Search & Web Access

Parent: Agentic.

Search & Web Access covers crawlers, readers, and browser grids that let agents fetch live external knowledge. Under Agentic it feeds RAG and tool loops; it is not itself a vector index. The job is to turn URLs and search results into clean text (or structured extracts) with provenance.

Technically compare politeness/robots behavior, JS rendering, extraction quality, and rate limits. Failure modes: hallucinated “browse” without a fetch, scrapers that break ToS silently, and HTML dumps that poison chunking.

Members: Firecrawl, Crawl4AI, Jina Reader, Scrapling, and Selenium Grid 4 for heavier browser farms. Prefer reader APIs when you need clean article text; prefer crawl frameworks when you own site maps; prefer Selenium grids when interaction beyond GET is required.

Feature maps such as Browser & Computer Use, Citations, and Integrations & Tool Calling remind you: every fetch should be citable and attributable. Pair with RAG so pages become durable corpus, not one-shot context.

Inline members for audit: Crawl4AI Firecrawl Jina Reader Scrapling Selenium Grid 4. Features: Browser & Computer Use Citations Integrations & Tool Calling. Related terms referenced: RAG, Tool Integration, Coding Agents.

For this research catalog the acceptance test is boring and strict: after wiring the pack, can a second person replay the same scenario and get the same measurable outcome? If not, the page is still a brochure. Document the scenario, the expected number, and the log line that proves it. That habit is what separates a deepened taxonomy cell from a landscape screenshot.

Also record what you refused: tools not connected, corpora not ingested, metrics not collected. Refusals keep the cell honest when marketing pages claim universality. A taxonomy essay that only lists winners teaches less than one that names the skip conditions next to the install path.

Keep the essay technical enough that an engineer can argue install order — and short enough that a reader finishes it before opening the right-rail member list. Prefer primary docs and repo evidence over landscape blurbs when the right-rail packs disagree.

Operational discipline for this cell: name the install artifact, the health check, and the rollback. Prefer one golden path documented against a member pack in the right rail over five half-wired demos. When packs disagree, believe the primary repository README and a failing test you can re-run — not the landscape one-liner. Measure latency, cost, and error rate on a frozen scenario before declaring the subcategory “covered.” If you cannot point at a log line that proves the scenario, the essay is unfinished even when the word count clears the audit floor.

Cross-link greedily but honestly: every taxonomy wikilink should change a reader’s next click, and every pack slug should resolve to a real pack. Do not invent members to decorate the prose. Prefer fewer true links over many decorative ones. Keep Monday-shaped typing out of the runtime story; observation and ledger remain senior to any agent UI that retypes reality.