web-ai-sdk: experimenting with browser-native AI APIs and WebMCP
The web-ai-sdk provides building blocks for utilizing the Web's native AI APIs. It is designed to be composable and requires no runtime dependencies, supporting Vanilla TypeScript and optional React hooks. The SDK includes various packages for prompts, summarization, translation, and detection, with browser support primarily for Chrome and Edge.
- ▪The web-ai-sdk is built for the Web's built-in AI APIs and is composable.
- ▪It offers packages for prompts, summarization, translation, and detection, with lifecycle and streaming support.
- ▪Browser support is primarily for Chrome and Edge with built-in AI flags enabled.
2 outlets in our directory ran this story, first to last over 15 hours. All of the coverage we found sits in one bucket: centre. That one-sidedness is itself worth noticing.
Hacker News (AI / LLM) files mainly under ai. We currently carry 4,376 of its stories.
Story provenance
Source · retrieval · rights · ranking — open for full record
inspect →
Story provenance
Attribution is not the same as permission. This drawer separates discovery metadata, excerpts, WeSearch-generated summaries, reuse status, and whether the publisher receives the visit. Nothing here claims a legal grant the publisher has not made.
Record
| Original publisher | web-ai-sdk |
| Canonical URL | https://web-ai-sdk.dev/ |
| Publication time | Thu, 21 May 2026 21:27:29 +0000 |
| Retrieval time | 2026-05-21T21:31:35.756Z |
| Last seen | 2026-05-21T21:31:35.756Z |
| Headline source | Publisher (no WeSearch rewrite) |
| Excerpt source | publisher body |
| Excerpt method | First ~120 words (~800 chars) of extracted publisher body, fair-use limited. |
| Summary | WeSearch · cerebras-chat (WeSearch summarizer) |
| Summary source text | contentText |
| Citation coverage | Summary is a WeSearch-generated derivative; primary citation is the original publisher URL. |
| Cluster | IQRO-GvGne1A · 2 stories |
| Cluster logic | Grouped by semantic title/content similarity across sources within a rolling window. Same-publisher template collisions are excluded from coverage comparison. |
| Ranking reason | Story pages are not engagement-ranked. Hub feeds use recency, with optional source-diversified chronological ordering (cap consecutive stories per source). No personalized ranking. |
| Publisher visit | Yes — open original |
| Substitutes article? | No — link-out required for full text |
Rights status (four layers)
WeSearch handling by dimension
| Indexing | May the item be indexed (stored, ranked, made findable)? | Allowed |
| Snippet | May a short excerpt of the publisher's text be shown? | Allowed |
| AI summary | May WeSearch generate its own short summary of the article? | Limited |
| Retrieval / RAG | May the content be exposed for third-party retrieval-augmented generation? | Not asserted |
| Model training | May the content be used to train AI models? | Not asserted |
| Commercial reuse | May the content be reused commercially? | Not permitted |
Basis: Derived from the published RSS/Atom feed. Contact: [email protected]. Reviewed: 2026-07-24.
Opening excerpt (first ~120 words) tap to expand
web-ai-sdk Building blocks for the Web's built-in AI APIs. Composable. No runtime deps. Just lifecycle, streaming, AbortSignals. Vanilla TypeScript by default, with optional React hooks. Install npm i @web-ai-sdk/all # all five wrappers npm i @web-ai-sdk/prompt # one wrapper at a time Packages Package Guide React hook @web-ai-sdk/all Meta-package— @web-ai-sdk/prompt Prompt usePrompt · useSession @web-ai-sdk/webmcp WebMCP useWebMCP @web-ai-sdk/summarizer Summarizer useSummarizer @web-ai-sdk/translator Translator useTranslator @web-ai-sdk/detector Detector useDetector Browser support Chrome and Edge 138+ with the Built-in AI flags enabled. See the support matrix for the per-API breakdown. Links Documentation — Starlight site with guides, React hooks, browser support.
…
Excerpt limited to ~120 words for fair-use compliance. The full article is at web-ai-sdk.
Discussion
0 commentsMore from web-ai-sdk
