记忆梦境引擎 · AI 的睡眠系统 — Claude Code MCP server
Simulates sleep cycles for agents: extracts facts without LLM calls, scores signals, and trims outdated entries via an Ebbinghaus decay curve.
Open on GitHubWhat 记忆梦境引擎 · AI 的睡眠系统 does
The server introduces a biological sleep cycle into persistent agent memory. Running every 180 minutes, it executes a five-stage pipeline: signal collection, scoring, writing, optimization, and idea sprouting. Fact extraction relies entirely on standard regular expressions across English and Chinese text without consuming model tokens. Retention follows an Ebbinghaus decay model with a 30-day half-life, letting unused notes fade into archives while repeated lookups reinforce memory weight.
The underlying logic in server.py exposes six MCP tools. Clients can trigger regex extraction with extract_facts, evaluate relevance via score_signal, inspect decay dynamics in decay_report, or run cycle tests using simulate_dream. Connections operate over standard input/output or streamable HTTP on port 8770.
The setup requires Python 3.9+ and the mcp>=2.1 package. In cron jobs, agent sub-processes often run without memory write privileges, silently skipping stages three and four for items scored 70 or higher. That constraint requires scheduling periodic interactive sessions to flush the accumulated backlog.
What it helps with
- extract dialogue facts using regex without LLM token expenses
- trim obsolete agent memories along an Ebbinghaus decay curve
- score decision and correction signals before persistent storage
- detect clustered memory notes ready for article drafts
Example prompts for the agent
- Run
extract_factson our recent chat to pull out confirmed decisions - Check memory retention with
decay_reportto see what is ready for archival - Use
score_signalto determine whether this correction belongs in long-term memory
How to install 记忆梦境引擎 · AI 的睡眠系统
Install
The MCP registry has no launch command for it: see the repository README
Step by step, with commands for each platform: How to add an MCP server to Claude Code, Codex, Cursor, VS Code, Gemini CLI and more
Questions about 记忆梦境引擎 · AI 的睡眠系统
How to install 记忆梦境引擎 · AI 的睡眠系统?
Clone the repository using git clone https://gitee.com/savantcat/memory-dream-engine.git, enter the directory, and run pip install "mcp>=2.1". Next, register the server in your MCP client configuration using the command python server.py.
What does 记忆梦境引擎 · AI 的睡眠系统 do?
It manages long-term agent memory by extracting facts, filtering signal noise, and decaying unused entries over time. Processing relies on local regex matching and math scoring without external LLM inference costs.
Why does memory writing fail in cron environments?
Background cron sub-processes in many agent frameworks lack permissions to execute memory write actions. This silently blocks stages three and four, requiring manual interactive sessions to flush queued memories scored 70 and higher.
