{"passport":{"unfragile":{"@version":"1.0","version":"2026-05","artifact":{"id":"agentic","slug":"agentic","name":"Agentic","type":"framework","url":"https://agentic.so","page_url":"https://unfragile.ai/agentic","categories":["ai-agents","deployment-infra"],"tags":[],"pricing":{"model":"free","free":true,"starting_price":null},"status":"active","verified":false},"capabilities":[{"id":"agentic__cap_0","uri":"capability://tool.use.integration.multi.sdk.tool.integration.via.standardized.adapters","name":"multi-sdk tool integration via standardized adapters","description":"Agentic exposes tools through SDK-specific adapters (@agentic/ai-sdk for Vercel AI SDK, @agentic/platform-tool-client for direct consumption) that normalize tool schemas across different LLM frameworks. Each adapter translates Agentic's tool definitions into the native tool-calling format expected by the target SDK (OpenAI function calling, Vercel AI tool format, etc.), enabling developers to use the same Agentic tools across Vercel AI SDK, OpenAI, LangChain, LlamaIndex, Mastra, and Firebase GenKit without rewriting tool integration code.","intents":["I want to use the same web search tool across multiple LLM SDKs without duplicating integration code","I'm building with Vercel AI SDK but want access to a tool ecosystem that works with other frameworks too","I need to migrate from one LLM SDK to another without rewriting all my tool calling logic"],"best_for":["TypeScript developers building multi-SDK applications","teams standardizing on tool ecosystems across heterogeneous LLM stacks","developers avoiding vendor lock-in to a single LLM SDK"],"limitations":["Adapter coverage is SDK-specific — not all Agentic tools may be available for all SDKs simultaneously","Tool schema translation adds ~50-100ms latency per tool invocation due to adapter normalization","Breaking changes in upstream SDK tool-calling APIs require Agentic adapter updates","No automatic schema validation — developers must ensure tool parameters match the consuming SDK's expectations"],"requires":["TypeScript 4.7+","Node.js 18+","One of: Vercel AI SDK, OpenAI SDK, LangChain, LlamaIndex, Mastra, or Firebase GenKit","API key or authentication for the target LLM provider"],"input_types":["tool identifier string (e.g., '@agentic/search')","tool parameters as JSON matching the tool's schema"],"output_types":["tool result as JSON","structured tool response matching the consuming SDK's expected format"],"categories":["tool-use-integration","framework-interoperability"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"agentic__cap_1","uri":"capability://tool.use.integration.cloud.hosted.tool.marketplace.with.usage.based.billing","name":"cloud-hosted tool marketplace with usage-based billing","description":"Agentic operates a curated marketplace of LLM tools (e.g., @agentic/search for web search) hosted on Agentic's cloud infrastructure (Cloudflare Workers for MCP gateway, Node.js backend on Vercel). Tools are consumed via HTTP APIs or MCP protocol, with usage tracked and billed via Stripe on a per-tool, pay-as-you-go basis. Developers load tools by identifier (e.g., 'AgenticToolClient.fromIdentifier(@agentic/search)') and invoke them through their LLM SDK's tool-calling mechanism; Agentic handles execution, caching, rate-limiting, and billing transparently.","intents":["I want to add web search to my LLM application without building and hosting a search service myself","I need production-grade tools with SLAs and monitoring, not DIY implementations","I want to pay only for the tools I actually use, not maintain a fixed infrastructure cost","I'm building an agent that needs multiple specialized tools and want a single vendor for reliability"],"best_for":["startups and solo developers avoiding infrastructure overhead","teams building multi-tool agents who want managed, production-grade tool execution","developers prioritizing time-to-market over building custom tool infrastructure"],"limitations":["All tools are cloud-hosted — no local-first or offline execution option","Tool catalog is curated by Agentic, not community-driven like LangChain — fewer niche tools available","Pricing per tool is not enumerated in documentation — developers must check per-tool costs before committing","Vendor lock-in risk — migrating away from Agentic requires rewriting tool integration code for alternative providers","No guaranteed SLA terms published — 'production-ready' claim lacks specific uptime/latency guarantees","Rate-limiting and caching policies are customizable but not documented — developers must contact support for custom configurations"],"requires":["API key or authentication for Agentic platform","Stripe account for billing (if using paid tools)","Network connectivity to Agentic's cloud infrastructure","One of the supported LLM SDKs (Vercel AI, OpenAI, LangChain, etc.)"],"input_types":["tool identifier