Releasesby GlyphIntroducing Agent Plugins 1.0.0
Agent Plugins 1.0.0 is now available. It is an open, vendor-neutral standard for packaging Agent Skills and MCP servers into portable plugins. Compatible agent clients can discover and load them. Agent Plugins defines a common format: a root plugin.json manifest, plus fixed locations for portable components.
Also shipped Aug 6, 2026Vercel in August 2026 →
Automations in Snowflake CoWork (Public Preview)
Automations in Snowflake CoWork are now in Public Preview. An automation turns a one-time report into a recurring one: Snowflake CoWork re-runs your question with fresh data on the schedule you choose and emails you the results, including a summary and key metrics, along with a link that opens the full report so you can ask follow-up questions.
JAR tasks on serverless compute are now generally available
Package Scala or Java code as a JAR and run it as a task in a Lakeflow Job on serverless compute. Your JAR must match the Scala, Java Development Kit (JDK), and Databricks Connect versions of your serverless environment version. See Create and run JARs on serverless compute .
Databricks-managed MCP connectors are now integrated with Unity Gateway (Beta)
All Databricks-managed MCP connectors for Genie One and Genie Code have migrated to the Unity Gateway . This brings Databricks-managed connectors under Unity Gateway, enabling centralized governance, access controls, and visibility alongside your other MCP servers and tools.
JAR tasks on serverless compute are now generally available
Package Scala or Java code as a JAR and run it as a task in a Lakeflow Job on serverless compute, without provisioning or managing clusters. See Create and run JARs on serverless compute .
Genie Code web search is in Beta
Genie Code can now search the public web to answer questions that need current information. Web search is disabled by default during the beta for eligible workspaces and must be turned on from the Previews page. See Search the web .
Genie Agents enhancements and bug fixes
- Markdown tables in Agent mode APIs (Beta) : In the Agent mode APIs, table visualizations now return as markdown instead of table visualization attachments, which improves readability. See the Agent mode API reference .
More from AI SDK and AI GatewayEvery AI SDK and AI Gateway release →
Give every agent in Herdr its own Vercel Sandbox
Terminal coding agents like Claude Code, Codex, and OpenCode can now each run in their own isolated Vercel Sandbox , orchestrated from Herdr , a tmux-style manager that runs them side by side in panes. Nothing an agent runs or edits touches your machine.
Seedance 2.5 now available on Vercel AI Gateway
Seedance 2.5 from ByteDance is now available on AI Gateway. It can generate up to 30-second clips with synchronized audio, and takes up to 50 reference inputs in one request, spanning images, video, audio, and style.
Ling 3.0 Tiny is now available on AI Gateway
Ling 3.0 Tiny from ANT Group is now on AI Gateway, free to use till 8:00am PT on 8/14. Ling 3.0 Tiny takes the free slot from Ling 3.0 Flash . Ling 3.0 Tiny is a MOE model with 7.9B total parameters and about 1.3B active per token, a 256K token context window, and up to 32K output tokens.
Pause workflows for approval with Chat SDK
You can build human-in-the-loop approvals with Chat SDK through the new chat/workflow subpath. One requestApproval call posts a card with Approve and Deny buttons and suspends a Workflow SDK workflow until someone decides. The wait can last seconds or days and survives deploys and restarts.
Vercel AI Gateway and Vercel Sandbox now available on Hermes Agent
Hermes Agent can now use Vercel AI Gateway as its inference layer and run its agent commands in an isolated Vercel Sandbox microVM. Access 200+ models through AI Gateway at no markup on tokens, and every request appears in your AI Gateway dashboard with the rest of your usage and spend.
Export AI Gateway traces with Vercel Drains
AI Gateway now produces an OpenTelemetry trace for every request. Pro and Enterprise teams can send these traces through Vercel Drains to any OTLP/HTTP-compatible endpoint, including native integrations for Braintrust, Dash0, Kubiks, Sentry, and Statsig.
AI Gateway is now available on AWS Marketplace
AI Gateway is available on AWS Marketplace . Teams can procure AI Gateway through their existing AWS account, consolidating inference spend onto their AWS bill and streamlining procurement. Purchases are available as private offers with annual contract terms, plus usage-based pricing beyond the contract.
iMessage support for eve agents
eve agents can now connect to iMessage through the new Photon channel . The channel keeps each iMessage conversation in one eve session, verifies incoming webhooks, and marks accepted messages as read. If more messages arrive while the agent is replying, they steer the in-progress reply instead of each getting a separate answer.