Odel
token optimizer

token optimizer

Local
@omkar98541PythonApache-2.0Updated 1mo ago

Reversible context compression for AI agents: cut token usage up to 94%, originals retrievable

View on GitHub

Runs locally over stdio

This server isn't hosted — your MCP client launches it from a package registry. Use one of the commands below, or drop the config into your client (e.g. Claude Desktop).

PyPIslimctxv0.1.0

Run

uvx slimctx

MCP client config

{
  "mcpServers": {
    "token-optimizer": {
      "command": "uvx",
      "args": [
        "slimctx"
      ]
    }
  }
}