{"passport":{"unfragile":{"@version":"1.0","version":"2026-05","artifact":{"id":"tool_agentset-ai","slug":"agentset-ai","name":"Agentset.ai","type":"repo","url":"https://agentset.ai/","page_url":"https://unfragile.ai/agentset-ai","categories":["rag-knowledge"],"tags":[],"pricing":{"model":"unknown","free":false,"starting_price":null},"status":"active","verified":false},"capabilities":[{"id":"tool_agentset-ai__cap_0","uri":"capability://data.processing.analysis.multi.format.document.ingestion.with.automatic.parsing.and.metadata.attachment","name":"multi-format document ingestion with automatic parsing and metadata attachment","description":"Accepts 22+ file formats (PDF, DOCX, XLSX, PNG, EML, etc.) and URLs via SDK, automatically parses content into structured text, applies configurable chunking strategies, and attaches custom metadata per document. The ingestion pipeline processes files asynchronously with job status tracking, enabling bulk document onboarding without blocking application flow. Supports multimodal content including images, graphs, and tables with native extraction capabilities.","intents":["I need to ingest a mix of PDFs, Word docs, and spreadsheets into a RAG system without writing custom parsers","I want to attach custom metadata (department, date, source) to documents during ingestion for later filtering","I need to process documents asynchronously and track ingestion progress without polling manually","I want to extract and index content from images and tables, not just text"],"best_for":["Enterprise teams managing heterogeneous document repositories (legal, medical, financial sectors)","Developers building RAG applications who lack document parsing expertise","Organizations with strict data governance requiring metadata-driven retrieval"],"limitations":["Chunking strategy is configurable but implementation details are not documented, limiting fine-tuning control","Free tier capped at 1,000 pages (1,000 characters = 1 page), requiring upgrade for larger datasets","Custom file format support only available on Enterprise tier, excluding niche formats","Tabular data processing is mentioned but specifics on table extraction and preservation are undocumented"],"requires":["Agentset API key (obtained via signup)","Namespace identifier (created via dashboard)","TypeScript/JavaScript or Python SDK","For URLs: publicly accessible file endpoints or connector credentials (Google Drive, SharePoint, Notion)"],"input_types":["file (PDF, DOCX, PPTX, XLSX, CSV, PNG, JPEG, HTML, MD, TXT, EML, MSG, and 10+ others)","URL (with automatic crawling and parsing)","raw text with metadata"],"output_types":["parsed text chunks with embeddings","indexed documents with metadata","ingestion job status and tracking"],"categories":["data-processing-analysis","document-parsing"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"tool_agentset-ai__cap_1","uri":"capability://search.retrieval.semantic.search.with.metadata.filtering.and.reranking","name":"semantic search with metadata filtering and reranking","description":"Converts user queries into vector embeddings and performs similarity search across indexed documents, optionally filtering results by metadata predicates before retrieval. A reranking layer (algorithm unspecified) refines result precision after initial semantic matching. Supports hybrid search combining semantic and traditional retrieval mechanisms, though the hybrid implementation details are undocumented. Returns ranked results with relevance scores and source attribution.","intents":["I want to search my document corpus by meaning, not keywords, to find relevant content even with different phrasing","I need to filter search results by document metadata (e.g., department='legal', date>'2024-01-01') before ranking","I want to improve search precision by reranking initial results to surface the most relevant documents first","I need to combine semantic and keyword search for better coverage on mixed query types"],"best_for":["Teams building semantic search features for internal knowledge bases or customer-facing search","Organizations with large document repositories requiring precision filtering by metadata","Applications where search latency is critical (local deployment reduces round-trip time)"],"limitations":["Reranking algorithm is not documented, preventing optimization or debugging of ranking behavior","Hybrid search mechanism (semantic + traditional) is mentioned but implementation details are unknown","Pro tier limits retrievals to unlimited but Free tier caps at 10,000 retrievals/month","Embedding model selection options are not enumerated, limiting control over semantic space quality"],"requires":["Agentset API key","Namespace with pre-ingested documents","Query string (text)","Optional: metadata filter predicates"],"input_types":["query text","metadata filter expressions (format unspecified)","optional: search configuration (reranking enabled/disabled)"],"output_types":["ranked document chunks with relevance scores","source attribution (document name, URL, page reference)","metadata for each result"],"categories":["search-retrieval","memory-knowledge"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"tool_agentset-ai__cap_10","uri":"capability://automation.workflow.observability.and.logging.for.debugging.and.monitoring","name":"observability