{"passport":{"unfragile":{"@version":"1.0","version":"2026-05","artifact":{"id":"tool_respell","slug":"respell","name":"Respell","type":"product","url":"https://www.respell.ai","page_url":"https://unfragile.ai/respell","categories":["automation"],"tags":[],"pricing":{"model":"freemium","free":true,"starting_price":null},"status":"active","verified":false},"capabilities":[{"id":"tool_respell__cap_0","uri":"capability://planning.reasoning.natural.language.workflow.composition.with.conversational.prompts","name":"natural language workflow composition with conversational prompts","description":"Converts natural language task descriptions into executable workflow definitions through an LLM-powered intent parser that maps conversational instructions to workflow nodes and connections. The system interprets user intent (e.g., 'send me a Slack message when a new email arrives in Gmail') and translates it into a directed acyclic graph of actions, conditions, and data transformations without requiring users to manually construct the workflow graph.","intents":["I want to describe what I need in plain English and have the system build the workflow for me","I need to automate a task but don't know the technical steps or API calls required","I want to quickly prototype a workflow idea without learning a visual builder interface"],"best_for":["Non-technical business users and solopreneurs automating routine tasks","Teams without dedicated automation engineers seeking rapid prototyping","Users migrating from manual processes who lack technical workflow knowledge"],"limitations":["LLM-generated workflows may produce logically incorrect or inefficient node arrangements requiring manual review and testing","Complex conditional logic with multiple branches may be misinterpreted or oversimplified by the language model","Ambiguous natural language descriptions can result in workflows that don't match user intent, requiring iterative refinement","No built-in validation that generated workflows are syntactically correct before execution"],"requires":["Active Respell account with API access","LLM provider API key (OpenAI, Anthropic, or other supported provider)","Internet connectivity for real-time intent parsing"],"input_types":["natural language text","conversational prompts","task descriptions"],"output_types":["workflow definition (DAG structure)","node configuration objects","action sequences"],"categories":["planning-reasoning","automation-workflow"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"tool_respell__cap_1","uri":"capability://tool.use.integration.multi.provider.llm.orchestration.with.provider.abstraction","name":"multi-provider llm orchestration with provider abstraction","description":"Abstracts LLM provider APIs (OpenAI, Anthropic, Google, Ollama, etc.) behind a unified interface, allowing workflows to invoke different LLM providers with consistent prompting patterns and parameter mapping. The system handles provider-specific request formatting, token counting, rate limiting, and response parsing, enabling users to swap providers or use multiple providers in a single workflow without modifying workflow logic.","intents":["I want to use different LLM providers in the same workflow without rewriting prompts for each API","I need to switch from OpenAI to a cheaper provider without rebuilding my automation","I want to leverage provider-specific capabilities (e.g., Claude's long context) within my workflow"],"best_for":["Teams evaluating multiple LLM providers and wanting to avoid vendor lock-in","Cost-conscious teams seeking to optimize LLM spend by mixing providers","Workflows requiring specialized model capabilities (vision, long context, function calling)"],"limitations":["Provider abstraction adds ~50-100ms latency per LLM call due to request translation and response normalization","Not all provider-specific features are exposed through the abstraction layer (e.g., some vision capabilities may be unavailable)","Rate limiting and quota management are provider-specific and may not be transparently surfaced to users","Token counting accuracy varies by provider; billing calculations may not perfectly match actual provider charges"],"requires":["API keys for at least one supported LLM provider","Respell account with LLM integration permissions","Understanding of which providers support required capabilities (vision, function calling, etc.)"],"input_types":["prompts (text)","provider configuration (JSON)","model parameters (temperature, max_tokens, etc.)"],"output_types":["LLM responses (text)","structured outputs (JSON when using function calling)","token usage metrics"],"categories":["tool-use-integration","automation-workflow"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"tool_respell__cap_10","uri":"capability://automation.workflow.workflow.sharing.and.collaboration.with.role.based.access.control","name":"workflow sharing and collaboration with role-based access control","description":"Enables teams to share workflows and collaborate on workflow development through role-based access control that defines permissions for viewing, editing, and executing workflows. The system tracks workflow ownership, manages team access, and provides audit logs of who made changes and when, enabling teams to collaborate safely without requiring shared credentials or manual permission management.","intents":["I want to share a workflow with my team so they