently","Context size grows with each task; large context windows may exceed LLM token limits","No built-in deduplication; agents may re-process information from previous steps"],"requires":["Python 3.9+","crewAI framework 0.130.0+","LLM with sufficient context window for accumulated task outputs"],"input_types":["initial task input","agent outputs from previous tasks"],"output_types":["final task output","complete execution history with context at each step"],"categories":["automation-workflow","planning-reasoning"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"crewai-template__cap_3","uri":"capability://tool.use.integration.external.llm.provider.integration.with.model.abstraction","name":"external llm provider integration with model abstraction","description":"Supports multiple LLM providers (OpenAI, Anthropic, NVIDIA NIM, Azure OpenAI) through a unified agent interface, allowing agents to be configured with different models without code changes. The framework abstracts provider-specific APIs, enabling seamless switching between local models (Ollama), proprietary APIs (OpenAI), and enterprise solutions (Azure). Configuration specifies the LLM provider per agent, enabling heterogeneous crews where different agents use different models based on task requirements and cost optimization.","intents":["I want to use different LLM providers for different agents (e.g., GPT-4 for complex reasoning, cheaper model for simple tasks)","I need to integrate with enterprise LLM solutions like Azure OpenAI without rewriting agent code","I want to experiment with local models (Ollama) for privacy-sensitive tasks while using cloud APIs for others"],"best_for":["teams with multi-provider LLM strategies for cost optimization","enterprises requiring Azure or private LLM deployments","projects experimenting with local vs cloud models"],"limitations":["Provider-specific features (function calling, vision, streaming) may not be uniformly supported across all providers","Model switching requires re-testing agent behavior; different models produce different outputs for same prompts","No built-in cost tracking or provider failover; requires external monitoring"],"requires":["Python 3.9+","crewAI framework 0.130.0+","API keys for selected providers (OpenAI, Anthropic, Azure, NVIDIA NIM, or Ollama endpoint)","network access to provider endpoints"],"input_types":["provider configuration (API keys, endpoints)","model identifiers (gpt-4, claude-3, etc.)"],"output_types":["agent responses from selected LLM provider","provider-specific metadata (token usage, model version)"],"categories":["tool-use-integration","automation-workflow"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"crewai-template__cap_4","uri":"capability://tool.use.integration.tool.based.agent.capability.extension.with.function.calling","name":"tool-based agent capability extension with function calling","description":"Extends agent capabilities by binding external tools (APIs, functions, web search) to agents through a tool registry. Agents can invoke tools during task execution to fetch real-time data, perform calculations, or interact with external systems. The framework handles tool invocation, parameter binding, and result integration back into agent reasoning. Examples demonstrate tools for web search (trip planning), financial data retrieval (stock analysis), and API calls (weather, LinkedIn integration for recruitment).","intents":["I want agents to search the web or access real-time data during task execution","I need agents to call external APIs (weather, financial data, LinkedIn) to enrich their analysis","I want to extend agent capabilities without modifying the core agent logic"],"best_for":["workflows requiring real-time data (financial analysis, trip planning, recruitment)","agents that need to interact with external systems or APIs","teams building extensible agent systems with pluggable tools"],"limitations":["Tool invocation adds latency; each tool call requires network round-trip","Tool availability depends on external service uptime; no built-in fallback mechanisms","Tool parameter binding requires careful schema definition; mismatches cause agent errors"],"requires":["Python 3.9+","crewAI framework 0.130.0+","tool definitions with clear input/output schemas","API access for external tools (web search, financial data, etc.)"],"input_types":["tool definitions with schemas","agent task descriptions","external API credentials"],"output_types":["tool invocation results","agent responses enriched with tool data"],"categories":["tool-use-integration","automation-workflow"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"crewai-template__cap_5","uri":"capability://automation.workflow.specialized.crew.templates.for.domain.specific.workflows","name":"specialized crew templates for domain-specific workflows","description":"Provides pre-built crew templates optimized for specific domains: Game Builder (sequential game development), Stock Analysis (financial research with SEC filings), Marketing Strategy (content generation with NVIDIA AI), Job Posting (automated job description creation), Recruitment (LinkedIn integration and candidate scoring), Trip Planning (travel itinerary with weather/search APIs), and Book Writing (multi-chapter composition with reviews). Each template includes pre-configured agents, tasks, tools, and YAML configurations that can be adapted for similar use cases without building crews from scratch.","intents":["I want to quickly build a multi-agent system for a common use case (job posting, trip planning, stock analysis) without designing agents from scratch","I need reference implementations showing best practices for domain-specific agent orchestration","I want to understand how to structure agents and tasks for my specific domain by studying similar templates"],"best_for":["developers building systems for covered domains (recruitment, content creation, financial analysis, travel)","teams learning CrewAI patterns through concrete examples","rapid prototyping of domain-specific multi-agent systems"],"limitations":["Templates are