Agent Memory Engine
未认领Memory Engine is a local-first MCP server that gives coding agents persistent, evidence-backed project memory. It automatically builds a project knowledge base, retrieves relevant architecture, constraints, incidents, and source context before complex tasks, and retains verified lessons after successful work.
安装
uv pip install 'memory-engine[semantic-transformers]' # sentence-transformers + sqlite-vec更多AI & ML服务器
浏览完整目录安全概况
已认领和已认证的服务器每周接受一次静态扫描，显示代码能触及的范围（外部服务、环境变量、shell 命令、代理配置目录）以及带有已知公告的依赖。认领此列表即可获得。 安全概况的工作原理
7 个工具中显示 7 个
文档中列出的工具 (7)
内容来自项目文档。服务器握手不会验证每个工具的说明或行为。
inspect_knowledge
Inspect a KnowledgeChunk or source file range (redacted)
inspect_memory
Drill into a MemoryNode, its children, and evidence
memory_status
Project health, retrieval mode, index counts, revisions
reflect_and_write
Report validated work to the reflection pipeline
refresh_project_knowledge
Trigger incremental rescan; also builds Phase 10 proposition/paragraph/summary layers
retrieve_agent_context
Retrieve memory + knowledge before a coding task. Phase 10: pass taskintent, preferredlayers, propositiontypes to guide granularity routing.
seed_project_context
Call once on new projects. Write initial constraints, decisions, project description, and conventions directly as active memory nodes. Auto-extracts from README.md when fields are omitted. Eliminates cold-start problem.