AI Agent News
Read as

Sunday, October 11Frameworks

Google releases ADK for Kotlin 1.0 for building production AI agents

Google has released version 1.0 of the Agent Development Kit (ADK) for Kotlin, generally available now. The release reaches feature parity with ADK 1.0 Core and adds Android-first, on-device extensions.

Read the story23:43 UTC

Today

10 stories so far, newest first

Google Cloud API Gateway can now serve REST APIs as MCP tools

Google Cloud API Gateway is in Public Preview as a remote MCP server, letting existing REST operations be exposed to agents without a separate server. Developers opt in by annotating their OpenAPI 3.x spec and deploying the gateway, which then serves MCP at the /mcp path.

developers.googleblog.com/turn-your-rest-apis-into-mcp-tools-with-google-cloud-api-gateway

Google launches Agent Anomaly Detection in private preview on Gemini Enterprise Agent Platform

Google has put Agent Anomaly Detection into Private Preview on its Gemini Enterprise Agent Platform, a reasoning-based layer that audits what deployed agents do during a session. The tool flags behavioral anomalies, suspicious intent and policy violations without adding runtime latency.

developers.googleblog.com/agent-anomaly-detection-now-in-private-preview-on-the-gemini-enterprise-agent-platform

Google and Speakeasy open source OpenAPI client generator suite

Google and Speakeasy have released Speakeasy's OpenAPI client generator suite as open source under the AGPLv3 license. The suite generates SDKs, standalone agent-friendly CLIs and MCP servers from OpenAPI specs, following a shutdown that forced Google to rework its own SDK pipeline.

developers.googleblog.com/why-client-sdk-generation-belongs-in-the-open

Google releases AQuA, an ambient quality agent that diagnoses production agent failures

Google has released AQuA (Ambient Quality Agent), an open set of building blocks that runs beside a deployed agent in the user's own Google Cloud project and sweeps production sessions for recurring failures. It groups findings into verified insights and can trigger root-cause analysis that cites lines in the deployed source snapshot.

developers.googleblog.com/the-outer-loop-insights-first-an-ambient-quality-agent-that-diagnoses-your-production-agent

TypeSafe AI raises $870M at $7.5B valuation for non-text model Jev

TypeSafe AI has raised $870 million at a $7.5 billion valuation, with Andreessen Horowitz leading the round. The company's Jev model, released September 15, is not a large language model and produces probabilities rather than text.

techcrunch.com/2026/10/09/the-maker-of-non-text-ai-model-jev-valued-at-7-5b-just-weeks-after-launch

Lune launches search engine for scientific AI agents

Lune, a Product Hunt launch, is a search and grounding service that connects AI agents to research papers from top-tier academic conferences. It works as a connector for ChatGPT, Claude and other MCP-compatible apps.

www.producthunt.com/products/lune-research