Middleware memory engine for LLMs — replaces linear chat history with three parallel structures (Entity Graph, Semantic Tree, Focus Buffer) to retrieve only the most relevant context within a token budget. Works as a Python library or MCP server for Claude Code, Copilot CLI, and other AI tools.
1 file for Claude Code: hce CLAUDE.md — 1,411 tokens loaded in every session.
CLAUDE.md A 1,411 tok These files are nakurian/hce's own configuration — they tell Claude Code how to work on this repository, so they are not mods to install elsewhere. Copy one as a starting point and replace the parts that are about this project.