RNN+Transformer hybrid with O(n) inference.
Part of AI Research Skills (Orchestra)Pack · 98 skills
by Orchestra-Research· AI & agentsUnclaimed · Yours? Claim it
About
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, Office, NeMo. RWKV-7 (March 2025). Models up to 14B parameters.
Skills people install alongside rwkv-architecture.
Runs on your machine.
Runs on your machine.
Runs on your machine.
Runs on your machine.
npx -y degit Orchestra-Research/AI-Research-SKILLs/01-model-architecture/rwkv ~/.copilot/skills/rwkv-architecture
Runs on your machine.
npx -y degit Orchestra-Research/AI-Research-SKILLs/01-model-architecture/rwkv ~/.cursor/skills/rwkv-architecture
Runs on your machine.
npx -y degit Orchestra-Research/AI-Research-SKILLs/01-model-architecture/rwkv ~/.claude/skills/rwkv-architecture
/plugin marketplace add Orchestra-Research/AI-Research-SKILLs /plugin install rag@ai-research-skills
Runs on your machine.
npx -y degit Orchestra-Research/AI-Research-SKILLs/01-model-architecture/rwkv ~/.agents/skills/rwkv-architecture
Runs on your machine.
Runs on your machine.
npx -y degit Orchestra-Research/AI-Research-SKILLs/01-model-architecture/rwkv ~/.gemini/skills/rwkv-architecture
Runs on your machine.
npx -y degit Orchestra-Research/AI-Research-SKILLs/01-model-architecture/rwkv .agents/skills/rwkv-architecture
Runs on your machine.
npx -y degit Orchestra-Research/AI-Research-SKILLs/01-model-architecture/rwkv ~/.openclaw/skills/rwkv-architecture
Runs on your machine.
npx -y degit Orchestra-Research/AI-Research-SKILLs/01-model-architecture/rwkv ~/.config/opencode/skills/rwkv-architecture
Runs on your machine.
npx -y degit Orchestra-Research/AI-Research-SKILLs/01-model-architecture/rwkv ~/.hermes/skills/rwkv-architecture
Scanned and passed · checked 49 min ago
From people who use it
Step by step
Nothing new reaches your agent until a person has looked at it.
Scanned on every change, and again when our rules improve.
No reviews yet. Used rwkv-architecture? Say how it went.
Write a reviewSkills people install alongside rwkv-architecture.
Has your agent write a tight, ready-to-paste prompt for the AI tool you name, from Claude Code and Cursor to Midjourney and Sora.
Turns a task into a copy-ready /goal command for Claude Code or Codex, with a checkable finish line and a stop bound.
The .NET team's skill for picking the right AI or ML stack in .NET 8+ apps, from ML.NET to Microsoft.Extensions.AI and Agent Framework.
Turn a repeated workflow, prompt set or SOP into a tested, packaged agent skill, or audit and improve a skill you already have.
Nobody has shared how they use rwkv-architecture yet.
Security scan
Passed
Safe to install in every agent it supports. Runs in your agent, as instructions.