Sign In

@llmtrim/cli

Package Overview
Dependencies
Maintainers
1
Versions
54
Alerts
File Explorer

Advanced tools

Socket logo

Install Socket

Detect and block malicious and high-risk dependencies

Install

@llmtrim/cli - npm Package Compare versions

Comparing version
0.1.4
to
0.1.5
+24
README.md
# llmtrim
**Cut ~66% off your LLM bill.** A drop-in local HTTPS proxy that compresses every LLM
request and reply — input, output, and cache — with zero extra model calls. Works with
Claude Code, Cursor, Cline, and any tool that talks to OpenAI / Anthropic / Google /
DeepSeek / Mistral & co. Answers unchanged: every cut is re-counted with the provider's
real tokenizer and auto-reverted if it doesn't save.
```bash
npm install -g @llmtrim/cli && llmtrim setup
# open a new shell, then watch the bill shrink:
llmtrim status --watch
```
`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: AGPL-3.0-only
+8
-8
{
"name": "@llmtrim/cli",
"version": "0.1.4",
"version": "0.1.5",
"description": "Cut your LLM bill: drop-in proxy that compresses input, output, and cache. Any provider, answers unchanged.",

@@ -10,11 +10,11 @@ "repository": "https://github.com/fkiene/llmtrim",

"bin": { "llmtrim": "bin/llmtrim.js" },
"files": ["bin"],
"files": ["bin", "README.md"],
"optionalDependencies": {
"@llmtrim/linux-x64": "0.1.4",
"@llmtrim/linux-arm64": "0.1.4",
"@llmtrim/darwin-x64": "0.1.4",
"@llmtrim/darwin-arm64": "0.1.4",
"@llmtrim/win32-x64": "0.1.4",
"@llmtrim/win32-arm64": "0.1.4"
"@llmtrim/linux-x64": "0.1.5",
"@llmtrim/linux-arm64": "0.1.5",
"@llmtrim/darwin-x64": "0.1.5",
"@llmtrim/darwin-arm64": "0.1.5",
"@llmtrim/win32-x64": "0.1.5",
"@llmtrim/win32-arm64": "0.1.5"
}
}