Control center / Discover
Discover Browse by category instead of drowning in search results. Every category opens a submenu of subcategories with live counts, and checking one narrows the grid to exactly that slice.
◑ Verified against GitHub · scores pending
Sort by: Best match Skill installs Stars Downloads Last updated Forks Name ↓ DescType: Filter by entry type All types MCP Server Claude Skill Agent Repository Tool Trust: Filter by trust evidence Any trust state Crown eligible Trust checked Audit conflict Maturity: Filter by maturity Any maturity Stable Active Experimental Slowing 4 shown
All (4) ◎ Marketing (0)↗ GTM & Growth (0)✎ Design (0)⛨ Security (0)▶ Video & YouTube (0)⌘ Development (0)⌕ Data & Research (0)⑂ Automation (0)⚡ Token & Cost Optimization (4)◆ AI Agents (0)◐ LLM Ops & Observability (0)◇ RAG & Knowledge (0)
⚡ Token & Cost Optimization4 Browse subcategories → ggerganov ★ 130k Repository stable Efficient C plus plus inference of LLaMA models enabling cheaper on device execution.
Best match because its name, category, capabilities, or owner matches “efficiency”. Adoption and trust break close ties.
Stars 130k
Downloads —
Updated 2026-09-27
Skill installs — Trust pending Momentum not matched
$ pip install llama-cpp-scriptsCopy Cheaper-Model Agents
microsoft ★ 43k Repository experimental Deep learning optimization library enabling efficient large model training and inference.
Best match because its name, category, capabilities, or owner matches “efficiency”. Adoption and trust break close ties.
Stars 43k
Downloads —
Updated 2026-09-28
Skill installs — Trust pending Momentum not matched
Context Compression
turboderp ★ 4.6k Repository slowing Fast inference library for running quantized LLMs on consumer GPUs at lower cost.
Best match because its name, category, capabilities, or owner matches “efficiency”. Adoption and trust break close ties.
Stars 4.6k
Downloads —
Updated 2026-03-04
Skill installs — Trust pending Momentum not matched
$ pip install exllamav2_extCopy Cheaper-Model Agents
huggingface ★ 11k Tool slowing Production ready inference server for LLMs optimized for throughput and cost efficiency.
Best match because its name, category, capabilities, or owner matches “efficiency”. Adoption and trust break close ties.
Stars 11k
Downloads —
Updated 2026-03-21
Skill installs — Trust pending Momentum not matched
Observability & Cost