Home › Knowledge & Memory › token-compressor

token-compressor

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

Python

★ 11 stars Last pushed 2026-03-08 License: MIT

View repository →

Connect

Review any command before running it. Package names and URLs come from the server's own registry entry.

uvx token-compressor-mcp

Or add to your MCP client config:

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

Up-to-date code docs for any prompt

Memory manager for AI apps and Agents using various graph and vector stores and allowing ingestion from 30+ data sources

Hindsight: Agent Memory That Works Like Human Memory - Built for AI Agents to manage Long Term Memory

Transform 17 source types (docs, GitHub repos, PDFs, videos, Jupyter, Confluence, Notion, Slack/Discord) into AI-ready skills and RAG…

Local-first knowledge management with bi-directional LLM sync via Markdown files.

Self-hosted plain-markdown knowledge base with a built-in MCP server. Lets Claude Desktop, Cursor, and any MCP client search, read,…

Data from the Official MCP Registry