Semantic compression for IDE↔LLM communication — CLI, MCP server, and VS Code extension, with a Context Router, team-shared dictionaries, and compression calibrated against real provider tokenizers.
View on GitHub →
🔍 Audit Wallet Slippage →
Quick Install
Copy the config for your editor. Some servers may need additional setup — check the README.
Claude Desktop
Claude Code
Cursor
Add to claude_desktop_config.json:
{
"mcpServers": {
"glyph-compress": {
"command": "npx",
"args": [
"-y",
"Neolambo/glyph-compress"
]
}
}
}
📋 Copy
Run in terminal:
claude mcp add glyph-compress npx -y Neolambo/glyph-compress
📋 Copy
Add to .cursor/mcp.json:
{
"mcpServers": {
"glyph-compress": {
"command": "npx",
"args": [
"-y",
"Neolambo/glyph-compress"
]
}
}
}
📋 Copy
README Excerpt
<h1 align="center">⚡ GlyphCompress</h1> <p align="center"> <img src="./assets/logo.png" alt="GlyphCompress Logo" width="300"> </p> <p align="center"> <a href="https://www.npmjs.com/package/glyph-compress"><img src="https://badgen.net/npm/v/glyph-compress" alt="NPM Version"></a> <a href="https://opensource.org/licenses/AGPL-3.0"><img src="https://badgen.net/badge/License/AGPL-3.0-only/blue" alt="License: AGPL-3.0-only"></a>
Tools (6)
benchmark compress_file compress_text doctor get_codebook route_context
Topics
ai coding-agents developer-tools llm mcp model-context-protocol prompt-engineering semantic-compression token-compression token-optimization vscode-extension