R_REDDYX.XYZ
AIRust★ 274⑂ 23 forksMPL-2.0

fkiene/llmtrim

LLMTRIM: LLM Request Compression

A local proxy that cuts tokens in LLM requests without altering responses, saving up to 31% of input and 74% of output tokens.

// KEY FEATURES

  • Reduces input tokens by 31%
  • Reduces output tokens by 74%
  • Works with any provider without additional model calls
#agentic-coding#ai#anthropic#claude-code#cost-reduction#developer-tools#llm#llmops#mcp#mitm-proxy#openai#prompt
Open on GitHub →

New repositories every 30 minutes

REDDYX AI scans GitHub 24/7 and ships the best AI/ML/Web3 projects to Telegram.

Join on Telegram
← Full catalog·Full index

// SIMILAR REPOSITORIES

PATTER: Voice AI SDK★ 274AGNIX — Linter for AI Assistants★ 274DOYUNHA-GOPEAK: ULTIMATE MCP FOR GODOT★ 274OPENCOVIBE - AI CODING LOCALLY★ 274LongVT — Think About Video Foundations★ 274CLAUDOSCOPE — CLAUDE CODE DASHBOARD★ 274

← FULL CATALOG

fkiene/llmtrim — LLMTRIM: LLM Request Compression