and logging for debugging and monitoring","description":"Provides logging and observability features for tracking ingestion progress, search performance, RAG generation quality, and system errors. Logs include request/response traces, latency metrics, token usage, and error details. Observability data is accessible via API and optional dashboard for monitoring system health, identifying bottlenecks, and debugging issues. Supports integration with external monitoring platforms (DataDog, New Relic, etc.).","intents":["I want to monitor ingestion progress and identify documents that failed to parse","I need to track search latency and identify performance bottlenecks","I want to monitor RAG generation quality and identify hallucinations or low-quality responses","I need to debug system errors and understand failure modes"],"best_for":["Teams operating Agentset in production and requiring visibility into system health","Organizations implementing SLOs and monitoring RAG quality metrics","DevOps teams integrating Agentset with existing monitoring infrastructure","Teams debugging ingestion failures or search quality issues"],"limitations":["Observability features are mentioned but specifics are undocumented (metrics, dashboards, retention)","Integration with external monitoring platforms is not detailed","No clear documentation on what logs are retained and for how long","Custom metrics or alerting rules are not mentioned; unclear if available"],"requires":["Agentset API key","Optional: external monitoring platform credentials (DataDog, New Relic, etc.)","Optional: custom alerting or notification rules"],"input_types":["optional: monitoring configuration (metrics, thresholds, alert rules)"],"output_types":["logs (ingestion, search, RAG generation, errors)","metrics (latency, token usage, error rates)","optional: dashboard visualizations","optional: alerts and notifications"],"categories":["automation-workflow","safety-moderation"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"tool_agentset-ai__cap_11","uri":"capability://automation.workflow.tiered.pricing.with.usage.based.scaling.free.pro.enterprise","name":"tiered pricing with usage-based scaling (free, pro, enterprise)","description":"Offers three pricing tiers with different feature sets and usage limits: Free tier (1,000 pages, 10,000 retrievals/month, no connectors), Pro tier ($49/month, 10,000 pages included, unlimited retrievals, per-connector charges), and Enterprise tier (custom pricing, BYOC/self-hosted, unlimited pages, custom features). Usage is measured in 'pages' (1,000 characters = 1 page) rather than documents, enabling predictable cost scaling. Connector costs ($100/month each on Pro) are separate from base subscription.","intents":["I want to evaluate Agentset with a small dataset before committing to paid tier","I need predictable pricing based on document size rather than opaque per-document fees","I want to scale from startup (Free) to enterprise (custom) without migrating to a different platform","I need to understand total cost of ownership including connector and infrastructure costs"],"best_for":["Startups and small teams evaluating RAG solutions with limited budgets","Mid-market organizations with moderate document volumes (10K-100K pages)","Enterprise teams requiring custom deployments and volume discounts","Organizations with multiple data sources (Google Drive, SharePoint, Notion) requiring multiple connectors"],"limitations":["Free tier is heavily limited (1,000 pages, 10,000 retrievals/month), unsuitable for production use","Pro tier connector costs ($100/month each) add up quickly for multi-source setups (3 connectors = $300/month)","Page-based pricing (1,000 characters = 1 page) is non-standard and may be difficult to estimate upfront","Enterprise pricing is opaque; no public pricing available, requiring sales engagement"],"requires":["Agentset account (free signup)","Credit card for Pro tier (if upgrading from Free)","Optional: sales engagement for Enterprise tier"],"input_types":["tier selection (Free, Pro, Enterprise)","optional: connector selection (Pro tier)"],"output_types":["subscription confirmation","usage dashboard with page count and retrieval tracking","billing invoice"],"categories":["automation-workflow"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"tool_agentset-ai__cap_2","uri":"capability://text.generation.language.simple.rag.retrieval.augmented.generation.with.automatic.citation","name":"simple rag (retrieval-augmented generation) with automatic citation","description":"Chains semantic search results directly into an LLM prompt, grounding generated responses in retrieved documents. Automatically tracks and attributes citations to source documents, enabling end-users to inspect the evidence backing each answer. Supports pluggable LLM providers (OpenAI, Anthropic, Google, xAI, Azure, Cohere, Qwen, Mistral, DeepSeek) via configuration, abstracting provider-specific APIs. Reduces hallucinations by constraining generation to indexed knowledge.","intents":["I want to build a chatbot that answers questions using my proprietary