BetaWeekly digests are a beta — we're trying something new. Feedback welcome.
Browser Automation & Scraping weekly digests
- Week of November 2, 2026Agent data gets deeper while agent reach gets governed
Firecrawl expanded its Alexandria corpus to SEC filings, life sciences research, and election records—each readable directly inside ChatGPT and Claude—while Browserbase introduced Navigation Policies to control which sites browser agents can reach and Apify hardened its SDK against restarts.
- Week of October 26, 2026Firecrawl turns Alexandria into a data marketplace while Browserbase unlocks logged-in pages
Firecrawl spent the week turning Alexandria into something agents can shop in — recruiting shortlists, dependency vulnerability checks, and a hook into Vercel's eve framework — while Browserbase made Fetch able to read pages behind a login and Apify hardened its child-run orchestration.
- Week of October 19, 2026Agents get safer sign-ins and a legal database of their own
Browserbase shipped 1Password-backed agentic autofill so agents can log in without ever seeing a password, while Firecrawl opened a free Government & Legal Index spanning 30 million US government pages. Stagehand also gained official OpenAI and Anthropic SDK integrations and a set of browser-automation fixes.
- Week of October 12, 2026Firecrawl turns the web into research fuel for AI agents
Firecrawl shipped two curated data providers into its Alexandria platform — a funding dataset and a marketing intelligence pack — while Browserbase opened its Search API to Parallel's fast and deep-research modes.
- Week of October 5, 2026Firecrawl opens its scrapers to files and third-party data feeds
Firecrawl turned /scrape into a single front door for web pages, documents, and external provider data, while Apify primed its Python SDK and Crawlee for a 4.x transition.
- Week of September 28, 2026Agents get richer data sources as Firecrawl pushes Alexandria everywhere
Firecrawl opened its Alexandria data layer to people-and-company enrichment and brought it inside ChatGPT and Codex, while Crawlee hardened its browser pool against hanging page closes and task-context leaks.
- Week of August 3, 2026Hardening the foundations: stability fixes across browser automation
Apify and Browserbase shipped stability-focused patches this week, closing shutdown races and turning cryptic daemon errors into actionable commands. Crawlee relaxed click option handling for more flexible link enqueuing.
- Week of June 15, 2026Firecrawl edges out Browserbase's WebMCP in a week of agent-first tooling
Firecrawl launched a specialized Research Index for AI/ML literature search that sets a new benchmark for recall, while Browserbase's Stagehand shipped WebMCP support, letting pages expose typed tools directly to agents.
- Week of June 1, 2026Stagehand puts vision into extract and lowers the barrier to local automation
Stagehand 3.5.0 ships a screenshot-aware extract mode for visual content, and the browse CLI now steers new users toward local-first automation. Meanwhile, Crawlee v3.17.0 hardens sitemap discovery and fixes a Puppeteer page-binding bug.
- Week of May 25, 2026Monitor-driven automation finds its footing
Firecrawl introduced a smart monitoring endpoint that cuts LLM token usage by up to 90%, while Stagehand added visual context to its extraction command and the Apify SDK patched a critical run-kwargs omission.
- Week of May 11, 2026Firecrawl parses documents, Stagehand slims context, replays go live
Firecrawl's v2.10 adds a document parsing endpoint and lockdown mode, Browserbase ships embeddable session replay streaming, and Stagehand 3.4 introduces `ignoreSelectors` to trim agent context bloat.