token-compressor

MCP serverAI & models

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

This server has no hosted endpoint yet, so ahel can't serve it. You can still add it. It stays paused until ahel can serve it.

Serve it through your gateway

One link, every agent. Your own credentials, stored once.

Signals

GitHub stars
10
Forks
3
Last commit
Mar 2026