MemoryMesh

The SQLite of AI Memory — persistent, zero-dependency memory for any LLM application. Dual-store architecture (project + global), pluggable embeddings (local/Ollama/OpenAI), semantic search with time decay, auto-categorization, and contradiction detection. 10 MCP tools. Works with Claude Code, Cursor, Gemini CLI, and any MCP client.

该来源不提供完整文件导出（国内平台多为平台内托管），仅存元数据与原链

接入信息

传输形态: http
鉴权方式: 鉴权未知
端点: https://memorymesh--sparkvibe-io.run.tools

鉴权方式未标注，请核对官方文档后再接入——不要直接使用以下片段

{
  "mcpServers": {
    "MemoryMesh": {
      "url": "https://memorymesh--sparkvibe-io.run.tools"
    }
  }
}

能力清单

工具	说明
remember	Store a new memory in MemoryMesh. Use this to save facts, preferences, decisions, or any information that should persist across conversations.
recall	Recall relevant memories from MemoryMesh using semantic similarity and keyword matching.
forget	Permanently delete a specific memory by its ID. Searches both project and global stores.
forget_all	Forget ALL stored memories in the specified scope. This is a destructive operation. Defaults to project scope.
update_memory	Update an existing memory's text, importance, scope, or metadata in place. Only provided fields are changed.
memory_stats	Get statistics about stored memories: total count, oldest and newest timestamps.
session_start	Retrieve structured context for the start of a new AI session. Returns user profile, guardrails, common mistakes, and project context.
review_memories	Audit memories for quality issues (scope mismatches, verbosity, staleness, duplicates). Returns issues with suggestions.
status	Get MemoryMesh health status: project store, global store, embedding provider, and version.
configure_project	Set the project root at runtime without restarting the server. Creates the project database at <path>/.memorymesh/memories.db.

纠错与举报（发现条目失效、署名有误或涉及侵权？）

提交举报 / 纠错

侵权举报经核验成立后，我们会即时下线该条目并删除已存的内容副本。