Releasesby GlyphDigitalOcean Harness Runtime can start a sandbox with no harness in it
DigitalOcean Harness Runtime can start a sandbox with no harness in it. Set harness: none in the environment spec, and the session boots the base image with a general-purpose toolchain and nothing running. You run commands with doctl …
Also shipped Oct 26, 2026DigitalOcean in October 2026 →
Conversation logging for Conversational analytics in BigQuery is generally available
BigQuery now supports logging data agent conversations directly to a BigQuery table within the agent's project.
Improved Lakeflow Performance Observability will soon be available by default for workspaces with the compliance security profile enabled
Databricks is enabling improved Lakeflow performance observability by default for workspaces with the compliance security profile.
Looker (Google Cloud core) data lineage is generally available
Data lineage for Looker (Google Cloud core) is now generally available, providing end-to-end visibility for LookML dashboards and Conversational Analytics agents.
BigQuery Python user-defined functions support volume mounts in preview
Python user-defined functions in BigQuery now support volume mounts, allowing users to access dependency files directly from Cloud Storage.
QuickBooks connector is available in Beta
The managed QuickBooks connector is now available in beta, enabling incremental ingestion of accounting data into Databricks.
Looker-managed Model Context Protocol (MCP) server is generally available
The Looker-managed MCP server is now generally available, allowing AI agents to interact with business data and LookML models without middleware.
More from DigitalOceanEvery DigitalOcean release →
DigitalOcean deprecates several OpenAI models
DigitalOcean has deprecated the o1, o3-mini, and GPT Image 1 models, recommending migration to GPT-5.6 Sol and GPT Image 2.
DigitalOcean Harness Runtime platform templates rebuilt for security
DigitalOcean has rebuilt Harness Runtime platform templates to address a remote code execution vulnerability in the Brotli decoder.
DigitalOcean Cost Analysis adds grouping and filtering by model and token usage
The Cost Analysis page in DigitalOcean now allows users to group and filter spend by project, tag, model, token type, and model access key.
MiniMax M3.1-Flash model is available in public preview on DigitalOcean
DigitalOcean has added the MiniMax M3.1-Flash model to its serverless inference platform in public preview.
DigitalOcean App Platform PHP buildpack update
DigitalOcean updated the PHP buildpack to version 298, adding support for multiple PHP versions including 8.5, 8.4, 8.3, and 8.2 releases.
The following DeepSeek model is now available on DigitalOcean Inference for serverless inference: DeepSeek...
The following DeepSeek model is now available on DigitalOcean Inference for serverless inference: DeepSeek V4.1 Flash 1017 For more information, see the Available Models page.
The following Reflection AI model is now available on DigitalOcean Inference for serverless inference: Beam...
The following Reflection AI model is now available on DigitalOcean Inference for serverless inference: Beam For more information, see the Available Models page.
The following NVIDIA model is now available on DigitalOcean Inference for serverless inference: NVIDIA...
The following NVIDIA model is now available on DigitalOcean Inference for serverless inference: NVIDIA Nemotron 3.5 Super VL For more information, see the Available Models page.