Browserbase
Session replays can now be embedded in your product and streamed to end users within seconds of a session ending.1
Fetch API now returns markdown and JSON — the Fetch API, originally launched for sessionless page retrieval at ~$1/1,000 pages, now returns content as markdown or structured JSON. The data cap rose from 1MB to 5MB, and extract pricing landed at $4/1,000 pages ($7 with proxies).2 Use it when a full browser session isn't warranted.
Session replay streaming — embed an HLS-compatible replay in your own product by fetching a .m3u8 playlist from the API and handing it to any player. Browserbase handles storage, fMP4 encoding, and CDN delivery; end users stream segments directly.3
Stagehand agent reliability — Stagehand 3.3.0 introduced verified mode for improved agent identity on sites that gate bot traffic.4 Claude CUA now scales extended-thinking budget to match task complexity, and extract() uses strict JSON schema enforcement to eliminate malformed responses.5
observe() and extract() noise filtering — ignoreSelectors, available since Stagehand 3.4, lets agents skip ads, navbars, modals, and other irrelevant elements during both observation and extraction passes without re-tuning prompts.6 Stagehand 3.7.0 added a screenshot option to extract() and introduced an evaluator backend for recording and assessing agent trajectories.7
Downloads API — every file an agent downloads is now individually addressable with its own ID and metadata.8 Filter by filename, MIME type, size, or timestamp; fetch a single file or just its metadata. Existing session-level zip endpoints continue to work with no migration required.
Model Gateway and deprecations — passing a Browserbase API key now routes Stagehand through OpenAI, Anthropic, or Gemini at list price with no extra accounts.9 projectId was deprecated in v3.6.5; only BROWSERBASE_API_KEY is required to start a session.10