domain-specific; limited applicability outside covered use cases","Templates may require customization for specific business logic; not plug-and-play for all scenarios","Some templates (Instagram Post, Trip Planner) are marked as legacy and may require updates to current framework versions"],"requires":["Python 3.9+","crewAI framework 0.130.0+","domain-specific API access (LinkedIn for recruitment, weather APIs for trip planning, SEC EDGAR for stock analysis)","LLM API keys"],"input_types":["domain-specific input data (job requirements, travel dates, stock symbols, book outline)","customization parameters"],"output_types":["domain-specific outputs (job postings, travel itineraries, stock reports, book chapters)"],"categories":["automation-workflow","planning-reasoning"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"crewai-template__cap_6","uri":"capability://automation.workflow.configuration.driven.agent.and.task.definition.with.yaml","name":"configuration-driven agent and task definition with yaml","description":"Enables declarative definition of agents and tasks through YAML configuration files (e.g., gamedesign.yaml) rather than Python code. YAML files specify agent roles, goals, backstories, tools, and task descriptions with dependencies. The framework parses YAML and instantiates agents and tasks at runtime, enabling non-developers to modify agent behavior, add tasks, or adjust tool bindings without touching Python. Configuration changes are immediately reflected in crew execution without recompilation.","intents":["I want non-technical stakeholders to modify agent roles and task flows without code changes","I need to version control agent configurations separately from implementation code","I want to quickly experiment with different agent configurations without redeploying code"],"best_for":["teams with non-technical stakeholders who need to adjust agent behavior","projects requiring frequent configuration changes without code deployment","organizations wanting to separate configuration from implementation"],"limitations":["YAML configuration is limited to predefined schema; complex conditional logic requires Python","No validation of YAML configuration at definition time; errors surface at runtime","Large YAML files become difficult to manage; no built-in organization for crews with 20+ agents"],"requires":["Python 3.9+","crewAI framework 0.130.0+","YAML file format understanding","knowledge of agent and task schema"],"input_types":["YAML configuration files with agent and task definitions"],"output_types":["instantiated agents and tasks","crew execution with configured behavior"],"categories":["automation-workflow","planning-reasoning"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"crewai-template__cap_7","uri":"capability://automation.workflow.asynchronous.task.execution.with.parallel.processing","name":"asynchronous task execution with parallel processing","description":"Supports asynchronous task execution within flows, enabling parallel processing of independent tasks and non-blocking workflow progression. The Flow framework manages async task scheduling, concurrent execution, and result aggregation. Tasks can run in parallel when they have no dependencies, reducing total workflow execution time. Examples demonstrate async patterns in Lead Score Flow and Email Auto-Responder Flow where multiple agents process data concurrently.","intents":["I want to process multiple leads or emails in parallel rather than sequentially","I need to reduce workflow execution time by running independent agent tasks concurrently","I want to handle long-running operations (API calls, analysis) without blocking the main workflow"],"best_for":["workflows with independent parallel tasks (batch processing, multi-lead scoring)","systems requiring low-latency response times","applications processing high-volume data with multiple agents"],"limitations":["Parallel execution increases resource consumption; no built-in resource pooling or rate limiting","Debugging concurrent workflows is more complex than sequential execution","Task dependencies must be explicitly defined; incorrect dependency specification causes race conditions"],"requires":["Python 3.9+ with async/await support","crewAI framework 0.130.0+ with Flow support","understanding of async programming patterns"],"input_types":["independent task definitions","task dependency specifications"],"output_types":["aggregated results from parallel tasks","execution timeline with concurrency metrics"],"categories":["automation-workflow","planning-reasoning"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"crewai-template__cap_8","uri":"capability://tool.use.integration.integration.with.external.orchestration.frameworks.langgraph","name":"integration with external orchestration frameworks (langgraph)","description":"Provides integration patterns with LangGraph for advanced workflow orchestration, enabling CrewAI crews to be embedded within LangGraph state machines. The CrewAI-LangGraph example demonstrates how to compose crews as nodes in a LangGraph workflow, combining CrewAI's agent orchestration with LangGraph's graph-based state management and visualization. This enables hybrid workflows where CrewAI handles agent coordination and LangGraph manages overall workflow topology.","intents":["I want to use CrewAI agents within a LangGraph workflow for more advanced state management","I need to visualize and debug complex workflows combining multiple orchestration frameworks","I want to leverage LangGraph's graph-based execution model with CrewAI's agent specialization"],"best_for":["teams already using LangGraph who want to add specialized agent orchestration","complex workflows requiring both graph-based and agent-based orchestration","projects needing advanced visualization and debugging of multi-agent systems"],"limitations":["Integration adds complexity; requires understanding both CrewAI and LangGraph patterns","Context passing between frameworks requires careful state management","Limited documentation on integration patterns; requires reverse-engineering