documents without hallucinating","I need to show users which documents support each answer for transparency and trust","I want to switch between LLM providers (OpenAI to Anthropic) without rewriting application code","I need to ground AI responses in my company's knowledge base to reduce liability from incorrect information"],"best_for":["Customer support teams building internal knowledge base chatbots","Legal and compliance teams requiring auditable, cited answers","Organizations evaluating multiple LLM providers and needing provider-agnostic abstractions","Teams building chatbots for sensitive domains (healthcare, finance) where hallucinations carry high cost"],"limitations":["Simple RAG does not perform multi-hop reasoning; complex queries requiring multiple retrieval steps are not supported","LLM provider selection is broad but integration mechanism is undocumented, preventing custom provider addition","Citation format and customization options are not detailed, limiting control over how sources are presented","No built-in handling of conflicting information across retrieved documents"],"requires":["Agentset API key","Namespace with indexed documents","LLM API key (OpenAI, Anthropic, Google, etc.) or Azure endpoint","Query text","Optional: LLM configuration (temperature, max_tokens, model selection)"],"input_types":["user query (text)","LLM provider and model selection","optional: system prompt or instructions"],"output_types":["generated response text","citations with source document references","metadata for cited documents"],"categories":["text-generation-language","memory-knowledge"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"tool_agentset-ai__cap_3","uri":"capability://planning.reasoning.agentic.rag.with.multi.hop.reasoning.and.planning","name":"agentic rag with multi-hop reasoning and planning","description":"Extends simple RAG with AI-driven planning and multi-hop retrieval, enabling the system to decompose complex queries into sub-questions, retrieve relevant documents iteratively, and reason across multiple sources. Integrates with Vercel's AI SDK for agent orchestration, allowing the LLM to decide when to search, what to search for, and how to synthesize results. Supports custom tool definitions and agentic reasoning loops without manual prompt engineering.","intents":["I need to answer complex questions that require retrieving and reasoning across multiple documents","I want the system to autonomously decide which documents to retrieve based on the query, not just return top-k results","I need to support follow-up questions and context retention across multiple turns","I want to build agents that can decompose ambiguous queries into clarifying sub-questions"],"best_for":["Teams building advanced chatbots for complex domains (legal research, financial analysis, technical support)","Organizations with large, interconnected document repositories requiring multi-step reasoning","Developers comfortable with AI SDK and agentic patterns","Applications where query complexity justifies the latency overhead of multi-hop retrieval"],"limitations":["Requires Vercel AI SDK integration; no standalone agentic capability without external dependency","Multi-hop reasoning adds latency per retrieval step (estimated ~200ms per step based on typical agent overhead), unsuitable for real-time applications","Planning and reasoning behavior is not fully customizable; limited control over agent decision-making heuristics","No built-in fallback or error recovery for failed retrieval steps in multi-hop chains"],"requires":["Agentset API key","Namespace with indexed documents","Vercel AI SDK (TypeScript/JavaScript)","LLM API key (OpenAI, Anthropic, etc.)","Optional: custom tool definitions for agent actions"],"input_types":["user query (text)","optional: conversation history for context retention","optional: custom tool definitions"],"output_types":["generated response with multi-hop reasoning trace","citations for each reasoning step","agent decision log (which searches were performed, in what order)"],"categories":["planning-reasoning","memory-knowledge"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"tool_agentset-ai__cap_4","uri":"capability://automation.workflow.connector.based.document.synchronization.from.external.sources","name":"connector-based document synchronization from external sources","description":"Automatically syncs documents from external data sources (Google Drive, SharePoint, Notion) into Agentset namespaces via pre-built connectors. Handles authentication, incremental updates, and metadata extraction from source systems. Connectors are charged per-connector on Pro tier ($100/month each), enabling organizations to maintain live links between source systems and RAG indexes without manual re-ingestion. Webhook events notify downstream systems of sync completion.","intents":["I want to automatically sync documents from Google Drive or SharePoint into my RAG system without manual uploads","I need to keep my RAG index in sync with live document repositories as content changes","I want to extract metadata from source systems (owner, last-modified, folder structure) during sync","I need to trigger downstream workflows (notifications, analytics) when new documents are synced"],"best_for":["Enterprise teams with existing Google Drive, SharePoint, or Notion repositories","Organizations requiring live document synchronization without manual ETL","Teams with document governance policies requiring source-system metadata preservation","Applications where document freshness is critical (legal, compliance, knowledge management)"],"limitations":["Connector support is limited to Google Drive, SharePoint, and Notion; custom data sources require enterprise tier","Pro tier charges $100/month per connector, making multi-source setups expensive","Incremental sync behavior is not detailed; unclear if deletions in source systems are reflected in RAG index","Webhook event types and payload structure are not documented, limiting integration planning"],"requires":["Agentset API key","Namespace identifier","Credentials for source system (Google Drive, SharePoint, or Notion)","Pro tier or higher (Free tier does not support connectors)","Optional: webhook endpoint for sync notifications"],"input_types":["source system credentials (OAuth token or API key)","optional: folder/workspace filters to limit sync scope","optional: metadata mapping rules"],"output_types":["synced documents in namespace","metadata extracted from source system","webhook events on sync completion","sync status and error logs"],"categories":["automation-workflow","data-processing-analysis"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"tool_agentset-ai__cap_5","uri":"capability://tool.use.integration.customizable.chat.interface.with.feedback.collection","name":"customizable chat interface with feedback collection","description":"Generates shareable preview links to chat interfaces for RAG responses, enabling end-users to interact with grounded answers without accessing the backend system. Interfaces are customizable (branding, instructions, model selection) and collect user feedback (thumbs up/down, comments) for quality monitoring and model improvement. Feedback data is stored and accessible via API for analytics and fine-tuning workflows.","intents":["I want to share RAG responses with non-technical stakeholders without exposing the backend API","I need to collect user feedback on answer quality to identify gaps in my knowledge base","I want to customize the chat interface to match my brand and add company-specific instructions","I need to track which answers users find helpful to prioritize document ingestion or retraining"],"best_for":["Teams deploying RAG systems to non-technical end-users (customers, employees, partners)","Organizations building feedback loops for continuous RAG improvement","Customer support teams using RAG to augment human agents","Product teams evaluating RAG quality before full deployment"],"limitations":["Customization options are not detailed; unclear what branding and configuration options are available","Feedback collection mechanism is mentioned but data schema and analytics capabilities are undocumented","No built-in A/B testing framework for comparing different RAG configurations","Preview link security model is not documented (expiration, access control, rate limiting)"],"requires":["Agentset API key","Namespace with RAG configured","Optional: custom branding assets (logo, colors)","Optional: webhook endpoint for feedback events"],"input_types":["RAG configuration (model, retrieval settings)","optional: custom instructions or system prompt","optional: branding configuration"],"output_types":["shareable preview link (URL)","chat interface (HTML/web)","feedback data (ratings, comments, metadata)","analytics dashboard (usage, feedback trends)"],"categories":["tool-use-integration","automation-workflow"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"tool_agentset-ai__cap_6","uri":"capability://tool.use.integration.model.context.protocol.mcp.server.integration","name":"model context protocol (mcp) server integration","description":"Exposes Agentset RAG capabilities as an MCP server, enabling external applications (Claude, other AI agents, custom tools) to invoke semantic search and RAG operations without direct API calls. MCP standardizes the interface for tool use, allowing Agentset to be plugged into any MCP-compatible client. Supports function-calling semantics with schema-based tool definitions for search, retrieval, and chat operations.","intents":["I want to use Agentset RAG within Claude or other MCP-compatible AI applications","I need to integrate Agentset into a custom agent framework that supports MCP","I want to expose my RAG system as a reusable tool for multiple downstream applications","I need standardized tool calling semantics across different AI platforms"],"best_for":["Teams building multi-agent systems with MCP-compatible clients (Claude, custom agents)","Organizations standardizing on MCP for tool integration across AI applications","Developers integrating Agentset into existing MCP-based workflows","Applications requiring tool-use semantics without custom API wrappers"],"limitations":["MCP server implementation details are not documented; unclear what tools/operations are exposed","Requires MCP-compatible client; not all AI platforms support MCP yet","No documentation