Externalizing Developers' Intuition as Code
Learns from Claude Code failures, stores insights—but requires Ollama and unclear workflow impact.
CLI + Local MCP - A shared structured memory store across Claude Code, Cursor, Windsurf, Antigravity, and every MCP client. Semantically queryable.
Structured decision memory via MCP beats generic AI memory for actual codebase context.
Developers using AI coding assistants (Claude Code, Cursor, Windsurf)
Mem0 · Cursor Memory · Windsurf Memory
Learns from Claude Code failures, stores insights—but requires Ollama and unclear workflow impact.
Cross-project memory for AI agents when single-project solutions already exist.
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.
Hierarchical memory that persists across Claude Code, Cursor, and Windsurf—solve context amnesia.
Local memory for AI agents that actually learns from your last 50 sessions, not just context window tricks.
Mimir hooks into Claude Code lifecycle events so agents can 'mark' facts (e.g., "API uses snake_case") into a DuckDB-backed memory and RAG pipeline, then auto-injects that context as additionalContext for later agents. It's a pragmatic, well-scoped solution to the annoying problem of agent amnesia — very useful if you run agent swarms, but its impact is limited by Claude Code adoption and the need for the surrounding infra (BGE keys, hooks).