DigitalOcean Agent Data Services

DigitalOcean's managed data layer for agents: ingestion flows, a catalog with vectors, and SQL or vector query, in private preview.

DigitalOcean · Data, training, and fine-tuning platforms (datasets, labeling, RAG/vector DBs, fine-tuning-as-a-service) · product

Published in Feed

Overview

DigitalOcean announced Agent Data Services on October 12, 2026 as a managed data layer for AI agents. Managed Data Flows process, vector-index and enrich incoming data, including documents, images, audio, video and agent execution traces; a Data Catalog stores structured records and vectors together with lineage to the source; and data can be queried by SQL, vector search or API. It is private preview for accepted participants, offered as-is with no SLA and outside DigitalOcean's standard compliance certifications.

This is a sourced directory entry. Features and capabilities are reported in the linked sources; this entry does not document independent Aymorphic testing.

Key features

  • Managed Data Flows for behavioral (logs, traces) and multimodal data
  • Data Catalog storing records and vectors with source lineage
  • SQL, vector search and API query access
  • Per-workspace scoped access, roles, API tokens and audit logging
  • Integrates with Managed Agents, Serverless Inference, Spaces and Agent Learning Services

Use cases

  • Turning agent traces into queryable sessions
  • Indexing multimodal documents for agent retrieval without running pipelines

Pricing

Private preview; pricing is in development and not published.

Pricing reflects the source record and may change. Confirm current terms with the provider.

Dates and sources

Released
12 Oct 2026
Record updated
15 Oct 2026
Record last checked
15 Oct 2026

Explore the Feed

Other entries filed under data, training, and fine-tuning platforms (datasets, labeling, rag/vector dbs, fine-tuning-as-a-service); inclusion does not imply equivalent features.

  • pplx-embed-v2-late

    Perplexity's late-interaction multimodal embedding models (0.6B and 9B) with 128-dim per-token vectors, open on Hugging Face.

  • EmbeddingGemma 2

    Open-weight 740M-parameter multimodal embedding model built on Gemma 4 that encodes text, images, audio, and video for on-device search.

  • AutoSynthData

    ServiceNow CoreAI's framework that turns an enterprise agent's capability gaps into targeted synthetic training data.

Browse the Feed