integration

Vercel announces that Hermes Agent can now run using Vercel AI Gateway for model inference with observability and Vercel Sandbox for isolated microVM execution.

TotalSegmentator now has an MCP server, enabling AI agents like Codex to run it and answer clinical questions about CT scans, e.g., detecting hepatosplenomegaly or NAFLD/NASH.

vast.ai now supports Hugging Face Storage Buckets as a cloud connection, allowing rented GPU instances to pull datasets and checkpoints directly from HF buckets and push results back without manual transfers.

Actual, a local inference stack with low CPU impact, now natively supports Hermes Agent by NousResearch, letting users leverage personal inference capacity from anywhere.

Hugging Face announces Baseten as a supported Inference Provider, enabling serverless access to popular open-weight LLMs like Kimi K3, DeepSeek V4 Flash, and GLM-5.2 directly from model pages and SDKs.

Tavily announces an isolated Convex component that adds real-time web search and content extraction to reactive applications and AI agents built with Convex.

An engineer reflects on repeatedly building webhook integration systems, detailing the hidden complexity of signature verification, deduplication, buffering, and reconciliation crons, and argues that webhook notifications are not a reliable substitute for a complete ordered data log.

Dover MCP lets you run your hiring process directly from Claude or ChatGPT, integrating AI assistants with recruitment workflows.

Google Health's 5.05 update finally lets Fitbit users sync workouts, steps, and vitals directly to Apple Health, eliminating the need for third-party workarounds. The update also introduces Smart Health Links for sharing medical records in the US.

A tweet highlights that connecting a Claude Connector (e.g., Gmail, calendar, Slack) also enables Claude Code to use those integrations, including within Artifacts.

Tavily announces the official opencode-tavily plugin, allowing OpenCode agents to use Tavily's web search, content extraction, crawling, URL discovery, and deep research with citations.

Airtable and OpenAI have partnered to integrate Airtable directly into ChatGPT, enabling users to connect databases, generate tables, and manage data within the chat interface.

SyncStaq keeps Stripe billing data always current in Google Sheets with automated syncing.

Hermes Agent now integrates with Buzz, Block's open-source, self-hostable Nostr-based workspace, enabling humans and AI agents to collaborate in shared channels. The integration offers three deployment modes: Buzz Desktop managed runtime, a relay bridge via ACP, and a native Hermes Gateway platform.

Pioneer now has a native integration with OpenCode, allowing users to select it as a provider in the UI.

Grok 4.5, the latest AI model from xAI, is now available in GitHub Copilot, allowing users to select it for high-speed frontier intelligence.

Mach 1 built an AI agent platform that uses Zapier MCP to connect to 25 companies' diverse tool stacks, completing over 150k tasks across internal workflows and customer operations.

Grok now supports multiple languages and is more deeply integrated into Tesla vehicles, including Spotify control.

VLC for Unity now supports Linux, allowing developers to integrate video playback into Unity projects on the Linux platform.

Enter Pro Agent Builder by Converge AI lets you build custom AI agents using natural language, then deploy them as webpages, embeds, SDKs, or bots, with version control and rollback.