
by Reducto
Reducto is a document processing platform with APIs to classify, parse, extract, split and edit documents. It turns files such as PDFs and scans into LLM-ready text and structured JSON.
APIUsage-based
Step 1: Sign up at Studio and create an API key.
Step 2: Install an SDK or the CLI, set REDUCTO_API_KEY, and parse a sample PDF.
Step 3: Or in Studio, create an Extract pipeline, upload a document and generate a JSON schema.
Step 4: Run the pipeline and compare the results with the original document, using citations to check sources.
Step 5: Click Deploy to get a code snippet and call the pipeline by its Pipeline ID.
Step 6: For agents, install the MCP server and call its parse tool on a document URL.
It supports 30+ file types, including PDFs, images, spreadsheets, presentations and scanned documents.
Yes. Studio lets you build, test and deploy document workflows in the browser, then call them from code with a Pipeline ID.
It is SOC 2 Type II audited and offers a signed HIPAA BAA, with Zero Data Retention that deletes documents within 24 hours. Data is encrypted at rest and in transit, with EU data residency, and deployment options include SaaS, hybrid VPC, full VPC and air-gapped on-premises.
Yes. It offers an MCP server, a CLI and SDKs, and the docs include an agent guide.
Ocean ProtocolOcean Protocol is an open-source, decentralized stack for sharing, selling and computing on data and AI models while the data owner keeps control. It is for data owners, data scientists and developers building data and AI applications on Web3.
MemoriMemori is a memory layer for AI agents that stores and recalls facts from conversations and agent actions. It ships Python and TypeScript SDKs, a cloud service and an MCP endpoint.