AI SDK now supports ACP-compatible harnesses via new package
The AI SDK harness layer now supports any Agent Client Protocol (ACP)-compatible harness through the new @ai-sdk/harness-acp package, enabling integration with harnesses that don't have direct adapters. This meta-adapter wraps the ACP protocol instead of specific runtimes, letting you build an adapter for any harness that ships an ACP-compatible package.
The now supports any Agent Client Protocol (ACP)-compatible harness with through the new package.AI SDK harness layerHarnessAgent@ai-sdk/harness-acp
Previously, every harness adapter wrapped one specific runtime (Claude Code, Codex, Pi, Deep Agents, OpenCode). wraps the protocol instead. It is a meta adapter: rather than adapting a single harness, it lets you build an adapter for any harness that ships an ACP-compatible package.@ai-sdk/harness-acp
Implement a harness by passing that package to and configure basic harness mapping.createACP
Then pass it to like any other harness:HarnessAgent
ACP is an abstraction over coding harnesses, but the AI SDK harness layer stays deliberately decoupled from it. Not every harness supports ACP, and for some, ACP limits or changes how well they expose their internal behaviors, so a direct adapter can produce a tighter integration.
For Claude Code and Codex, prefer the direct and adapters over an ACP-based implementation; reach for when a harness has no direct adapter but ships an ACP-compatible package.@ai-sdk/harness-claude-code@ai-sdk/harness-codex@ai-sdk/harness-acp
Read the to get started.ACP harness documentation
Source: original entry ↗
More from Vercel
Follow Vercel to get its new changes in your feed and email digest.
Updates to Hobby and Pro Terms of Service
Vercel is updating Terms of Service for Hobby and Pro customers effective October 19, 2026, clarifying credit policies, managed accounts, auto-renewal practices, and adding statutory cancellation and refund rights for UK and EU consumers, including protections for service changes with negative impact.
Mercury 3 now available on AI Gateway
Inception's Mercury 3 model is now available on Vercel's AI Gateway with 50% launch pricing and generation speeds exceeding 1,000 tokens per second. The model enables parallel text refinement with a 1M-token context window, ideal for real-time applications like browser agents and customer support.
MiniMax M3.1 Flash now available on AI Gateway for free
MiniMax M3.1 Flash, an open-weight multimodal model with 1M-token context window for coding and agentic work, is now available on Vercel's AI Gateway at no cost through October 20. The model excels at complex agent tasks, coding applications, and cybersecurity work, and can be used through multiple APIs and coding agents.