can use it without needing to rebuild it","I need to control who can edit workflows and who can only view or execute them","I want to track who made changes to a workflow for audit and accountability purposes"],"best_for":["Teams collaborating on workflow development and maintenance","Organizations with multiple users needing access to shared workflows","Teams with compliance requirements for audit trails and access control"],"limitations":["Role-based access control is coarse-grained; fine-grained permissions (e.g., edit specific nodes) are not supported","Shared workflows may have conflicting edits if multiple users modify simultaneously; last-write-wins conflict resolution may lose changes","No built-in notification system for workflow changes; users must manually check for updates","Audit logs are retained for a limited time; long-term audit trails require external storage"],"requires":["Respell account with team/organization features enabled","Team members with Respell accounts","Clear definition of roles and permissions for each team member"],"input_types":["workflow definition","user/team identifiers","role assignments (viewer, editor, owner, etc.)"],"output_types":["access control list (ACL)","audit log (who made changes and when)","shared workflow link or reference"],"categories":["automation-workflow"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"tool_respell__cap_11","uri":"capability://code.generation.editing.custom.code.execution.within.workflows.with.sandboxed.runtime","name":"custom code execution within workflows with sandboxed runtime","description":"Allows users to embed custom code (JavaScript, Python) within workflows to perform transformations or logic that cannot be expressed through pre-built actions or LLM evaluation. The system executes custom code in a sandboxed runtime environment with access to workflow context (previous step outputs, input parameters) and provides error handling and timeout protection to prevent runaway code from blocking workflow execution.","intents":["I need to perform a custom calculation or data transformation that isn't available in pre-built actions","I want to write a small script to process data between workflow steps","I need to implement complex logic that requires programming rather than configuration"],"best_for":["Workflows requiring custom logic that cannot be expressed through pre-built actions or LLM evaluation","Teams with some technical expertise seeking to extend workflow capabilities","Scenarios where performance or determinism is critical (custom code is faster and more predictable than LLM evaluation)"],"limitations":["Custom code execution requires programming knowledge; non-technical users cannot use this capability","Sandboxed runtime may have limited access to external resources (network, file system); complex integrations may not be possible","Code execution adds latency (~100-500ms per code block) compared to pre-built actions","Debugging custom code is difficult; error messages may not clearly indicate the source of failures","Security risk if custom code is not properly validated; malicious code could potentially escape the sandbox"],"requires":["Respell account with custom code execution enabled","Programming knowledge (JavaScript or Python)","Understanding of workflow context and available APIs","Testing and validation of custom code before production deployment"],"input_types":["custom code (JavaScript or Python)","workflow context (previous step outputs, input parameters)","external data (from previous steps or workflow inputs)"],"output_types":["code execution result (return value)","error messages (if code fails)","execution time and resource usage"],"categories":["code-generation-editing","automation-workflow"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"tool_respell__cap_12","uri":"capability://automation.workflow.workflow.templates.and.marketplace.with.pre.built.automation.patterns","name":"workflow templates and marketplace with pre-built automation patterns","description":"Provides a library of pre-built workflow templates for common automation scenarios (lead qualification, customer onboarding, support ticket routing, etc.) that users can instantiate and customize. Templates include pre-configured triggers, actions, and logic that users can modify to fit their specific needs, reducing time to deployment and providing reference implementations for best practices.","intents":["I want to quickly set up a workflow for a common scenario without building from scratch","I need inspiration or reference implementations for how to structure my workflow","I want to use a proven pattern that has worked for other teams"],"best_for":["Teams automating common business processes (lead qualification, customer onboarding, support routing)","Non-technical users seeking to avoid building workflows from scratch","Organizations seeking to standardize automation patterns across teams"],"limitations":["Template library is limited to common scenarios; niche or industry-specific workflows may not have templates","Templates may require significant customization to fit specific business processes; time savings may be minimal for complex scenarios","Template quality varies; poorly designed templates may introduce bad practices or inefficiencies","Templates may become outdated if tool integrations or best practices change"],"requires":["Respell account with access to