@llmtrim/cli
Advanced tools
Cut your LLM bill: drop-in proxy that compresses input, output, and cache. Any provider, answers unchanged.
llmtrim is a local proxy that compresses your LLM API requests so you pay less, with no change to the answers. It strips wasted tokens (verbose tool output, resent schemas, bulky JSON, long context) out of every request before it reaches the provider: −31% input and −74% output tokens, measured live across 112 A/B cases. Works with Claude Code, Cursor, Cline, and any tool that talks to OpenAI / Anthropic / Google / DeepSeek / Mistral & co.
Every cut is re-counted with the provider's real tokenizer and auto-reverted if it doesn't save, so it can never increase your bill or break a request.
npm install -g @llmtrim/cli@latest && llmtrim setup
# open a new shell, then watch the bill shrink:
llmtrim status
setup is transparent and fully reversible (llmtrim uninstall): a local CA, a proxy
block in your shell profile, a background service. Everything runs locally; nothing is
ever sent to us.
This package installs a prebuilt native binary for your platform (Linux, macOS, Windows; x64 & arm64). No Rust toolchain needed.
Docs, benchmarks (112 live A/B cases), and source: https://github.com/fkiene/llmtrim
License: MPL-2.0
FAQs
Cut your LLM bill: drop-in proxy that compresses input, output, and cache. Any provider, answers unchanged.
The npm package @llmtrim/cli receives a total of 644 weekly downloads. As such, @llmtrim/cli popularity was classified as not popular.
We found that @llmtrim/cli demonstrated a healthy version release cadence and project activity because the last version was released less than a year ago. It has 1 open source maintainer collaborating on the project.
Did you know?
Socket for GitHub automatically highlights issues in each pull request and monitors the health of all your open source dependencies. Discover the contents of your packages and block harmful activity before you install or update your dependencies.
Research
/Security News
Socket uncovered 77 linked Firefox extensions, including 40 that steal wallet secrets or credentials and 37 deceptive sports-score shells.
Security News
NIST disclosed an unreleased AI tool called V-etalon and opened a broad inquiry into NVD modernization after years of automation plans produced no public enrichment system.
Security News
In his AI Council 2026 talk, Feross Aboukhadijeh covers recent package compromises, vulnerability discovery, and a more automated security model.