Hmem – Persistent hierarchical memory for AI coding agents (MCP)
Hierarchical memory that persists across Claude Code, Cursor, and Windsurf—solve context amnesia.

Blog post marketing a SaaS product rather than a novel open-source Show HN project.
Developers using AI coding assistants
Cursor · Claude Desktop Memory · Sourcegraph Cody
Hierarchical memory that persists across Claude Code, Cursor, and Windsurf—solve context amnesia.
Unifies AI assistant configs across 6 tools—no cloud, local-first, syncs skills and MCP servers.
Persistent memory for Cursor and Claude when every chat resets to zero.
Vim+Emacs hybrid editor loses to VS Code and Neovim on community, ecosystem, plugins.
MCP memory standard solves AI context amnesia better than static .claude files.
Runs extraction and search server-side so your local MCP is a tiny HTTP client — no local DBs, no giant RAM leaks, and an easy npx install and .mcp.json or global MCP registration. It exposes clear tools (save_memory, recall_memories, extract_memories, get_project_context) and adds project-scoped + global preferences — a pragmatic fix for Claude Code's tiny flat-file memory. The tradeoff is obvious: usefulness depends on the hosted API (privacy, uptime, cost), and the repo looks early-stage with minimal commits and docs beyond the quickstart.