token compressor for Gemini CLI

io.github.base76-research-lab/token-compressor

Compress prompts 40-60% using local LLM + embedding validation. Preserves all conditionals.

client:Gemini CLI transport:stdio runtime:pypi

Install token compressor in Gemini CLI

~/.gemini/settings.json · windows: %USERPROFILE%\.gemini\settings.json

{
  "mcpServers": {
    "token-compressor": {
      "command": "uvx",
      "args": [
        "token-compressor-mcp"
      ]
    }
  }
}

Gemini expands $VAR and ${VAR} inside env values, so a secret can live in your shell rather than this file. Gemini CLI docs