Agentic

The Agentic layer is where products stop being a chat box over an LLM and start being operators: they break goals into steps, bind tools and memory, and hand judgment back to humans at policy gates. In this catalog it holds frameworks, RAG, gateways, evals, guardrails, coding and voice agents, protocols, and sandboxes — the connective tissue of an agentic OS.

It sits above Infrastructure (vectors/graphs) and beside LLMs (serve/tune weights). Browse children such as Frameworks, RAG, Observability, and Tool Integration when assembling observe→propose→gate→execute. Prefer this layer when the bottleneck is autonomy with evidence — not raw tokens/sec and not embedding storage alone.

Representative packs like Crew AI, LlamaIndex, and LangFuse illustrate composition, grounding, and traces. Feature maps such as Agent Lifecycle Management and Verify business effect, not API 200 define done: agents that run under gates with attributable effects.

Inline members for audit: Crew AI LlamaIndex LangFuse. Features: Agent Lifecycle Management Verify business effect, not API 200. Related terms referenced: Infrastructure, LLMs.

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.