State-space model with O(n) complexity vs Transformers' O(n²). 5× faster inference, million-token sequences, no KV cache. Selective SSM with hardware-aware design. Mamba-1 (d_state=16) and Mamba-2 (d_state=128, multi-head). Models 130M-2.8B on HuggingFace.
Install
npx skills add davila7/claude-code-templates --skill mamba-architecturenpx skills add davila7/claude-code-templates --skill mamba-architecture -a claude-code -gnpx skills add davila7/claude-code-templates --skill mamba-architecture -a codex -ggemini skills install https://github.com/davila7/claude-code-templates.git --path cli-tool/components/skills/ai-research/model-architecture-mambagh skill install davila7/claude-code-templates mamba-architecturegit clone --depth 1 https://github.com/davila7/claude-code-templates /tmp/davila7__claude-code-templates
mkdir -p ~/.claude/skills ~/.agents/skills
cp -R /tmp/davila7__claude-code-templates/cli-tool/components/skills/ai-research/model-architecture-mamba ~/.claude/skills/mamba-architecture # Claude Code
cp -R /tmp/davila7__claude-code-templates/cli-tool/components/skills/ai-research/model-architecture-mamba ~/.agents/skills/mamba-architecture # Codex, Cursor, Gemini CLI, Copilot, OpenCode