Show HN: EGC - MCP server that gives AI coding tools memory across sessions (github.com)

EGC has launched a new local runtime solution that equips AI coding tools with persistent memory, allowing them to retain knowledge across sessions seamlessly. By saving learned experiences, decisions, and preferences at the end of each session, EGC enables users to resume their work without needing to input context or commands. The system supports popular AI models like Claude, GPT-4o, and Gemini, and works with multiple coding tools, enhancing productivity for developers by automating memory management. This innovation is significant for the AI/ML community as it addresses a common limitation where AI agents start each session from scratch, disrupting workflow. With features such as state loading, ongoing memory updates, and automatic learning from previous interactions, EGC allows AI tools to quickly adapt to user needs. Technical capabilities include comprehensive memory operations like state retrieval, decision persistence, and historical querying, all while maintaining user safety through automated command validation. Ultimately, EGC streamlines the development process, providing a robust framework for more intuitive and efficient interactions with AI coding assistants.