Releasesby GlyphDatabricks-provided MCP Services will GA soon
Databricks-provided MCP Services for SaaS applications such as Slack, GitHub, Atlassian, and Google Drive will soon be generally available, with both read and write operations enabled by default. Admins and users can disable MCP Services and individual tools in Unity Gateway . See Connect agents to tools with MCP Services .
Also shipped Jul 10, 2026Databricks in July 2026 →
Online Feature Store (Public Preview)
Online Feature Store is now available in public preview. Serve the latest feature values with low-latency online retrieval backed by Snowflake Postgres for real-time ML applications such as fraud detection, recommendations, and personalization.
Dreams research preview adds Claude Fable 5 and Claude Sonnet 5
Dreams, in research preview, now supports Claude Fable 5 and Claude Sonnet 5.
Agentic autofix for code scanning alerts in public preview
Agentic autofix is now in public preview for all code scanning alerts. It remediates alerts generated by CodeQL and third-party scanning tools by working across your codebase the way a developer would, it explores relevant files, proposes a fix, and reruns the original analysis to confirm the fix closes the alert before opening a pull request for your...
supabase-js will require TypeScript 5.0+ from January 31, 2027
@supabase/supabase-js will require TypeScript 5.0 starting January 31, 2027, dropping support for TypeScript 4.7 to 4.9.
Confluent Gateway 1.3.0 adds centralized governance enforcement (Early Access)
Gateway validates messages and enforces data governance with Schema Registry, with four policy types (schema ID, deep validation, field-level and full-payload encryption) and per-topic overrides. Docker only during EA.
You Don't Need a Vector Database, Postgres Already Has pgvector
Prisma 8 now provides type-safe support for pgvector, enabling semantic search directly within Postgres.
More from Agent Bricks and Mosaic AIEvery Agent Bricks and Mosaic AI release →
Protobuf tensor input for custom model serving endpoints (Public Preview)
For custom model serving endpoints with a tensor-based input signature, you can now send the request body as a serialized KServe v2 ModelInferRequest with Content-Type: application/x-protobuf , instead of JSON. This feature is in Public Preview and is only available on endpoints deployed after July 9, 2026. See Protobuf tensor input .
OpenAI GPT-5.6 Sol, GPT-5.6 Terra, and GPT-5.6 Luna now available as Databricks-hosted models
Model Serving now supports OpenAI GPT-5.6 Sol , GPT-5.6 Terra , and GPT-5.6 Luna as Databricks-hosted models. You can access these models using Foundation Model APIs pay-per-token . Customers are responsible for ensuring their compliance with applicable terms .
Google Gemini 2.5 Flash and Pro are scheduled for retirement
Google Gemini 2.5 Flash and Gemini 2.5 Pro will be retired on October 2, 2026. The recommended replacement models are Gemini 3.1 Pro or Gemini 3.5 Flash. See Deprecated and retired models for migration guidance.
Anthropic Claude Sonnet 4 is scheduled for retirement
Anthropic Claude Sonnet 4 will be retired on October 9, 2026. Claude Sonnet 4.6 is the recommended replacement. See Deprecated and retired models for migration guidance.
Restrict access to AI Functions with Unity Catalog permissions (Public Preview)
You can now use Unity Catalog permissions to restrict which task-specific AI Functions your organization can access, independent of foundation model access. Contact your account team to enable this feature. See AI Functions Unity Catalog permissions .
MLflow trace storage in Unity Catalog will soon be available by default for workspaces with the compliance security profile enabled
MLflow trace storage in Unity Catalog tables will be available by default for workspaces with the compliance security profile enabled in mid-August 2026. Store MLflow traces in Unity Catalog tables for scalable, governed trace storage: storage is unlimited, traces are stored in OpenTelemetry (OTel) format, access is governed through Unity Catalog schema and...
MLflow trace storage in Unity Catalog is now generally available
MLflow trace storage in Unity Catalog tables is now generally available. Databricks recommends storing traces in Unity Catalog for new and production workloads: storage is unlimited, traces are stored in OpenTelemetry (OTel) format, access is governed through Unity Catalog schema and table permissions, and you can query traces with SQL, Genie, AI/BI...
Google Gemini 3 Pro is retired
Google Gemini 3 Pro is retired. Gemini 3.1 Pro is the recommended replacement. See Deprecated and retired models for migration guidance.