Clevis

Clevis provides a drag-and-drop interface that chains AI model calls, data transformations, and conditional logic without code. Users connect nodes representing API calls, prompt templates, and data flows into directed acyclic graphs (DAGs) that execute sequentially or in parallel. The builder abstracts away HTTP request construction, authentication, and response parsing by exposing model-agnostic input/output ports that automatically serialize/deserialize between UI forms and API payloads.

Clevis abstracts differences between OpenAI, Anthropic, and local model APIs through a unified prompt node that accepts template variables, system messages, and model parameters (temperature, max_tokens, top_p). The platform handles provider-specific authentication, request formatting, and response parsing internally. Users define prompts once and can swap between providers (e.g., GPT-4 to Claude) by changing a dropdown without rewriting the workflow.

Clevis allows creators to save workflow versions and deploy specific versions to production. Users can revert to previous versions if a deployment breaks, and maintain separate draft and published versions. The platform tracks version history with timestamps and creator information, but does not support branching or collaborative editing.

Clevis provides a marketplace where creators can publish workflows for other users to discover, clone, and use. Published workflows can be monetized (paid) or free. The marketplace includes search, filtering by category/rating, and one-click cloning. However, the marketplace is nascent with limited content and discoverability.

Clevis embeds Stripe payment processing directly into published apps, allowing creators to charge users per API call, per subscription tier, or per-use basis without external payment infrastructure. The platform handles billing logic, invoice generation, and payout management. Creators define pricing rules in the workflow (e.g., 'charge $0.10 per request'), and Clevis automatically gates access and deducts credits from user accounts before executing the workflow.

Clevis provides a template system for AI prompts that supports variable interpolation (e.g., {{user_input}}, {{context}}) and conditional text blocks. Templates are stored in the workflow and rendered at runtime by substituting variables from user input, previous workflow steps, or external data sources. The system supports Handlebars-style syntax for basic logic (if/else, loops) within prompts.

Clevis includes transformation nodes that parse, filter, and restructure AI model outputs into structured data. Users can extract JSON fields from text responses, split responses into arrays, apply regex patterns, or map responses to predefined schemas. The platform supports chaining transformations (e.g., extract JSON → filter by field → format as CSV) without writing code.

Clevis automatically exposes published workflows as HTTP REST APIs with auto-generated OpenAPI schemas. Users can publish a workflow and immediately get a public URL that accepts JSON requests and returns responses. The platform handles API authentication (API keys), rate limiting, request validation, and response formatting. No manual API server setup or deployment is required.

Clevis provides built-in user authentication for published workflows, supporting email/password signup, API key authentication, and optional OAuth integration. Creators can restrict workflow access to authenticated users only, track usage per user, and manage user quotas (e.g., 100 API calls/month per free user). The platform handles session management, password hashing, and token generation internally.

Clevis logs workflow executions with timestamps, input/output data, and execution duration. When workflows fail, the platform captures error messages and the node where failure occurred. Creators can view execution history in a dashboard, filter by date/status, and export logs for debugging. However, logs lack granular node-level tracing and stack traces.

Clevis supports conditional nodes that evaluate expressions (e.g., 'if user_input contains keyword') and route workflow execution to different branches. Users can chain conditions to create complex decision trees without code. The platform evaluates conditions at runtime and executes only the relevant branch, skipping unnecessary API calls and reducing costs.

Clevis includes HTTP request nodes that allow workflows to call external APIs (REST endpoints, webhooks) and process responses. Users configure request method (GET, POST, etc.), headers, authentication (API keys, OAuth), and request body without writing code. Responses are automatically parsed and available to downstream workflow steps.