template library","Understanding of the template's purpose and how to customize it for specific needs"],"input_types":["template selection","customization parameters (tool accounts, field mappings, etc.)"],"output_types":["instantiated workflow","template documentation and usage guide"],"categories":["automation-workflow"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"tool_respell__cap_2","uri":"capability://planning.reasoning.intelligent.chat.agent.with.multi.turn.conversation.state.management","name":"intelligent chat agent with multi-turn conversation state management","description":"Maintains stateful conversation context across multiple user interactions, enabling agents to remember prior messages, extract relevant context, and make decisions based on conversation history. The system manages conversation state (message history, extracted entities, decision context) in a structured format, allowing agents to reference prior turns and build coherent multi-step interactions without requiring users to re-provide context.","intents":["I want a chat agent that remembers what I told it earlier in the conversation","I need the agent to ask clarifying questions and use answers to refine its actions","I want the agent to maintain context across multiple conversation turns to handle complex requests"],"best_for":["Customer support teams building conversational automation that handles multi-step inquiries","Teams automating complex workflows that require user input and clarification mid-execution","Applications requiring natural, context-aware interactions rather than single-turn request/response"],"limitations":["Conversation state grows linearly with message count; very long conversations may exceed context windows of underlying LLMs","No built-in conversation summarization or context compression, requiring manual pruning for long-running agents","State persistence is not guaranteed across agent restarts without explicit checkpoint configuration","Multi-turn reasoning can amplify LLM errors (hallucinations compound across turns)"],"requires":["Respell account with chat agent capabilities enabled","LLM provider with sufficient context window for conversation history","Storage backend for conversation state (Respell-managed or external)"],"input_types":["user messages (text)","conversation history (structured message objects)","context metadata (user ID, session ID, etc.)"],"output_types":["agent responses (text)","extracted entities (JSON)","action payloads (for downstream workflow steps)","conversation state snapshots"],"categories":["planning-reasoning","text-generation-language"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"tool_respell__cap_3","uri":"capability://automation.workflow.declarative.workflow.trigger.configuration.with.event.based.activation","name":"declarative workflow trigger configuration with event-based activation","description":"Defines workflow entry points through declarative trigger configurations that listen for external events (webhook payloads, scheduled times, manual invocations, or provider-specific events like new emails or Slack messages) and automatically instantiate workflow executions when trigger conditions are met. Triggers are configured through a schema-based interface that maps event properties to workflow input parameters without requiring code.","intents":["I want my workflow to automatically run when a specific event happens (e.g., new email, Slack message)","I need to trigger workflows on a schedule (daily, weekly, or custom intervals)","I want to manually invoke workflows through a button or webhook without writing code"],"best_for":["Teams automating event-driven processes (customer signups, support tickets, form submissions)","Workflows requiring scheduled execution (daily reports, weekly syncs, periodic cleanups)","Integration scenarios where external systems need to trigger Respell workflows via webhooks"],"limitations":["Webhook-based triggers may experience latency (100-500ms) between event occurrence and workflow execution","Scheduled triggers are subject to platform execution queues; exact execution time is not guaranteed","No built-in deduplication for duplicate events; workflows may execute multiple times for the same event if not explicitly deduplicated","Complex event filtering logic must be implemented within the workflow rather than at the trigger level"],"requires":["Respell account with trigger configuration permissions","For webhook triggers: ability to configure webhooks in source systems (Gmail, Slack, etc.)","For scheduled triggers: timezone configuration and cron expression support","For manual triggers: user access to workflow invocation interface"],"input_types":["event payloads (JSON from webhooks)","schedule definitions (cron expressions or interval specifications)","manual invocation parameters (form inputs or API payloads)"],"output_types":["workflow execution instances","execution status (queued, running, completed, failed)","trigger metadata (event timestamp, source, etc.)"],"categories":["automation-workflow","tool-use-integration"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"tool_respell__cap_4","uri":"capability://tool.use.integration.integrated.business.tool.connector.library.with.pre.built.action.templates","name":"integrated business tool connector library with pre-built action templates","description":"Provides pre-built connectors for popular business