Agent SDKs

Vercel's AI SDK harness now runs fx through the same HarnessAgent API used for other coding agents, reducing the need for another bespoke integration.

Agentic checkout spans product feeds, tool discovery, checkout state, and delegated payment authority. Builders need protocol-specific adapters and evals because ACP and UCP have not converged.

Vercel’s AI SDK can now run Cursor behind the same HarnessAgent interface as seven other coding agents, reducing application changes when swapping harnesses.

Gemini 3.5 Transcribe adds batch and live WebSocket transcription to AI Gateway, with automatic language detection, 85+ languages, and custom vocabulary.

Run SDK executes agent-generated JavaScript or TypeScript behind narrow host functions, with resumable approval and auth boundaries instead of application-level eval access.

Warp’s cloud-agent design separates runtime, harness, artifacts, and orchestration so teams can swap tools without fragmenting workflows or removing human review.

MidTool trains general tool use before post-training, using API, MCP, document, web, PDF, and code data. Qwen3 4B and 8B variants improved across three downstream tool-use benchmarks.

Chat SDK now supports Instagram bots for DMs, media, reactions, story replies, and interactive cards, with buffered streaming and Meta’s 24-hour reply window.

Vercel AI Gateway added four Fish Audio models for speech generation and transcription, with AI SDK 7 support and a free window whose model naming determines later billing.

Vercel’s AI SDK harness now runs Cline behind the same interface as six other coding-agent runtimes, while keeping Cline in the host and sandboxing only its tools.

OpenAI’s GPT-5.6 guide focuses on model selection and Responses API features for building agents with lower development and operating costs.

A new ACP meta-adapter lets HarnessAgent run compatible runtimes that lack dedicated integrations. Keep direct Claude Code and Codex adapters where tighter behavior matters.

Grok Build now plugs into AI SDK’s common HarnessAgent interface, letting agent applications add or swap this runtime without rewriting their orchestration code.

AI Gateway now exposes Exa search as a keyless tool for any gateway model, and eve uses it by default. The free period ends August 31, so keep cost assumptions temporary.

Vercel AI Gateway now exposes xAI’s image model through the AI SDK, including 1K/2K generation, batches, and targeted edits that aim to preserve untouched details.

Seedance 2.5 adds multimodal video generation and local edits to AI Gateway, with clips up to 30 seconds and separate image and video references.

Chat SDK can pause a workflow for a verified human decision and resume after seconds or days, without a custom approvals table, action handler, or polling loop.

The generally available v0 API gives agents headless app generation with stateful chats, sandboxed execution, streamed traces, live previews, and one-call Vercel deployment.

Chat SDK’s Teams adapter adds reactions, user-only ephemeral messages, custom token supply, and routing fixes useful for building safer agent approval and progress flows.

Sandstone pairs composable agent workflows with preview deployments and private data connectivity, showing the infrastructure a small team used to operate enterprise legal automation.

Chat SDK can put Claude Managed Agents behind browser and messaging interfaces while Anthropic retains the loop, tools, session state, and research sandbox.

AI Gateway can now stream audio into transcription models and emit partial text, letting text-based agents accept lower-latency voice input without changing the agent itself.

Searchable says Vercel’s AI SDK and Gateway let it swap models without SDK or key changes, helping the team ship some customer requests in 30 minutes and move 2–5× faster.

PalmClaw runs the agent loop, memory, skills, and tools directly on a phone, exposing device capabilities as structured calls instead of GUI gestures. The paper reports faster, more reliable task execution.

Prime Intellect is centering eval, data generation, and RL on composable environments, with an endpoint interceptor that lets existing coding-agent harnesses participate without rewrites.

Chat SDK now targets X alongside six other channels from one bot codebase, handling webhook verification and OAuth refresh while accepting no streaming and likes-only reactions.

eve’s Chat SDK channel lets one agent span messaging adapters while retaining threads, approval cards, proactive sends, webhook handling, and overridable defaults.

Alibaba's page-agent is an MIT-licensed JS library that embeds a natural-language GUI agent in any webpage via one script tag. It drives the DOM as text — no extension, headless browser, or multimodal model needed.

GitHub now exposes the Copilot CLI agent runtime as SDKs for six languages, including planning, tools, and file edits. Builders can embed it with configurable permissions, auth, models, and BYOK.

Notion used the Cursor SDK to embed coding agents in a few weeks: users tag Cursor in docs or assign it issues, and it plans, codes, tests, and opens PRs. A pattern for embedding agents in your own product.

A TypeScript agent stack can share types and schemas across the loop, tools, backend and UI, reducing service-boundary contracts. Keep Python where training and model serving require it.

Project Nanda proposes open discovery, identity and coordination layers for agents across vendors. Its local simulator lets builders test one protocol layer without building the entire network.