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 3 shown
All (3) ◎ Marketing (0)↗ GTM & Growth (0)✎ Design (0)⛨ Security (0)▶ Video & YouTube (0)⌘ Development (0)⌕ Data & Research (0)⑂ Automation (0)⚡ Token & Cost Optimization (3)◆ AI Agents (0)◐ LLM Ops & Observability (0)◇ RAG & Knowledge (0)
⚡ Token & Cost Optimization3 Browse subcategories → abetlen ★ 11k Repository experimental Python bindings for llama.cpp enabling low cost local large language model inference.
Best match because its name, category, capabilities, or owner matches “savings”. Adoption and trust break close ties.
Stars 11k
Downloads 698k
Updated 2026-09-22
Skill installs — Trust pending Momentum not matched
$ pip install llama_cpp_pythonCopy Cheaper-Model Agents
zilliztech ★ 8.2k Tool slowing Semantic cache for storing LLM responses to bypass redundant API calls.
Best match because its name, category, capabilities, or owner matches “savings”. Adoption and trust break close ties.
Stars 8.2k
Downloads 437k
Updated 2026-09-22
Skill installs — Trust pending Momentum not matched
$ pip install gptcacheCopy Prompt Caching
ollama ★ 182k Tool experimental Run large language models locally to reduce inference costs and latency.
Best match because its name, category, capabilities, or owner matches “savings”. Adoption and trust break close ties.
Stars 182k
Downloads —
Updated 2026-09-27
Skill installs — Trust pending Momentum not matched
Cheaper-Model Agents