llmtrim

About llmtrim

llmtrim llmtrim is a local proxy that compresses your LLM API requests so you pay less, with no change to the answers. It sits between your AI tools and the provider, strips the wasted tokens out of every request, and forwards it on. You get the same answers for a smaller bill. −31% input and −74% output tokens, measured live across 112 A/B cases, with no change in answer quality. What it does • See it in action • Get started • CLI & library • Works with • Configuration • Numbers What it actually do

Quick Facts

Compatible Skills

These tools work well together with llmtrim for enhanced workflows:

• homebrew-ccr — semantic(0.26)+complementary+rare_topics+same_lang+similar_pop+shared_platform (59%)
• homebrew-pandafilter — semantic(0.23)+complementary+rare_topics+same_lang+similar_pop+shared_platform (58%)
• crab-code — semantic(0.22)+complementary+same_lang+similar_pop+shared_platform (53%)

More MCP Server Tools

Explore other popular mcp server tools:

• ECC ⭐ 226.5k
• n8n ⭐ 195.7k
• everything-claude-code ⭐ 186.6k
• dify ⭐ 148.2k
• open-webui ⭐ 143.9k
• cc-switch ⭐ 114.8k
• gemini-cli ⭐ 105.8k
• awesome-mcp-servers ⭐ 90.3k
• servers ⭐ 88.1k
• lobehub ⭐ 79.6k

Popular Rust Agent Tools

• cc-switch ⭐ 114.8k · MCP Server
• rtk ⭐ 69.5k · Agent Tool
• Pake ⭐ 59.6k · Claude Skill
• agent-browser ⭐ 38.1k · Agent Tool
• zeroclaw ⭐ 32.2k · Codex Skill

Frequently Asked Questions