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