string","tool parameters as JSON"],"output_types":["tool result as JSON","structured response from the executed tool"],"categories":["tool-use-integration","automation-workflow"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"agentic__cap_10","uri":"capability://code.generation.editing.tool.schema.validation.and.type.safety.across.sdks","name":"tool schema validation and type safety across sdks","description":"Agentic enforces tool schema validation using JSON Schema or OpenAPI specifications, ensuring that tool parameters and responses conform to defined types. SDK adapters (e.g., @agentic/ai-sdk) provide TypeScript type definitions generated from tool schemas, enabling compile-time type checking and IDE autocomplete. When tools are invoked, Agentic validates parameters against the schema and returns type-safe results, reducing runtime errors and improving developer experience.","intents":["I want compile-time type safety when calling tools from TypeScript","I need to validate tool parameters before invoking them","I want IDE autocomplete and documentation for tool parameters"],"best_for":["TypeScript developers prioritizing type safety","teams building large-scale agents with many tool integrations","developers wanting to catch tool-calling errors at compile time"],"limitations":["Type safety is TypeScript-only — non-TypeScript consumers (Python, Go) do not benefit from compile-time checking","Schema validation is performed at runtime — no static analysis of tool calls","Type definitions are generated from tool schemas — schema quality directly impacts type safety","IDE autocomplete depends on SDK adapter implementation — not all SDKs may provide full autocomplete support","Breaking schema changes require SDK adapter updates — developers may experience type errors after tool updates"],"requires":["TypeScript 4.7+","Agentic SDK adapter for your LLM framework","Tool schema definition (JSON Schema or OpenAPI spec)"],"input_types":["tool parameters as TypeScript objects"],"output_types":["type-safe tool results as TypeScript objects"],"categories":["code-generation-editing","tool-use-integration"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"agentic__cap_11","uri":"capability://tool.use.integration.tool.composition.and.chaining.within.llm.sdk.workflows","name":"tool composition and chaining within llm sdk workflows","description":"Agentic tools are designed to compose seamlessly within LLM SDK tool-calling workflows, enabling developers to chain multiple tools together in a single agent loop. The LLM SDK (Vercel AI, OpenAI, etc.) orchestrates tool calls based on the model's reasoning, and Agentic tools integrate transparently into this workflow. Developers can combine Agentic tools with custom tools and SDK-native tools without special composition logic — the LLM SDK handles orchestration.","intents":["I want to build an agent that uses multiple Agentic tools in sequence","I need to combine Agentic tools with custom tools in a single agent workflow","I want the LLM to decide which tools to use and in what order"],"best_for":["developers building multi-step agents with complex reasoning","teams combining Agentic tools with custom or third-party tools","applications requiring tool orchestration and decision-making"],"limitations":["Tool composition is entirely delegated to the LLM SDK — Agentic provides no composition framework","No explicit tool dependency management — developers must ensure tools are compatible","Tool chaining latency compounds with each tool call — no optimization for sequential tool execution","No built-in tool composition patterns (e.g., map-reduce, fan-out) — developers must implement these in the LLM SDK","Tool result passing between steps is SDK-specific — no standardized format for tool output"],"requires":["LLM SDK with tool-calling support (Vercel AI, OpenAI, LangChain, etc.)","Multiple Agentic tools or a mix of Agentic and custom tools","LLM model capable of multi-step reasoning"],"input_types":["tool definitions and parameters"],"output_types":["composed tool results from multiple sequential or parallel tool calls"],"categories":["tool-use-integration","planning-reasoning"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"agentic__cap_2","uri":"capability://tool.use.integration.mcp.model.context.protocol.server.exposure.with.cloudflare.edge.gateway","name":"mcp (model context protocol) server exposure with cloudflare edge gateway","description":"Agentic exposes all marketplace tools as MCP servers accessible through a Cloudflare Workers-based gateway, enabling any MCP-compatible client (Claude Desktop, custom MCP consumers) to invoke Agentic tools without SDK integration. The MCP gateway runs on Cloudflare's global edge network, providing low-latency access to tools and handling protocol translation, authentication, and request routing. Developers can consume Agentic tools via standard