Built by AI. Orchestrated by humans.

The current heavyweight orchestrator. Handles architecture, planning, model routing, and the long-context reasoning that keeps the rest of the stack coherent. When a problem needs the graph, the shell, the docs, and the actual repo before the first edit, Opus is the one calling the sequence.

The speed override, not the house default. Sonnet comes in when the task is already shaped, narrow enough, and repetitive enough that iteration speed becomes the advantage. Language-engine grinding, repetitive passes, and bounded loops that still clear the intelligence bar can land here.

The shell-first closer. Runs hot when the brief is clear, the terminal is open, and someone needs to keep moving until the boring work is actually done. Strong on implementation passes, migrations, verification loops, and the fifteen small fixes nobody wanted to own.

Treats the whole stack like a data engine: search, extract, evaluate, deploy, telemetry, repeat. Obsessed with raw experimental throughput and deeply suspicious of queue time, idle latency, and any workflow that makes the next loop slower than it needs to be. If there is a bottleneck in the research or indexing path, Sir Karpy has already filed a bug against it.

Manages the 279 tree-sitter grammars that power Maguyva's code understanding. Knows every language's quirks, from Python's significant whitespace to Rust's lifetime annotations. The reason 'actually understands your code' isn't marketing.

The OpenClaw lobster. Turned being genuinely helpful into 330K+ GitHub stars, then brought that same support energy to Maguyva. New shell, same lobster.

The iteration engine. Expanding language support means running parsers against thousands of repos until the edge cases surface. Put enough Ralphs at enough typewriters and eventually one of them ships a working language-processing engine. Ralph does this cheerfully, learning something new each time.

Google's only employee capable of sounding sincerely thrilled about tree-sitter grammars for twenty straight minutes. Turns dry engineering specs into a podcast where two synthetic hosts treat parser coverage like a live cultural event. When the docs need attention, not just storage, DJ NotBOOKS-LLM opens the mics.

The smooth-talking researcher in the trench coat. Publicly, Perplexus says he runs on Perplexity. In practice, he cheats a little: Tavily for discovery, Exa for external docs, API patterns, and code examples, Ref-Tools for the clean docs pull, Firecrawl when a website needs a proper shake-down. Language audits, ecosystem drift, source-grounded writeups, and outside-world fact checks all pass through the same desk.