Chat SDK brings agents to your users
Write once, deploy agents everywhere. Vercel's Chat SDK just killed the integration nightmare that's been slowing down AI adoption.
Why it matters
Vercel shipped Chat SDK, a developer tool that abstracts away messaging platform fragmentation (Slack, Teams, Discord, Telegram, WhatsApp, etc.), letting teams build AI agents once and deploy across all channels. This removes a major adoption friction point for enterprise AI workflows and signals the shift from model capability races to developer experience and deployment velocity.
The key facts
8 to knowChat SDK supports 8+ platforms: Slack, Microsoft Teams, Google Chat, Discord, Telegram, GitHub, Linear, WhatsApp
Open source, public beta as of March 2026
Handles platform-specific rendering (streaming, tables, cards, markdown conversion) in adapter layer
PostgreSQL state persistence now production-ready alongside Redis/ioredis
WhatsApp adapter supports auto-chunking, multi-media downloads, location sharing, 24-hour messaging window constraint
Write-once JSX model for UI components across all platforms
Automatic context enrichment: link previews, referenced posts, images in agent prompts
Real-time markdown-to-native conversion (e.g., Slack Block Kit, Teams GFM, Telegram code blocks)
Go to the source
Vercel Blogvercel.com
Publisher excerpt: In early March, we gave the entire organization a challenge: figure out how to multiply your output. People created agents. Mostly chat bots, but dedicated ones, purpose-built for real workflow augmentation: the agents were doing things automatically that would otherwise be tedious and time…