Spatial bidirectional persistent memory MCP server for LLMs - vector-based semantic memory as a navigable landscape
Wellknown found it in public sources; nobody has proven control of it yet. Claiming takes one click if the repository is under your GitHub account, or a small file on your domain otherwise. Verified owners get the badge, 15-minute checks, status alerts, edits that outrank crawled data, and a ranking boost.
Agents can do it too: POST https://wellknown.network/api/v1/claims with {"agent":"spatial-memory-mcp","method":"well_known_file"} — machine-readable steps at claim.json, guide at /docs/claim.
Everything here was measured by our prober or read from a registry. Nothing is self-reported.
Attributed to the source that supplied each field. Treated as claims, not facts.
# Spatial Memory MCP Server [](https://pypi.org/project/spatial-memory-mcp/) [](https://www.python.org/downloads/) [](https://opensource.org/licenses/MIT) A persistent semantic memory system for LLMs via the [Model Context Protocol](https://modelcontextprotocol.io/) that treats knowledge as a navigable landscape, not a filing cabinet. > **Version 1.11.3** — Production-ready with 2,500+ tests across Windows, macOS, and Linux. **Your AI assistant forgets everything between sessions. Spatial Memory fixes that.** It gives Claude Code, Cursor, and any MCP client a persistent brain — memories that fade when stale, sharpen with use, and organize themselves into a navigable knowledge graph. Install in one command, capture knowledge automatically, and let your AI build on what it learned yesterday. ## Why Spatial Memory? Most memory servers store and retrieve. Spatial Memory **thinks** about your knowledge. ### Memories That Fade Like Yours Do Other memory tools treat every piece of information as equally important forever. Spatial Memory applies **time-based decay** — old, unused memories gradually lose importance while frequently accessed knowledge stays sharp. The result: your AI assistant surfaces what's relevant *now*, not what was relevant six months ago. Decay is automatic and configurable — adjust half-life, decay curves (exponential, linear, step), and minimum importance floors. Memories accessed frequently decay slower, just like human recall. **Why this approach?** The cognitive memory model is inspired by established research: - **[Ebbinghaus, H. (1885)](https://psychclassics.yorku.ca/Ebbinghaus/index.htm)** — *Memory: A Contribution to Experimental Psychology*. The foundational research on the forgetting curve showing how memory retention decays exponentia…
Mapped onto the structured taxonomy from declared text and observed tool names. Confidence shown for derived entries.
Every source is kept verbatim. Field changes are logged as events.