Libraries tagged by AI base

Base classes which can be used to build an api-client.

Go to Download

Augments HTTP 500 errors with AI-based exception analysis using Symfony AI

Go to Download

# Introduction **INDA (INtelligent Data Analysis)** is an [Intervieweb](https://www.intervieweb.it/hrm/) AI solution provided as a RESTful API. The INDA pricing model is *credits-based*, which means that a certain number of credits is associated to each API request. Hence, users have to purchase a certain amount of credits (established according to their needs) which will be reduced at each API call. INDA accepts and processes a user's request only if their credits quota is grater than - or, at least, equal to - the number of credits required by that request. To obtain further details on the pricing, please visit our [site](https://inda.ai) or contact us. INDA HR embraces a wide range of functionalities to manage the main elements of a recruitment process: + [**candidate**](https://api.inda.ai/hr/docs/v2/#tag/Resume-Management) (hereafter also referred to as **resume** or **applicant**), or rather a person looking for a job; + [**job advertisement**](https://api.inda.ai/hr/docs/v2/#tag/JobAd-Management) (hereafter also referred to as **job ad**), which is a document that collects all the main information and details about a job vacancy; + [**application**](https://api.inda.ai/hr/docs/v2/#tag/Application-Management), that binds candidates to job ads; it is generated whenever a candidate applies for a job. Each of them has a specific set of methods that grants users the ability to create, read, update and delete the relative documents, plus some special features based on AI approaches (such as *document parsing* or *semantic search*). They can be explored in their respective sections. Data about the listed document types can be enriched by connecting them to other INDA supported entities, such as [**companies**](https://api.inda.ai/hr/docs/v2/#tag/Company-Management) and [**universities**](https://api.inda.ai/hr/docs/v2/#tag/Universities), so that recruiters may get a better and more detailed idea on the candidates' experiences and acquired skills. All the functionalities mentioned above are meant to help recruiters during the talent acquisition process, by exploiting the power of AI systems. Among the advantages a recruiter has by using this kind of systems, tackling the bias problem is surely one of the most relevant. Bias in recruitment is a serious issue that affect both recruiters and candidates, since it may cause wrong hiring decisions. As we care a lot about this problem, we are constantly working on reduce the bias in original data so that INDA results may be as fair as possible. As of now, in order to tackle the bias issue, INDA automatically ignores specific fields (such as name, gender, age and nationality) during the initial processing of each candidate data. Furthermore, we decided to let users collect data of various types, including personal or sensitive details, but we do not allow their usage if it is different from statistical purposes; our aim is to discourage recruiters from focusing on candidates' personal information, and to put their attention on the candidate's skills and abilities. We want to help recruiters to prevent any kind of bias while searching for the most valuable candidates they really need. The following documentation is addressed both to developers, in order to provide all technical details for INDA integration, and to managers, to guide them in the exploration of the implementation possibilities. The host of the API is [https://api.inda.ai/hr/v2/](https://api.inda.ai/hr/v2/). We recommend to check the API version and build (displayed near the documentation title). You can contact us at [email protected] in case of problems, suggestions, or particular needs. The search panel on the left can be used to navigate through the documentation and provides an overview of the API structure. On the right, you can find (*i*) the url of the method, (*ii*) an example of request body (if present), and (*iii*) an example of response for each response code. Finally, in the central section of each API method, you can find (*i*) a general description of the purpose of the method, (*ii*) details on parameters and request body schema (if present), and (*iii*) details on response schema, error models, and error codes.

Go to Download

Base recipe for Varbase AI Figma (vartheme_bs5 / Bootstrap 5.3) - applies Varbase AI Base, installs ai_figma + varbase_ai_figma, Context Control Center, and the targeted Figma AI Context items, and wires the Figma tools into the Drupal Canvas AI Orchestrator.

Go to Download

Smart AI-based text-checking package

Go to Download

Base classes for Yii2 DNK flow architecture.

Go to Download

An interactive, terminal-based AI coding assistant for Laravel — a Claude Code native to your Laravel app.

Go to Download

Laravel-based autonomous AI agent platform with cyclic thinking, persistent memory and real-time code execution

Go to Download

Store machine, human, and source assertions as append-only claims with confidence, basis, and provenance.

Go to Download

AI Universe is the shared AI foundation layer for TYPO3 extensions. It centralizes AI provider communication, model selection, request handling, statistics preparation, and utility functions so other extensions can build AI features faster and with consistent behavior.

Go to Download

MCP (Streamable HTTP) scaffolding for Laravel apps — AgentTool base class, bearer + OAuth 2.1 (Passport) auth with RFC 7591 Dynamic Client Registration, tool registry, audit log subscriber.

Go to Download

The initial composer file to start a new project via Aion Starter Kit. This file will be re-populated based on the starter kit variant.

Go to Download

The Agent-Friendly CMS — a lightweight, flat-file Content Management System with block-based content rendering

Go to Download

Self-hosted LLM assistant for Semitexa Framework — console-based skill execution

Go to Download

Keeps a curated PHP config catalog of your Eloquent models in sync with the real code, using an LLM-assisted analyze/apply workflow (git-diff-based change detection, reflection-first structural facts, human-in-the-loop review before writing).

Go to Download