pseudogiant-xr/pseudolife-mcp

このページは AI により自動翻訳されています。技術的な詳細は原文をご確認ください。原文を見る

6 stars 1 forks 品質 83 トレンド 26Apache-2.0

Persistent long-term memory for Agents — an MCP server with an associative memory bank, a canonical-fact cortex, sleep-like dream consolidation, and a web console. Not quite alive.

概要

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. - — 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.) - — one current value per entity.attribute slot (or a member set, for slots that hold many concurrent values); corrections supersede rather than silently overwrite, and the full version history survives. - — a bundled local extractor, or any OpenAI-compatible endpoint (a Claude model on your Max plan, a GPT-5.

README

以下は原文 README の抜粋です。原文を見る。

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.

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.attribute slot (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	~~0.936~~ (retired — see below)

Equal accuracy to naive RAG across the whole benchmark on **~73% of the

GitHub で README 全文を見る

インストール

This server does not publish a one-line install command.

Open the repository installation guide MCP 初心者？mcpskill.org のガイドから始めましょう →

設定

{
  "mcpServers": {
    "pseudolife-memory": {
      "type": "http",
      "url": "http://127.0.0.1:8765/mcp"
    }
  }
}