MCP client libraries by connecting to the Agentic MCP gateway endpoint.","intents":["I want to use Agentic tools in Claude Desktop or other MCP-compatible applications without writing custom integration code","I need low-latency tool access from anywhere in the world via a globally distributed edge network","I'm building an MCP client and want access to a curated set of production-grade tools"],"best_for":["Claude Desktop users wanting to extend Claude with Agentic tools","developers building MCP-compatible applications","teams using MCP as their standard tool-calling protocol across multiple LLM clients"],"limitations":["MCP protocol support is limited to MCP-compatible clients — not all LLM applications support MCP yet","Cloudflare Workers have execution time limits (~30 seconds) — long-running tools may timeout","MCP gateway adds a network hop compared to direct SDK integration, introducing ~100-200ms latency","Authentication and rate-limiting via MCP are less granular than direct API access","Tool discovery via MCP is limited — developers must know tool identifiers in advance"],"requires":["MCP-compatible client (Claude Desktop, custom MCP consumer)","Network connectivity to Cloudflare's edge network","MCP client library for your platform (Python, TypeScript, etc.)"],"input_types":["MCP tool call request with parameters"],"output_types":["MCP tool result as JSON"],"categories":["tool-use-integration","automation-workflow"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"agentic__cap_3","uri":"capability://tool.use.integration.http.api.fallback.for.direct.tool.invocation","name":"http api fallback for direct tool invocation","description":"All Agentic tools are accessible via HTTP POST requests to Agentic's REST API, enabling developers to invoke tools directly without SDK integration or MCP protocol overhead. Each tool exposes a documented HTTP endpoint accepting JSON parameters and returning JSON results. This fallback mechanism allows developers to use Agentic tools from any programming language or environment (Python, Go, Rust, etc.) by making standard HTTP requests, bypassing the need for TypeScript SDK adapters.","intents":["I want to use Agentic tools from a non-TypeScript language (Python, Go, Rust, etc.)","I need to invoke tools from a serverless function or environment without SDK support","I want to test Agentic tools quickly without setting up SDK integration"],"best_for":["polyglot teams using multiple programming languages","developers building in languages without Agentic SDK support","rapid prototyping and testing scenarios"],"limitations":["HTTP API requires manual request/response handling — no automatic schema validation or type safety","No built-in retry logic or error handling — developers must implement these patterns","HTTP overhead (~50-100ms per request) is higher than direct SDK calls","API endpoint documentation is not enumerated in provided content — developers must discover endpoints","No SDK-level abstractions — developers must manually construct request bodies and parse responses"],"requires":["HTTP client library for your programming language","API key or authentication token for Agentic","Network connectivity to Agentic's HTTP API endpoint"],"input_types":["JSON request body with tool parameters"],"output_types":["JSON response with tool result"],"categories":["tool-use-integration"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"agentic__cap_4","uri":"capability://search.retrieval.web.search.tool.with.production.grade.caching.and.rate.limiting","name":"web search tool with production-grade caching and rate-limiting","description":"Agentic provides a built-in web search tool (@agentic/search) that integrates with major search APIs and implements production-grade caching (likely Redis-based) and customizable rate-limiting to optimize cost and performance. The tool accepts search queries as input and returns structured search results (title, URL, snippet, etc.). Caching reduces redundant API calls for identical queries, while rate-limiting prevents abuse and controls costs. Developers invoke the search tool through their LLM SDK's tool-calling mechanism, and Agentic handles the underlying search API orchestration transparently.","intents":["I want to add web search to my LLM agent without building a search integration myself","I need search results that are cached to reduce API costs and latency","I want to control search rate-limiting to prevent abuse or excessive API usage"],"best_for":["LLM agents that need real-time information retrieval","applications requiring current events, news, or web data","developers avoiding the complexity of search API integration"],"limitations":["Search result freshness depends on Agentic's cache TTL — not documented, likely 1-24 hours","Caching is global across all users — no per-user or per-query cache isolation","Rate-limiting policies are