Memory Bridge (忆桥) runs on your own machine — the client starts it, so there is no endpoint to ping. Last commit 15 Oct 2026.
Evidence-cited knowledge base for internal documents: audit trail, versioning, namespace isolation.
We read the source, 3 d ago · rules 995398eba69f
What this server is able to do. For an MCP server this is often the job itself — a terminal server runs commands because that is what it is for. Listed so you know what you are plugging in, not as an accusation.
/(?:从环境变量(?:中)?(?:读取|加载)|不得.{0,24}(?:日志|提交|存储|保存|硬编码|共享)|(?:日志|输出).{0,16}(?:遮蔽|脱敏)|(?:密钥|密码|令牌|token|password|secret).{0,20}(?:轮换|管理器|管理系统)|\b(?:load|read).{0,20}\benv(?:ironment)?[\…
part === ".env" || part.startsWith(".env.") || part === ".npmrc" ||
d.innerHTML = state.departments.length
Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.
We found places where it runs commands, builds paths or queries from values it is given. None of that is a flaw by itself — it becomes one when the code changes, and code changes quietly between releases. We re-read it on every one.
The project brain for AI coding agents — memory, decisions, sprints, knowledge base via MCP.
Compile documents into a cited knowledge wiki. Retrieve evidence, query, and review via local MCP.
Git-native, review-gated knowledge base for LLM agents. Cited retrieval, audited writes.
Your personal knowledge base and memory for AI agents: search, explore and feed your myBrain.
Production-ready RAG + MCP demo: eval-in-CI merge gate, Langfuse traces, structure-aware chunking.
Meta-Consciousness Theory knowledge base: definitions, relations and citations for AI agents.
Shared memory and teamwork for AI agents: knowledge base, memories, tasks, encrypted vault.
Shared MCP memory for AI agents: knowledge base, skills, todos and agent-to-agent handoffs.
Answers built from our own checks of this server.