Reduces AI agent token usage by 90% via context compression and task checkpoint persistence.
MCP server that reduces AI agent token usage by up to 90% with intelligent context compression (measured on this project). Restart Cursor. Done. Optional assisted mode for long tasks: Restart Claude Desktop. Done. Restart Qwen Code. Done. Restart your AI client. Done. After updating: The binary is updated globally, but agent rules (, , ) in each project are generated from the installed version…
Verification confirms publisher identity (repo ownership), not code safety. The security scan covers known CVEs and suspicious install scripts — it cannot prove the absence of malicious code.
MCP server that reduces AI agent token usage by up to 90% with intelligent context compression (measured on this project). Restart Cursor. Done. Optional assisted mode for long tasks: Restart Claude Desktop. Done. Restart Qwen Code. Done. Restart your AI client. Done. After updating: The binary is updated globally, but agent rules (, , ) in each project are generated from the installed version and are not updated automatically. Re-run init after each update to get the latest rules: Then restart…