About
Exabase is a data layer for AI agents. It handles memory, search, file storage, extraction, and isolated workspaces through a single API, so the team building the agent does not have to build the infrastructure underneath it.
The memory engine, M-1, holds state-of-the-art results on both LongMemEval and BEAM at every evaluated scale. It extracts structured facts from conversations, resolves contradictions as they arise, tracks how information changes over time, and retrieves using multiple signals rather than similarity alone. The cognitive science behind the architecture is documented in the research.
Deep Search is hybrid semantic and keyword search with temporal weighting, reranking, and sub-document precision. Text, PDFs, images, audio, and video are all searchable through the same endpoint, with results returned at the paragraph, timestamp, or region level rather than the document level.
Extract processes PDFs, images, audio, video, and web pages into structured JSON or markdown. Common document types like invoices and contracts return typed fields automatically. Every file is indexed at write time and immediately searchable through Deep Search.
Resources is the file storage layer. Upload a file and it is extracted, chunked, embedded, and indexed without a pipeline to build. Bases are isolated cloud filesystem instances for multi-tenant or team-scoped workloads, with snapshot rollback for version control. Workers handle scheduled maintenance, enrichment, and automation tasks in the background.
The platform is model-agnostic and framework-agnostic. It works via REST API, Python and JavaScript SDKs, and MCP support for Claude, Cursor, and Windsurf. There is a free tier and a Scale plan at $149 per month.