接入你的智能体
發布者自己的指令。不是 PlugMCP 端點。
用我們的金鑰與日誌託管一份副本。
uvx mindcore-memory==0.1.11Claude Code 沒有本機指令的安裝連結。複製下方指令並在終端機中執行。
claude mcp add io.github.woshilaohei-mindcore-memory -- uvx mindcore-memory==0.1.11在終端機中執行。
{ "mcpServers": { "io.github.woshilaohei-mindcore-memory": { "command": "uvx", "args": [ "mindcore-memory==0.1.11" ] } }}claude_desktop_config.json
遠端 URL 還是本機指令？ 兩種安裝方式的差異
來自發布者
The only MCP memory server with circuit breaker, SLO tracking, and BM25+FAISS hybrid search. AI agents forget everything between sessions. MindCore Memory gives them persistent, searchable, production-grade memory — with 118/118 tests passing and full CI/CD.
⭐ If this project helps your AI remember, a star means the world to us.
AI long-term memory MCP server with importance scoring and confidence calibration
# 1. Install
pip install mindcore-memory
# 2. Launch (stdio mode — works with any MCP client)
mindcore-memory
# 3. Your AI agent remembers across sessions
{
"mcpServers": {
"mindcore-memory": {
"command": "python",
"args": ["-m", "mindcore_memory.server"],
"env": { "MINDCORE_MEMORY_PATH": "~/.mindcore/memory" }
}
}
}
pip install mindcore-memory[semantic]
# Enables FAISS embeddings for hybrid BM25+semantic search
MindCore is the only MCP memory server designed for production workloads from day one. Circuit breaker protects against embedding service failures. Retry with exponential backoff handles transient errors. SLO tracking alerts you before users notice. Metrics export for your monitoring stack. Every other server assumes nothing fails — MindCore doesn't.
MindCore is not just a memory store — it's a cognitive boundary engine. Every stored memory is automatically evaluated through a 4-dimensional scoring system based on the 正反公式 (Forward/Reverse Formula):
BND_score = 0.28·TRJ(Trajectory) + 0.28·EVO(Evolution) + 0.28·COG(Cognition) + 0.16·BALANCE
from mindcore_memory import BNDManager
bnd = BNDManager()
result = bnd.evaluate("基于之前修复, 理解到根因, 改进后提升30%", importance=4)
# → TRJ:0.63 EVO:0.54 COG:0.61 BALANCE:0.98 BND:0.75 ACCEPTED
No other MCP memory server does this. BND transforms memory storage from a passive data dump into an active cognitive filter — rejecting noise, flagging risk chains, and ensuring only structured, growth-oriented knowledge enters the version chain.
/metrics: Zero-dependency Prometheus-compatible collector. Drop-in for any monitoring stack.mindcore-memory[encrypt]).Search formula: score = BM25(40%) + FAISS(50%) + importance(5%) + recency(5%)
When FAISS embeddings are unavailable, automatically falls back to BM25-only keyword search.
┌───────────────────┐ MCP JSON-RPC ┌────────────────────────────┐
│ AI Client │ ◄──────────────────► │ MindCore Memory │
│ (Claude/Cursor) │ stdio / HTTP │ MCP Server │
└───────────────────┘ └──────────┬─────────────────┘
│
┌──────────▼─────────────────┐
│ Memory Engine │
│ ┌──────────────────────┐ │
│ │ Hybrid Search │ │
│ │ BM25 (keyword) 40% │ │
│ │ FAISS (semantic)50%│ │
│ │ importance 5%│ │
│ │ recency 5%│ │
│ └──────────────────────┘ │
│ ┌──────────────────────┐ │
│ │ Resilience │ │
│ │ Circuit Breaker │ │
│ │ Retry + Backoff │ │
│ │ SLO Tracking │ │
│ └──────────────────────┘ │
└──────────┬─────────────────┘
│
┌──────────▼─────────────────┐
│ Storage │
│ JSONL (append) │
│ + FAISS index (IVF > 500) │
│ + Fernet encrypt (opt) │
└────────────────────────────┘
See docs/comparison.md for a detailed 5-server comparison covering architecture, search quality, latency, and migration guides.
See CONTRIBUTING.md for the full guide. Quick path:
git clone https://github.com/woshilaohei/mindcore-memory-mcp.git
cd mindcore-memory-mcp
pip install -e ".[dev]"
pytest -v # 118 tests
ruff check . # linter
mypy mindcore_memory/ # type checker
MIT License — Copyright (c) 2025 Lao Hei
⭐ If MindCore helps your AI remember, give it a star! ⭐
AI long-term memory MCP server with importance scoring and confidence calibration
{ "mcpServers": { "io.github.woshilaohei-mindcore-memory": { "command": "uvx", "args": [ "mindcore-memory==0.1.11" ] } }}工具
尚無工具清單。遠端伺服器會在首次健康檢查後取得工具清單。
常見問題
在本頁複製適用於 Cursor、Claude Desktop、Claude Code 或 VS Code 的 stdio 設定。它使用發布者的安裝方式，而不是 PlugMCP 代理伺服器。
這筆記錄未列出必要的環境變數。
MindCore Memory MCP 透過 stdio 在本機執行。
上次檢查時間：2026-11-10。 AI long-term memory MCP server with importance scoring and confidence calibration