RNN+Transformer hybrid with O(n) inference. Linear time, infinite context, no KV cache. Train like GPT (parallel), infer like RNN (sequential). Linux Foundation AI project. Production at Windows,...
Define the technical stack and architecture for a project. Interactive session with the Architect agent.
>
Test application performance, scalability, and resilience. Use when planning load testing, stress testing, or optimizing system performance.
>
>
>
>
Three.js performance optimization and best practices guidelines. Use when writing, reviewing, or optimizing Three.js code. Triggers on tasks involving 3D scenes, WebGL/WebGPU rendering,...
Expert at advanced debugging and root cause analysis. Use when troubleshooting complex issues, finding root causes of bugs, investigating performance problems, or analyzing system failures.
Redis development best practices for caching, data structures, and high-performance key-value operations
|
>
Write reliable prompts for Agentica/REPL agents that avoid LLM instruction ambiguity
Write reliable prompts for Agentica/REPL agents that avoid LLM instruction ambiguity
Automatically recover working context after session compaction or when continuation is implied but context is missing. Works across Discord, Slack, Telegram, Signal, and other supported channels.
Pinia state management for JARVIS system state
Debug Docker containers and containerized applications. Diagnose deployment issues, container lifecycle problems, and resource constraints.
Ultimate AGI Evolution - 200 UltraThink thoughts, quantum branching, self-improvement loops, cross-skill orchestration, and predictive goal decomposition. The pinnacle of autonomous agent capability.
Enterprise context and session management with token budget optimization and state persistence