tools (Slack, Gmail, Notion, HubSpot, Salesforce, Google Sheets, etc.) that expose tool-specific actions as workflow nodes without requiring users to write API calls. Each connector includes action templates (e.g., 'send Slack message', 'create Notion page', 'update HubSpot contact') with parameter mapping, authentication handling, and response normalization, enabling workflows to interact with external tools through a consistent interface.","intents":["I want to send messages to Slack, create tasks in Notion, or update records in HubSpot from my workflow","I need to read data from Gmail, Google Sheets, or other tools and use it in my automation","I want to avoid writing API calls and instead use pre-configured actions for common tasks"],"best_for":["Teams using popular SaaS tools (Slack, Notion, HubSpot) and seeking to automate cross-tool workflows","Non-technical users who need to integrate tools without learning APIs","Organizations with standardized tool stacks seeking rapid automation deployment"],"limitations":["Connector coverage is limited to popular tools; niche or enterprise-specific tools may not have pre-built connectors","Pre-built action templates may not expose all tool capabilities; advanced features may require custom API calls","Authentication requires users to grant OAuth permissions or provide API keys; permission scoping may be overly broad","Tool API changes may break workflows if connectors are not kept in sync with provider updates"],"requires":["Respell account with connector library access","OAuth credentials or API keys for each tool being integrated","Tool accounts with appropriate permissions (e.g., Slack workspace admin for workspace-level actions)","Understanding of tool-specific concepts (channels, databases, objects, etc.)"],"input_types":["action parameters (text, numbers, dates, etc.)","data from previous workflow steps","tool-specific identifiers (channel IDs, page IDs, contact IDs, etc.)"],"output_types":["tool-specific responses (message IDs, page URLs, contact records, etc.)","structured data (JSON objects representing tool entities)","execution status and error messages"],"categories":["tool-use-integration","automation-workflow"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"tool_respell__cap_5","uri":"capability://planning.reasoning.conditional.branching.and.decision.logic.with.llm.powered.evaluation","name":"conditional branching and decision logic with llm-powered evaluation","description":"Enables workflows to branch execution paths based on conditions evaluated by LLMs or traditional rule engines. The system supports both explicit rule-based conditions (if X equals Y, then branch A) and implicit LLM-evaluated conditions (if the sentiment is positive, then branch A), allowing workflows to make intelligent decisions based on unstructured data without requiring users to write conditional logic code.","intents":["I want my workflow to make different decisions based on email content or user input","I need to route tasks to different teams based on priority, sentiment, or category","I want to use AI to evaluate conditions rather than writing explicit if/then rules"],"best_for":["Workflows requiring intelligent routing or classification (support ticket triage, lead scoring, content moderation)","Teams automating decision-making processes that depend on unstructured data (emails, messages, documents)","Organizations seeking to reduce manual decision-making through AI-powered branching"],"limitations":["LLM-evaluated conditions introduce non-determinism; identical inputs may produce different branches on different executions","LLM evaluation adds latency (~500ms-2s per condition) compared to rule-based branching","Complex multi-branch logic can become difficult to reason about and test; debugging branching decisions requires examining LLM reasoning","No built-in explainability for why a particular branch was chosen; users must infer decision logic from LLM outputs"],"requires":["Respell account with conditional branching enabled","LLM provider API key for LLM-evaluated conditions","Clear definition of branching criteria and expected outcomes","Test data to validate branching logic before production deployment"],"input_types":["condition definitions (text descriptions or rule objects)","data to evaluate (text, structured objects, etc.)","branch configuration (target nodes for each branch)"],"output_types":["branch selection (which path to execute)","condition evaluation results (true/false or confidence scores)","reasoning or explanation (for LLM-evaluated conditions)"],"categories":["planning-reasoning","automation-workflow"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"tool_respell__cap_6","uri":"capability://automation.workflow.workflow.execution.monitoring.and.error.handling.with.retry.logic","name":"workflow execution monitoring and error handling with retry logic","description":"Provides visibility into workflow execution status, logs, and error states, with built-in retry mechanisms for failed steps. The system tracks execution progress through each workflow node, captures logs and error messages, and automatically retries failed steps with configurable backoff strategies (exponential backoff, fixed delay, etc.) without requiring manual intervention or workflow re-execution.","intents":["I want to see what happened when my workflow failed and why","I need failed steps to automatically