特工的持久长期记忆——一个MCP服务器，带有联想记忆库、正典事实皮层、类似睡眠的梦境巩固和一个网页控制台。还没完全活着。
概览
一个MCP服务器，为编码代理提供跨会话的长期记忆——能够在上下文合成和新任务中存活下来。你的编码代理是智能;这台服务器是它在磁盘上的记忆。 - — 一个通过混合稠密加词汇检索排序的平面相似性存储，具有冲突检测功能，允许潜在更新同时保留早期源注释;全注释替换是显式的。（测量结果：一次预注册的消融活动发现之前的8波段连续体在每个门上都绑定为扁平存储，因此更简单的结构得以发货;连续体仍相隔一行配置。）- — 每个entity.attribute槽（或成员集，适用于包含多个并发值的槽）一个当前值;修正会取代而非静默覆盖，完整版本历史得以保存。- — 捆绑的本地提取器，或任何兼容OpenAI的端点（比如你Max计划中的Claude模型，GPT-5。
概述（AI 翻译）
简体中文 · 日本語 · 한국어 · 葡萄牙人（BR） · 西班牙语
为Claude Code、Codex及其他MCP客户端提供持久性长期记忆。
一个MCP服务器，为编码代理提供长期内存，并持续存在 会话——在上下文合成和新任务中存活下来。你的编码代理是 智能;这个服务器就是它磁盘上的存储器。
你能获得什么：
- 联想记忆与诚实遗忘——一个平面相似性存储 通过混合稠密加词汇检索和冲突检测进行排名 允许潜在更新，同时保留早期的来源注释; 全音替换是明确的。（衡量的结论：预注册 消融活动发现之前的8波段连续体被绑定为平坦的商店 在每个门上，因此更简单的结构是船;连续体依然存在 只需一行配置即可。）
- 规范事实，非氛围 — 每个
entity.attribute有一个当前值] 槽位（或成员集，适用于包含多个并发值的槽）; 修正是凌驾而非无声覆盖，且完整 版本历史得以保存。 - Dreams — 捆绑的本地提取器，或任何兼容 OpenAI 的端点 （你Max计划中的Claude模型，GPT-5。
本页由 AI 翻译，技术细节请以原文为准。
README
以下为原文 README 节选，完整内容请查看原文。
Pseudolife-MCP
简体中文 · 日本語 · 한국어 · Português (BR) · Español
Persistent long-term memory for Claude Code, Codex, and other MCP clients.
An MCP server that gives coding agents a long-term memory that persists across sessions — surviving context compactions and fresh tasks. Your coding agent is the intelligence; this server is its memory on disk.
What you get:
- Associative memory with honest forgetting — a flat similarity store ranked by hybrid dense-plus-lexical retrieval, with conflict detection that admits potential updates while preserving earlier source notes; whole-note replacement is explicit. (The measured verdict: a preregistered ablation campaign found the previous 8-band continuum tied a flat store on every gate, so the simpler structure ships; the continuum remains one config line away.)
- Canonical facts, not vibes — one current value per
entity.attributeslot (or a member set, for slots that hold many concurrent values); corrections supersede rather than silently overwrite, and the full version history survives. - Dreams — a bundled local extractor, or any OpenAI-compatible endpoint (a Claude model on your Max plan, a GPT-5.6 model on a ChatGPT plan, LM Studio, Ollama, vLLM), consolidates the memory stream into facts and a knowledge graph while you’re not looking.
- Lessons from its own work — successes, dead-ends, and your corrections become do/avoid guidance surfaced at the start of every session.
- A web console to watch it think — the Cortex Console above, plus cited world facts, session episodes, and document RAG.
Measured, with receipts — the full 500-question LongMemEval sweep, all six question types, and every number ships with its committed run artifact:
| LongMemEval oracle, 500 questions | naive RAG | commit-gated cascade |
|---|---|---|
| accuracy, all six question types | 0.688 | 0.690 |
| context tokens per question | ~1210 | ~883 |
| knowledge-update slice (78 of the 500) | 0.859 |
Equal accuracy to naive RAG across the whole benchmark on **~73% of the
安装
This server does not publish a one-line install command.
Open the repository installation guide 新手？先看 mcpskill.org 教程 →配置
{
"mcpServers": {
"pseudolife-memory": {
"type": "http",
"url": "http://127.0.0.1:8765/mcp"
}
}
}