Skip to main content
This page covers service-based agent integrations. First deploy a ReMe service, then choose how the agent will connect and when it should recall or record memory. For AgentScope’s in-process ReMeMiddleware, use the Python integration instead.

​
Choose an Integration Pattern

The following patterns differ in how they package service access and memory behavior: All three patterns connect to the same service boundary:
The Agent-side integration does not own the ReMe process. It selects the service interface, supplies session context, and decides when returned memory should affect an answer.

​
Skill

A Skill is the behavior layer above the service interface, not a service or transport. The bundled skills/reme_memory/ uses the ReMe CLI; another host can apply the same behavior through MCP tools or HTTP. To use the Skill, install the complete skills/reme_memory/ directory in the host’s skill location. Keep SKILL.md and its supporting rules together. The host should then:
  1. Search, then read relevant files before answering about earlier conversations, preferences, decisions, or project history.
  2. Record only durable facts, preferences, decisions, and lessons; do not store secrets or sensitive information by default.
  3. Call auto_memory after a useful session or when stable information appears, using a stable session_id from the host lifecycle.
  4. Let ReMe’s cron run auto_dream, or trigger it from the host lifecycle.
  5. Treat ReMe as memory input; the Agent still decides whether and how to use the result.
The Skill does not start ReMe or invent missing conversation history.

​
Plugin

A plugin packages the pieces needed by a specific host, such as service connection settings, tools, Skills, and session hooks. It should point to an already deployed ReMe service and use the host lifecycle for automatic recall or recording. Installing a plugin does not imply that it starts or owns ReMe.

​
Maintained Integrations

ReMe currently includes maintained integration packages for these hosts: The following sections cover their host-specific setup and verification.

​
Claude Code

The Claude Code plugin combines MCP recall, a recall skill, and asynchronous session recording. It connects to a shared ReMe MCP server and does not start ReMe itself.

​
1. Start ReMe

Install ReMe through the ReMe Quick Start, then keep the MCP service running:
The default endpoint is http://127.0.0.1:2333/mcp. Automatic recording also requires the configured LLM environment.

​
2. Install the Plugin

Clone the ReMe repository. From its root, add the bundled marketplace and install the plugin in Claude Code:
Restart Claude Code, run /mcp, and confirm that the reme server and tools are connected. The package is located under plugins/claude_code/. Its .mcp.json defines the server URL, the reme-memory skill controls recall, and hooks/auto_memory.py calls auto_memory_cc after a session ends.

​
3. Verify Recall and Recording

Write a distinctive memory from a terminal:
Ask Claude Code what to run before submitting changes. It should search and read ReMe before answering. Next, end a conversation containing durable information and search for a distinctive phrase after a short delay:
The Stop hook runs asynchronously and is best-effort: an unavailable ReMe service does not block Claude Code. If you change the server port, update plugins/claude_code/reme/.mcp.json too. See the plugin README for hook overrides and log locations.

​
QwenPaw

QwenPaw integrates through the bundled ReMe Skill described above. The Skill defines when the Agent should recall or record; the ReMe service handles persistence, indexing, and refinement.

​
1. Start ReMe

Keep the default HTTP service running:
Conversation refinement and consolidation require the LLM environment described in the Quick Start model setup.

​
2. Install the ReMe Skill

Install the repository’s complete skills/reme_memory/ directory in QwenPaw’s skill location. Keep SKILL.md and its behavior rules together. Once loaded, QwenPaw should:
  • search and read before answering about past conversations, preferences, decisions, or project history;
  • record durable information with auto_memory rather than saving every turn;
  • obtain explicit consent before storing sensitive information;
  • provide a stable session_id from its session lifecycle.
skills/qwenpaw_memory directly maintains MEMORY.md and memory/*.md; it does not call ReMe. Use skills/reme_memory for ReMe integration.

​
3. Verify Recall and Recording

Write a test memory from a terminal:
Ask QwenPaw how you prefer technical explanations. Confirm that it searches ReMe and reads the file before answering. After providing another durable fact, end the session and search for its keywords. If the installed QwenPaw version has no session-end hook, let the application call auto_memory explicitly or enable recall only; do not invent a missing message history.