Memex
未认领Persistent memory for AI coding agents via MCP — a bitemporal knowledge graph of your codebase, served to Claude Code, Cursor, Gemini CLI, and any MCP client. Tree-sitter + Gemini Flash → Neo4j (via Graphiti). 12 MCP tools, hierarchical clusters, two-regime confidence decay.
安装
npx stifler-memex-mcp init --repo .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
12 个工具中显示 12 个
文档中列出的工具 (12)
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。
explain_change
Given a commit SHA, cross-references the diff with linked Decision/Problem nodes and asks Gemini Pro for a grounded explanation
get_open_problems
Active bugs and tech debt, sorted by severity
get_project_context
Session start. Returns a cluster-level briefing under 1500 tokens regardless of repo size
get_recent_decisions
Last N days of architectural decisions, optionally module-scoped
get_stale_context
Edges whose composite confidence dropped below threshold
get_symbol_context
Before editing a function or class. Returns callers, callees, linked decisions
invalidate_edge
When a stored fact is no longer true
predict_impact
Given a file path, returns a ranked list of modules likely affected based on graph coupling (no LLM call)
record_decision
After making a technical choice. Supports corroborates (reinforce) and supersedes (replace)
record_problem
When discovering a bug or piece of tech debt
resolve_problem
When a tracked problem is fixed
search_context
Hybrid search: semantic × keyword × graph traversal × RRF merge