Pseudolife Memory MCP server

Pseudolife-MCP

<!-- mcp-name: io.github.Pseudogiant-xr/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:

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.)

• Associative memory with honest forgetting — a flat similarity store

slot (or a member set, for slots that hold many concurrent values); corrections supersede rather than silently overwrite, and the full version history survives.

• Canonical facts, not vibes — one current value per entity.attribute

(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.

• Dreams — a bundled local extractor, or any OpenAI-compatible endpoint

become do/avoid guidance surfaced at the start of every session.

• Lessons from its own work — successes, dead-ends, and your corrections

world facts, session episodes, and document RAG.

• A web console to watch it think — the Cortex Console above, plus cited

Measured, with receipts — the full 500-question LongMemEval sweep, all six question types, and every number ships with its committed run artifact:

Shortened. The full README is on GitHub.