customizable but not documented — developers must contact support for custom limits","Search result quality depends on the underlying search API (not specified in documentation)","No control over search ranking, filtering, or advanced search operators — limited to basic query input","Pricing per search query is not enumerated — developers must check per-query costs"],"requires":["Agentic API key","One of the supported LLM SDKs","Network connectivity to Agentic's infrastructure"],"input_types":["search query string"],"output_types":["structured search results (title, URL, snippet, etc.) as JSON"],"categories":["search-retrieval","tool-use-integration"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"agentic__cap_5","uri":"capability://tool.use.integration.tool.publishing.and.monetization.for.custom.mcp.servers.and.openapi.services","name":"tool publishing and monetization for custom mcp servers and openapi services","description":"Agentic enables developers to publish custom tools (as MCP servers or OpenAPI services) to the Agentic marketplace and monetize them through usage-based pricing. Publishers define tool schemas, set pricing per invocation, and Agentic handles billing, payment processing (Stripe), and distribution. The platform manages tool versioning, SLAs, and monitoring. Developers can publish tools written in any language (as long as they expose MCP or OpenAPI interfaces) and earn revenue based on tool usage by other developers.","intents":["I've built a specialized tool (e.g., data enrichment, API wrapper) and want to monetize it","I want to publish my MCP server to a marketplace without building billing and distribution infrastructure","I'm a tool vendor and want to reach developers using Agentic without managing my own SaaS platform"],"best_for":["independent tool developers and vendors","teams building specialized tools for niche use cases","developers wanting to create a revenue stream from their tools"],"limitations":["Publisher pricing model is 'work in progress' — not yet fully implemented or documented","Tool discovery and marketing are limited to Agentic's marketplace — no direct control over visibility","Agentic takes a percentage of revenue (not specified in documentation)","Tool versioning and breaking change management are the publisher's responsibility","SLA guarantees are the publisher's responsibility — Agentic does not provide managed SLAs for published tools","No built-in analytics or usage reporting — publishers must request usage data from Agentic"],"requires":["MCP server or OpenAPI service implementation","Stripe account for receiving payments","Agentic developer account and publishing credentials","Tool schema definition (JSON Schema or OpenAPI spec)"],"input_types":["MCP server or OpenAPI service definition","tool schema and pricing configuration"],"output_types":["published tool accessible via Agentic marketplace","usage-based revenue from tool invocations"],"categories":["tool-use-integration","automation-workflow"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"agentic__cap_6","uri":"capability://search.retrieval.semantic.tool.discovery.and.recommendation","name":"semantic tool discovery and recommendation","description":"Agentic's marketplace provides semantic search and discovery capabilities enabling developers to find tools by natural language description or capability (e.g., 'I need a tool that extracts data from PDFs'). The discovery system likely uses embeddings-based search to match developer queries against tool descriptions and capabilities, surfacing relevant tools without requiring exact tool name knowledge. This reduces friction in tool selection and helps developers discover tools they didn't know existed.","intents":["I need a tool for a specific capability but don't know the exact tool name","I want to discover what tools are available for my use case","I'm exploring the Agentic marketplace and want recommendations based on my needs"],"best_for":["developers new to the Agentic ecosystem exploring available tools","teams building agents and wanting to discover specialized tools for specific tasks","rapid prototyping scenarios where developers need quick tool discovery"],"limitations":["Semantic search quality depends on tool description quality — poorly described tools may not be discoverable","Tool discovery is limited to Agentic's curated marketplace — no external tool sources","No collaborative filtering or usage-based recommendations — discovery is purely semantic","Tool discovery interface and API are not documented in provided content","No saved searches or tool collections — developers must re-discover tools on each visit"],"requires":["Access to Agentic marketplace website or API","Natural language query or tool capability description"],"input_types":["natural language query (e.g., 'PDF data extraction')","tool capability description"],"output_types":["ranked