from examples"],"requires":["Python 3.9+","crewAI framework 0.130.0+","LangGraph framework","understanding of both CrewAI and LangGraph APIs"],"input_types":["CrewAI crew definitions","LangGraph state machine definitions"],"output_types":["hybrid workflow execution results","combined state from both frameworks"],"categories":["tool-use-integration","automation-workflow"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"crewai-template__cap_9","uri":"capability://text.generation.language.email.auto.responder.workflow.with.template.based.response.generation","name":"email auto-responder workflow with template-based response generation","description":"Implements an automated email response system using CrewAI Flow that analyzes incoming emails, classifies them, and generates contextually appropriate responses using templates. The Email Auto-Responder Flow demonstrates how agents can process unstructured email content, extract key information, route to appropriate response agents, and generate personalized replies. The workflow includes conditional routing based on email classification and template selection based on email type.","intents":["I want to automatically respond to incoming emails with appropriate, personalized responses","I need to classify emails and route them to different response templates based on content","I want to reduce manual email handling while maintaining response quality"],"best_for":["customer support teams handling high email volume","businesses needing automated first-response systems","organizations wanting to reduce response time for common email types"],"limitations":["Template-based responses may feel generic; requires careful template design for personalization","Email classification errors lead to inappropriate responses; requires robust classification logic","No built-in email integration; requires external email system connection"],"requires":["Python 3.9+","crewAI framework 0.130.0+ with Flow support","email system integration (SMTP, API)","response templates for different email types"],"input_types":["incoming email content","email metadata (sender, subject, timestamp)"],"output_types":["classified email type","generated response text","routing decision"],"categories":["text-generation-language","automation-workflow"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"crewai-template__headline","uri":"capability://automation.workflow.multi.agent.orchestration.template.for.ai.applications","name":"multi-agent orchestration template for ai applications","description":"CrewAI Template provides a collection of example templates for multi-agent collaboration, enabling developers to build AI systems for diverse applications like content creation, trip planning, and code review with role-based orchestration.","intents":["best multi-agent orchestration template","multi-agent framework for AI applications","templates for AI content creation","AI trip planning templates","code review automation templates"],"best_for":["developers building AI systems","research teams","content creators"],"limitations":[],"requires":[],"input_types":[],"output_types":[],"categories":["automation-workflow"],"confidence":0.5,"matches":0,"success_rate":0}],"trust":{"score":55,"verified":false,"data_access_risk":"high","permissions":["Python 3.9+","crewAI framework 0.130.0 or later","YAML configuration files for agent and task definitions","LLM API access (OpenAI, Anthropic, or compatible provider)","crewAI framework 0.130.0+ with Flow support","async/await runtime support","optional: external state store (Redis, database) for persistence","LLM with strong writing capabilities","human reviewers for approval checkpoints","lead data with historical qualification outcomes"],"failure_modes":["YAML configuration approach scales linearly with crew complexity; large crews (20+ agents) require careful task dependency management","No built-in conflict resolution when multiple agents produce contradictory outputs","Agent communication is task-based only; no direct inter-agent messaging or negotiation patterns","Human-in-the-loop checkpoints introduce latency; no built-in timeout handling for approval delays","State management requires external persistence for production use; in-memory state is lost on process restart","Conditional routing logic must be defined in Python; no visual workflow builder for non-technical users","Maintaining narrative consistency across chapters requires careful prompt engineering and context management","Human review checkpoints introduce latency; no built-in deadline management","Generated content requires significant editing; AI-generated text often needs refinement for publication quality","Lead scoring accuracy depends on training data quality; biased training data produces biased scores","builder identity is not verified yet","no observed match outcomes yet"],"rank_breakdown":{"adoption":0.7,"quality":0.9,"ecosystem":0.39999999999999997,"match_graph":0.25,"freshness":0.52,"weights":{"adoption":0.25,"quality":0.25,"ecosystem":0.1,"match_graph":0.35,"freshness":0.05}},"observed_outcomes":{"matches":0,"success_rate":0,"avg_confidence":0,"top_intents":[],"last_matched_at":null},"maintenance":{"status":"active","updated_at":"2026-06-17T09:51:04.690Z","last_scraped_at":null,"last_commit":null},"community":{"stars":null,"forks":null,"weekly_downloads":null,"model_downloads":null,"model_likes":null}},"distribution":{"claim_url":"https://unfragile.ai/submit?claim=crewai-template","compare_url":"https://unfragile.ai/compare?artifact=crewai-template"}},"signature":"VuqHVFx5ftpGMBvJFpVVs1tPHsd2HLastLmj0K291NpgBXDnLYp0RfG7dIGnPuUbSGkuPAIOTmsoBOo+CkEOAg==","signedAt":"2026-06-21T00:18:29.706Z","signedBy":"unfragile.ai","version":1},"_links":{"self":"https://unfragile.ai/api/v1/passport/crewai-template","artifact":"https://unfragile.ai/crewai-template","verify":"https://unfragile.ai/api/v1/verify?slug=crewai-template","publicKey":"https://unfragile.ai/api/v1/trust-passport-public-key","spec":"https://unfragile.ai/trust","schema":"https://unfragile.ai/schema.json","docs":"https://unfragile.ai/docs"}}