A different approach from typical persistent-memory MCPs. Instead of a local
SQLite + embeddings store, the memory lives as plain files in a .ai-memory/
directory you commit to your repo (facts.jsonl, decisions/\*.md, gotchas.md).
Git is the sync layer — what one Claude/Cursor/Cline learns about a repo, the
next session (or a teammate's agent) picks up automatically.
5 MCP tools: get_rep
MCP server that exposes agent-memory-daemon to any MCP-compatible client — Kiro (CLI & IDE), Claude Desktop, Cursor, and others.
The daemon does the thinking (consolidation + extraction); this server is a thin filesystem bridge so agents can read, append, and search memory through the Model Context Protocol.
Self-hosted MCP-native agent memory server. Gives AI agents persistent, decay-weighted memory via 83 MCP tools — no cloud, full control. RocksDB+HNSW backend. Works with Claude Code, Cursor, and any MCP-compatible agent.
A self-hosted MCP server that gives AI agents persistent, searchable memory with importance scoring, knowledge graphs, and autonomous memory consolidation.
An MCP server that gives AI agents persistent, forgetting memory with layered decay, semantic search via token overlap, and zero external dependencies.
A Rust-based MCP server that provides long-term memory capabilities for AI agents using keyword-based storage and retrieval. It supports isolated namespaces for different users or projects, allowing LLMs to remember and recall information across sessions.