list of relevant tools with descriptions and pricing"],"categories":["search-retrieval","tool-use-integration"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"agentic__cap_7","uri":"capability://tool.use.integration.tool.versioning.and.backward.compatibility.management","name":"tool versioning and backward compatibility management","description":"Agentic supports semantic versioning for published tools, enabling publishers to release updates while maintaining backward compatibility with existing consumers. The platform manages tool version resolution, allowing developers to pin specific tool versions or use version ranges (e.g., '@agentic/search@1.x'). Breaking changes are handled through explicit version bumps, and Agentic provides tooling for publishers to deprecate old versions and migrate users to new ones.","intents":["I want to update a tool I'm using without breaking my application","I'm publishing a tool and need to manage versions and breaking changes","I want to pin a specific tool version to ensure consistent behavior across deployments"],"best_for":["teams using tools in production and requiring version stability","tool publishers managing multiple versions and user migrations","developers building applications with strict dependency management"],"limitations":["Version resolution logic is not documented — developers must infer versioning behavior","Breaking change handling is the publisher's responsibility — Agentic does not enforce backward compatibility","No automatic migration tooling — developers must manually update tool calls when versions change","Version pinning is at the tool level, not the entire dependency tree — no lock file equivalent","Deprecation policies are not documented — publishers must communicate deprecations manually"],"requires":["Semantic versioning understanding","Tool identifier with optional version specifier (e.g., '@agentic/search@1.2.3')"],"input_types":["tool identifier with version specifier"],"output_types":["resolved tool version and schema"],"categories":["tool-use-integration","automation-workflow"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"agentic__cap_8","uri":"capability://tool.use.integration.production.grade.tool.execution.with.slas.and.monitoring","name":"production-grade tool execution with slas and monitoring","description":"Agentic claims to provide production-grade tool execution with SLAs (Service Level Agreements) and monitoring, implying uptime guarantees, latency targets, and observability. Tools are executed on Agentic's managed infrastructure (Vercel, Cloudflare Workers) with built-in error handling, retry logic, and monitoring. Developers can rely on Agentic tools for mission-critical applications without building their own reliability infrastructure.","intents":["I need tools with guaranteed uptime and latency for production applications","I want to monitor tool performance and reliability without building custom monitoring","I need tools that handle errors gracefully and retry on failure"],"best_for":["production applications requiring high reliability","teams building mission-critical agents","developers avoiding the complexity of tool infrastructure management"],"limitations":["SLA terms are not published in documentation — specific uptime guarantees and latency targets are unknown","Monitoring and alerting capabilities are not documented — developers must contact support for details","Retry logic and error handling policies are not documented — behavior is opaque to developers","No SLA credits or compensation policy documented — recourse for SLA violations is unclear","Tool reliability depends on underlying service providers (search APIs, etc.) — Agentic's SLA may not cover upstream failures","No published status page or incident history — developers cannot assess historical reliability"],"requires":["Agentic API key","Production-grade LLM SDK integration","Network connectivity to Agentic's infrastructure"],"input_types":["tool invocation request"],"output_types":["tool result with implicit reliability guarantees"],"categories":["tool-use-integration","automation-workflow"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"agentic__cap_9","uri":"capability://code.generation.editing.open.source.typescript.sdk.with.community.contributions","name":"open-source typescript sdk with community contributions","description":"Agentic is fully open-source on GitHub, with a TypeScript codebase that developers can inspect, fork, and contribute to. The SDK includes core client libraries (@agentic/platform-tool-client), SDK adapters (@agentic/ai-sdk), and example tools (@agentic/search). The open-source model enables community contributions, security audits, and transparency into Agentic's implementation. Developers can self-host Agentic components or contribute improvements back to the project.","intents":["I want to audit Agentic's code for