on authentication, rate limiting, or security model for MCP connections","Tool schema and parameter definitions are not provided, limiting integration planning"],"requires":["Agentset API key","MCP-compatible client (Claude, custom agent framework)","MCP server endpoint (Agentset-hosted or self-hosted)","Optional: custom tool definitions or schema modifications"],"input_types":["MCP tool calls with schema-defined parameters","query text, metadata filters, configuration options"],"output_types":["MCP tool results (search results, RAG responses)","structured data conforming to MCP response schema"],"categories":["tool-use-integration","memory-knowledge"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"tool_agentset-ai__cap_7","uri":"capability://automation.workflow.bring.your.own.cloud.byoc.and.self.hosted.deployment","name":"bring-your-own-cloud (byoc) and self-hosted deployment","description":"Enables enterprise customers to deploy Agentset infrastructure on their own cloud accounts (AWS, GCP, Azure) or on-premises, maintaining full control over data residency, infrastructure, and compliance. BYOC deployments use customer-managed vector databases (Pinecone, Qdrant) and compute resources, eliminating data transfer to Agentset infrastructure. Self-hosted option provides complete source code and deployment automation for air-gapped or highly regulated environments.","intents":["I need to keep all data within my organization's cloud account for compliance or security reasons","I want to deploy RAG infrastructure in a specific region or air-gapped environment","I need to use my existing vector database (Qdrant, Pinecone) without migrating to Agentset-managed storage","I require full control over infrastructure, scaling, and operational decisions"],"best_for":["Enterprise organizations with strict data residency or compliance requirements (HIPAA, GDPR, FedRAMP)","Teams operating in air-gapped or restricted network environments","Organizations with existing vector database investments (Qdrant, Pinecone)","Large-scale deployments requiring custom infrastructure tuning or multi-region replication"],"limitations":["BYOC and self-hosted options are Enterprise tier only, requiring custom pricing negotiation","Infrastructure management overhead is significant; requires DevOps expertise for deployment and maintenance","Deployment automation and documentation are not detailed; unclear what infrastructure-as-code tools are provided","Vector database integration is limited to Pinecone and Qdrant; other vector stores require custom integration"],"requires":["Enterprise tier subscription","Cloud account (AWS, GCP, Azure) or on-premises infrastructure","Kubernetes cluster or container orchestration platform (for BYOC)","Vector database (Pinecone or Qdrant) or self-hosted alternative","DevOps expertise for deployment and operations","Optional: custom networking, security, and compliance configurations"],"input_types":["cloud provider credentials or on-premises infrastructure details","vector database configuration","optional: custom infrastructure-as-code templates"],"output_types":["deployed Agentset infrastructure","API endpoints for application integration","operational dashboards and monitoring"],"categories":["automation-workflow","tool-use-integration"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"tool_agentset-ai__cap_8","uri":"capability://text.generation.language.multi.provider.llm.abstraction.with.provider.agnostic.configuration","name":"multi-provider llm abstraction with provider-agnostic configuration","description":"Abstracts LLM provider differences (OpenAI, Anthropic, Google, xAI, Azure, Cohere, Qwen, Mistral, DeepSeek) behind a unified configuration interface, enabling model selection and switching without code changes. Handles provider-specific authentication, API formats, and response parsing transparently. Supports model-specific features (function calling, vision, streaming) while maintaining consistent application-level semantics.","intents":["I want to evaluate multiple LLM providers (OpenAI, Anthropic, Google) without rewriting application code","I need to switch LLM providers for cost optimization or performance reasons without downtime","I want to use different models for different use cases (fast inference vs. high-quality reasoning)","I need to support multiple LLM providers for redundancy or geographic distribution"],"best_for":["Teams evaluating or migrating between LLM providers","Cost-conscious organizations optimizing model selection per use case","Applications requiring high availability with provider fallbacks","Organizations with multi-region deployments needing geographically optimized model selection"],"limitations":["Provider-specific features (vision, function calling) may not be uniformly supported across all models","Configuration format and model selection semantics are not documented","No built-in fallback or retry logic if primary provider is unavailable","Pricing and rate limiting are provider-specific; no unified cost tracking or quota management"],"requires":["API keys for selected LLM providers (OpenAI, Anthropic, Google, etc.)","Model name or identifier for each provider","Optional: provider-specific