1. Reducto: AI-powered document parsing with layout, table, formatting, and bounding-box preservation, Structured data extraction with schema-level precision and citations, Document splitting, classification, editing, intelligent chunking, OCR, and multilingual processing, Support for PDFs, images, spreadsheets, presentations, text documents, and 30+ file types, Enterprise deployment, security, compliance, and scalable processing infrastructure.
2. NaN: Shared dedicated GPU inference cluster for open AI models, OpenAI-compatible API with a personal API key, Zero logging of prompts and model responses, EU-based data processing, Access to language, embedding, reranking, TTS, and STT models, Private Discord community with events, workshops, and hackathons, Quarterly community voting on available models.
3. Agenty: AI-powered web scraping and structured data extraction, No-code point-and-click scraping agents, Website crawling with sitemap discovery, depth controls, and JavaScript rendering, Website change detection with content monitoring, screenshots, keyword tracking, and email alerts, Web Data Extraction API for JSON output, HTML-to-Markdown API for LLM-ready content, Website Screenshot API with full-page capture and mobile emulation, Scheduled scraping jobs and automated workflows, Proxy rotation, including data center, static, and residential proxies, Data export to JSON, CSV, and databases, API access and integrations, Data cleaning, validation, and transformation.
4. LangSearch: Web Search API supporting natural language search, Semantic Rerank API, Hybrid search database supporting mixed keyword and vector searches, LangSearch Ranker Model for improved search accuracy, Easy integration with LLM tools and AI agent plugins.
5. EvalMy.AI: Automated AI answer verification, C3-score metric (correctness, completeness, contradiction), REST API and Python library integration, Customizable Sem-Score parameters, Scalable cloud-based SaaS.