security and reliability before using it in production","I want to contribute improvements or custom tools back to the Agentic project","I want to self-host Agentic components for compliance or performance reasons"],"best_for":["security-conscious teams requiring code transparency","developers wanting to contribute to the Agentic ecosystem","organizations with self-hosting requirements"],"limitations":["Open-source license is not specified in documentation — unclear if MIT, Apache 2.0, or other","Self-hosting Agentic components requires infrastructure setup (Postgres, Node.js, Cloudflare Workers) — not documented","Community is described as 'small but vibrant' — limited contributor base and slower issue resolution","No formal governance or contribution guidelines documented — contribution process is unclear","Self-hosted instances do not benefit from Agentic's managed infrastructure (SLAs, monitoring, billing) — developers must implement these","Marketplace integration requires Agentic's cloud platform — self-hosted instances cannot publish or consume marketplace tools"],"requires":["GitHub account for accessing the repository","TypeScript and Node.js knowledge for understanding and contributing to the codebase","For self-hosting: Postgres, Node.js 18+, Cloudflare Workers account"],"input_types":["GitHub repository access"],"output_types":["source code, documentation, and contribution opportunities"],"categories":["code-generation-editing","tool-use-integration"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"agentic__headline","uri":"capability://tool.use.integration.typescript.first.framework.for.building.ai.agents","name":"typescript-first framework for building ai agents","description":"Agentic is a TypeScript-first framework designed for developers to create production-ready AI agents with a standard library of well-typed tools, enabling reliable workflows with minimal boilerplate.","intents":["best TypeScript framework for AI agents","AI agent framework for production","TypeScript tools for building AI workflows","create AI agents with TypeScript","AI agent development framework comparison"],"best_for":["developers looking for TypeScript solutions","teams building AI workflows"],"limitations":[],"requires":["TypeScript knowledge"],"input_types":[],"output_types":[],"categories":["tool-use-integration"],"confidence":0.5,"matches":0,"success_rate":0}],"trust":{"score":60,"verified":false,"data_access_risk":"high","permissions":["TypeScript 4.7+","Node.js 18+","One of: Vercel AI SDK, OpenAI SDK, LangChain, LlamaIndex, Mastra, or Firebase GenKit","API key or authentication for the target LLM provider","API key or authentication for Agentic platform","Stripe account for billing (if using paid tools)","Network connectivity to Agentic's cloud infrastructure","One of the supported LLM SDKs (Vercel AI, OpenAI, LangChain, etc.)","Agentic SDK adapter for your LLM framework","Tool schema definition (JSON Schema or OpenAPI spec)"],"failure_modes":["Adapter coverage is SDK-specific — not all Agentic tools may be available for all SDKs simultaneously","Tool schema translation adds ~50-100ms latency per tool invocation due to adapter normalization","Breaking changes in upstream SDK tool-calling APIs require Agentic adapter updates","No automatic schema validation — developers must ensure tool parameters match the consuming SDK's expectations","All tools are cloud-hosted — no local-first or offline execution option","Tool catalog is curated by Agentic, not community-driven like LangChain — fewer niche tools available","Pricing per tool is not enumerated in documentation — developers must check per-tool costs before committing","Vendor lock-in risk — migrating away from Agentic requires rewriting tool integration code for alternative providers","No guaranteed SLA terms published — 'production-ready' claim lacks specific uptime/latency guarantees","Rate-limiting and caching policies are customizable but not documented — developers must contact support for custom configurations","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":0.75,"weights":{"adoption":0.3,"quality":0.2,"ecosystem":0.15,"match_graph":0.23,"freshness":0.12}},"observed_outcomes":{"matches":0,"success_rate":0,"avg_confidence":0,"top_intents":[],"last_matched_at":null},"maintenance":{"status":"active","updated_at":"2026-05-24T12:16:19.836Z","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=agentic","compare_url":"https://unfragile.ai/compare?artifact=agentic"}},"signature":"dkho6qUhMVxJsXvTS5n79/3gKwf10Ao9EWoA1+XEp7dhl9LhmH3v0bIeQZVQFTwouogq2+8+qYg4xcqzOQNzAQ==","signedAt":"2026-06-20T06:54:46.898Z","signedBy":"unfragile.ai","version":1},"_links":{"self":"https://unfragile.ai/api/v1/passport/agentic","artifact":"https://unfragile.ai/agentic","verify":"https://unfragile.ai/api/v1/verify?slug=agentic","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"}}