retry instead of requiring manual re-execution","I want to monitor workflow execution in real-time and get alerts when something goes wrong"],"best_for":["Teams running production workflows that require reliability and observability","Workflows integrating with external APIs that may experience transient failures","Organizations needing audit trails and execution history for compliance"],"limitations":["Retry logic may mask underlying issues; excessive retries can delay error detection and notification","Execution logs are retained for a limited time (typically 30-90 days); long-term audit trails require external storage","No built-in alerting for specific error types; users must configure external monitoring or check logs manually","Retry logic does not handle idempotency; workflows that perform side effects (sending emails, creating records) may duplicate actions on retry"],"requires":["Respell account with execution monitoring enabled","Configuration of retry policies (max retries, backoff strategy)","Optional: external monitoring or alerting system for critical workflows","Understanding of which steps are idempotent and safe to retry"],"input_types":["workflow execution instances","error messages and stack traces","retry configuration (max retries, backoff strategy)"],"output_types":["execution logs (timestamped events)","error details (error type, message, stack trace)","execution status (running, completed, failed, retrying)","retry history (number of retries, timestamps)"],"categories":["automation-workflow","safety-moderation"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"tool_respell__cap_7","uri":"capability://data.processing.analysis.data.transformation.and.mapping.with.schema.based.extraction","name":"data transformation and mapping with schema-based extraction","description":"Transforms and maps data between workflow steps using schema-based extraction that parses unstructured data (emails, documents, API responses) into structured formats. The system uses LLMs or rule-based parsers to extract relevant fields from unstructured inputs and map them to downstream tool schemas, enabling workflows to normalize data across different tool formats without requiring users to write transformation code.","intents":["I want to extract information from an email and use it to create a task in my project management tool","I need to map fields from one tool's format to another tool's format without writing code","I want to parse unstructured data (documents, messages) and extract structured information"],"best_for":["Workflows integrating tools with different data schemas or formats","Automation scenarios requiring extraction of information from unstructured sources (emails, documents, chat messages)","Teams seeking to avoid manual data entry or transformation code"],"limitations":["LLM-based extraction is non-deterministic; identical inputs may produce different extractions on different runs","Extraction accuracy depends on input quality and clarity; ambiguous or malformed data may result in incorrect extractions","Schema-based extraction requires explicit schema definition; complex or nested schemas may be difficult to specify","No built-in validation that extracted data matches expected schema; invalid extractions may propagate downstream"],"requires":["Respell account with data transformation capabilities","LLM provider API key for LLM-based extraction","Clear definition of source data format and target schema","Test data to validate extraction accuracy before production deployment"],"input_types":["unstructured data (text, emails, documents)","structured data (JSON, CSV, etc.)","schema definitions (JSON schema or similar)"],"output_types":["extracted structured data (JSON objects)","mapped data (transformed to target schema)","extraction confidence scores (for LLM-based extraction)"],"categories":["data-processing-analysis","automation-workflow"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"tool_respell__cap_8","uri":"capability://automation.workflow.workflow.versioning.and.rollback.with.execution.history","name":"workflow versioning and rollback with execution history","description":"Maintains version history of workflow definitions, allowing users to view, compare, and rollback to previous versions. The system tracks changes to workflow structure, node configuration, and trigger settings, enabling users to revert to known-good versions if a workflow update introduces errors or unintended behavior without losing execution history or requiring manual workflow reconstruction.","intents":["I want to see what changed in my workflow and revert to a previous version if something broke","I need to maintain multiple versions of a workflow for A/B testing or gradual rollout","I want to understand the history of changes to a workflow for audit or debugging purposes"],"best_for":["Teams managing production workflows that require change control and rollback capabilities","Organizations with compliance requirements for audit trails and change history","Workflows that are frequently updated and require safe rollback mechanisms"],"limitations":["Version history is stored indefinitely; storage costs may increase for workflows with frequent updates","Rollback does not restore execution state; in-flight executions continue with the current version","No built-in approval workflow for version changes; users can deploy versions without review","Version