Data Engineering & Extraction
Browse data engineering & extraction products.
Cognee is an open-source agent-memory platform that turns connected data into graph, vector, and relational memory that agents can recall across sessions through one API.
Cynthia AI is an SDR agent that researches prospects, enriches leads, identifies decision-makers, drafts personalized outreach, follows up, and connects sales channels.
Data-to-Paper is an open-source multi-agent research framework that turns raw data into backward-traceable, human-verifiable scientific papers with optional human guidance.
Dot is an AI data analyst that answers questions in natural language, writes SQL, creates charts and deep analyses, automates reports, and governs business context across data systems.
Extruct AI is a company-research API that searches a curated index of 10 million companies and the live web, evaluates custom criteria, and returns sourced company data and matches.
Fira is an AI financial research analyst that searches public and private data, reads complex financial documents, performs calculations, cites exact evidence, and exports results to Excel.
Firecrawl is an open-source context API that lets applications and AI agents search, scrape, crawl, monitor, and interact with the live web as clean Markdown, structured JSON, screenshots, or metadata.
Foundry provides reproducible browser simulations, detailed evaluations, expert-created datasets, and reinforcement-learning environments for training and testing enterprise web agents.
Genesis Computing deploys enterprise AI data agents inside existing cloud and data stacks to research sources, build and test pipelines, document work, create pull requests, monitor jobs, and repair errors.
GPT Researcher is an open-source autonomous research agent that gathers multiple web and local sources, organizes cited evidence, creates long reports, supports different models and search engines, and exports common document and data formats.
HARPA AI is a page-aware browser agent for summarizing, writing, research, extraction, monitoring, and web automation with multiple cloud, API, web-session, or local AI models.
Haystack is an open-source Python framework for building production-ready AI agents, retrieval-augmented generation pipelines, context-engineered applications, and multimodal search systems.
Hume AI is an emotional-intelligence lab and voice AI toolkit offering speech models, expressive text-to-speech, speech-to-speech interaction, human-feedback evaluation, and curated multilingual voice datasets.
Humen is an AI outbound automation platform for early-stage startups that researches prospects, builds targeted lead lists, personalizes cold email, schedules sends, handles replies, and reports campaign performance.