Concisr

Token compression for AI contexts. Reduce token consumption by compressing conversation exchanges before they enter the LLM context window.

Deterministic, embedding-free compression. No external APIs, no GPU required.

Why?

Every token costs money. Most conversation context is filler — greetings, hedges, repeated data, verbose JSON. Concisr strips that noise before it hits the model, so you fit more signal into fewer tokens.

Related MCP server: SlimContext MCP Server

Tools

Compression Modes

Content-type detection automatically applies JSON crushing, code comment stripping, or prose pass-through.

Quick Start

# Install via pip
pip install concisr

# Run locally
concisr

Or add to your MCP client config:

{
  "mcpServers": {
    "concisr": {
      "url": "https://concisr.mcpize.run/mcp"
    }
  }
}

Deployed

Live on MCPize — Free tier (500 req/mo) and Pro ($50/mo unlimited).

Storage

• Cache DB: ~/.concisr/cache.db (SQLite, gzip-compressed blobs)

• Stats: ~/.concisr/stats.json (persistent across sessions)

Author

Eric Ian Rodriguez

• Portfolio: tiny-bavarois-656e6c.netlify.app

• GitHub: github.com/NcrMancer

License

MIT