comparison is limited to workflow structure; semantic changes (e.g., parameter value changes) may not be clearly highlighted"],"requires":["Respell account with versioning enabled","Workflow definition storage (Respell-managed)","Understanding of workflow semantics to identify breaking changes"],"input_types":["workflow definition changes","version metadata (timestamp, author, description)"],"output_types":["version history (list of previous versions)","version comparison (diff between versions)","rollback confirmation (success/failure status)"],"categories":["automation-workflow"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"tool_respell__cap_9","uri":"capability://automation.workflow.workflow.testing.and.simulation.with.dry.run.execution","name":"workflow testing and simulation with dry-run execution","description":"Enables users to test workflows before deploying to production by executing them in a simulation mode that processes real or synthetic data without triggering external side effects. The system captures execution logs, output data, and error states, allowing users to validate workflow logic and identify issues before production deployment without risking unintended actions (sending emails, creating records, etc.).","intents":["I want to test my workflow with real data before deploying it to production","I need to verify that my workflow produces the expected output without actually sending emails or creating records","I want to debug workflow logic by examining execution logs and intermediate data"],"best_for":["Teams deploying new workflows or making significant changes to existing workflows","Workflows with side effects (sending emails, creating records) that require careful validation","Organizations with strict change control policies requiring testing before production deployment"],"limitations":["Dry-run execution may not catch all issues; some errors only manifest in production with real data or timing conditions","Dry-run mode requires manual data preparation; synthetic data may not reflect real-world edge cases","Execution logs in dry-run mode may not be identical to production logs due to timing differences or external state changes","No built-in test framework or assertion language; users must manually validate outputs"],"requires":["Respell account with testing capabilities enabled","Test data (real or synthetic) to execute the workflow","Understanding of expected workflow outputs for validation"],"input_types":["workflow definition","test data (real or synthetic)","trigger configuration (for simulating trigger events)"],"output_types":["execution logs (timestamped events)","intermediate data (outputs from each workflow step)","final output (workflow result)","error details (if execution fails)"],"categories":["automation-workflow"],"confidence":0.5,"matches":0,"success_rate":0}],"trust":{"score":43,"verified":false,"data_access_risk":"high","permissions":["Active Respell account with API access","LLM provider API key (OpenAI, Anthropic, or other supported provider)","Internet connectivity for real-time intent parsing","API keys for at least one supported LLM provider","Respell account with LLM integration permissions","Understanding of which providers support required capabilities (vision, function calling, etc.)","Respell account with team/organization features enabled","Team members with Respell accounts","Clear definition of roles and permissions for each team member","Respell account with custom code execution enabled"],"failure_modes":["LLM-generated workflows may produce logically incorrect or inefficient node arrangements requiring manual review and testing","Complex conditional logic with multiple branches may be misinterpreted or oversimplified by the language model","Ambiguous natural language descriptions can result in workflows that don't match user intent, requiring iterative refinement","No built-in validation that generated workflows are syntactically correct before execution","Provider abstraction adds ~50-100ms latency per LLM call due to request translation and response normalization","Not all provider-specific features are exposed through the abstraction layer (e.g., some vision capabilities may be unavailable)","Rate limiting and quota management are provider-specific and may not be transparently surfaced to users","Token counting accuracy varies by provider; billing calculations may not perfectly match actual provider charges","Role-based access control is coarse-grained; fine-grained permissions (e.g., edit specific nodes) are not supported","Shared workflows may have conflicting edits if multiple users modify simultaneously; last-write-wins conflict resolution may lose changes","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":0.25,"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":"2026-05-24T12:16:33.095Z","last_scraped_at":"2026-04-05T13:23:42.551Z","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=respell","compare_url":"https://unfragile.ai/compare?artifact=respell"}},"signature":"1WJlnkP525aiC/E0vo0gt2wRLgFhro/HaNTScrUsYCKGBJDkVlUM0QXoXPt6vWO3FfhyIamxDANqmdlJhupiDQ==","signedAt":"2026-06-20T19:55:28.434Z","signedBy":"unfragile.ai","version":1},"_links":{"self":"https://unfragile.ai/api/v1/passport/respell","artifact":"https://unfragile.ai/respell","verify":"https://unfragile.ai/api/v1/verify?slug=respell","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"}}