configuration (temperature, max_tokens, etc.)"],"input_types":["provider selection (enum or string)","model name","optional: provider-specific parameters"],"output_types":["generated text from selected provider","provider metadata (model version, token usage)","optional: streaming responses"],"categories":["text-generation-language","tool-use-integration"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"tool_agentset-ai__cap_9","uri":"capability://automation.workflow.webhook.driven.event.system.for.async.notifications","name":"webhook-driven event system for async notifications","description":"Emits webhook events for key system events (document ingestion completion, sync status, feedback collection) to customer-specified endpoints, enabling event-driven downstream workflows without polling. Webhook payloads include event metadata (timestamp, namespace, status, error details) for routing and error handling. Supports retry logic and delivery guarantees for reliable event propagation.","intents":["I want to trigger downstream workflows (notifications, analytics, retraining) when documents are ingested","I need to monitor ingestion status without polling the API","I want to automatically sync feedback data to external analytics or quality monitoring systems","I need to implement error handling and retry logic for failed webhook deliveries"],"best_for":["Teams building event-driven architectures with Agentset","Organizations integrating Agentset with workflow automation platforms (Zapier, Make, custom orchestration)","Applications requiring real-time notifications of system events","Teams implementing feedback loops and continuous improvement workflows"],"limitations":["Webhook event types are not enumerated; unclear what events are available beyond ingestion and sync","Payload schema and event metadata structure are not documented","Retry policy and delivery guarantees are not specified (at-least-once, exactly-once, best-effort)","No built-in webhook management UI; unclear how to register, test, or debug webhooks"],"requires":["Agentset API key","Webhook endpoint URL (HTTPS, publicly accessible)","Optional: webhook secret for signature verification","Optional: event filtering or routing rules"],"input_types":["webhook endpoint URL","optional: event type filters","optional: custom headers or authentication"],"output_types":["webhook POST requests with event payload","HTTP status codes (200 = success, retry on 5xx)","optional: webhook delivery logs and retry history"],"categories":["automation-workflow","tool-use-integration"],"confidence":0.5,"matches":0,"success_rate":0}],"trust":{"score":40,"verified":false,"data_access_risk":"high","permissions":["Agentset API key (obtained via signup)","Namespace identifier (created via dashboard)","TypeScript/JavaScript or Python SDK","For URLs: publicly accessible file endpoints or connector credentials (Google Drive, SharePoint, Notion)","Agentset API key","Namespace with pre-ingested documents","Query string (text)","Optional: metadata filter predicates","Optional: external monitoring platform credentials (DataDog, New Relic, etc.)","Optional: custom alerting or notification rules"],"failure_modes":["Chunking strategy is configurable but implementation details are not documented, limiting fine-tuning control","Free tier capped at 1,000 pages (1,000 characters = 1 page), requiring upgrade for larger datasets","Custom file format support only available on Enterprise tier, excluding niche formats","Tabular data processing is mentioned but specifics on table extraction and preservation are undocumented","Reranking algorithm is not documented, preventing optimization or debugging of ranking behavior","Hybrid search mechanism (semantic + traditional) is mentioned but implementation details are unknown","Pro tier limits retrievals to unlimited but Free tier caps at 10,000 retrievals/month","Embedding model selection options are not enumerated, limiting control over semantic space quality","Observability features are mentioned but specifics are undocumented (metrics, dashboards, retention)","Integration with external monitoring platforms is not detailed","builder identity is not verified yet","no observed match outcomes yet"],"rank_breakdown":{"adoption":0.36666666666666664,"quality":0.78,"ecosystem":0.15000000000000002,"match_graph":0.25,"freshness":0.75,"weights":{"adoption":0.3,"quality":0.2,"ecosystem":0.15,"match_graph":0.3,"freshness":0.05}},"observed_outcomes":{"matches":0,"success_rate":0,"avg_confidence":0,"top_intents":[],"last_matched_at":null},"maintenance":{"status":"active","updated_at":"2026-05-24T12:16:28.696Z","last_scraped_at":"2026-04-05T13:23:42.552Z","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=agentset-ai","compare_url":"https://unfragile.ai/compare?artifact=agentset-ai"}},"signature":"GnwLTm6/TuLCdDYwvvOfQXOESovK54cI24XhRtcSgr64x9ZQaj0Q50PTtfYJDVmTVM5k6zO+zAfMFGebhNyeAA==","signedAt":"2026-06-22T03:56:45.927Z","signedBy":"unfragile.ai","version":1},"_links":{"self":"https://unfragile.ai/api/v1/passport/agentset-ai","artifact":"https://unfragile.ai/agentset-ai","verify":"https://unfragile.ai/api/v1/verify?slug=agentset-ai","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"}}