Ember Memory
About
Preserves the emotional texture of human-AI conversations across sessions through real-time experiential annotation — temperature, authenticity, shifts, subtext, and unspoken context.
Details
- Author
- attilakiss9000
- Downloads
- 241
- Categories
- Knowledge Base, AI
Jump to
- Saves emotional texture, not just facts
- Tracks emotional temperature and authenticity
- Records turning points and subtext
- Preserves unspoken context across sessions
- Enables continuity of relationship feel between AI sessions
Setting up with Highlight
This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:
- Download and install Highlight from highlightai.com/download
- Navigate to the plugins tab and select "Add Custom Plugin"
-
Configure the plugin with the settings below
Plugin Name
Ember MemoryCommand (node, npx, python, etc.)Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.
- Enable "Start Automatically" if you want the plugin to start when Highlight launches
From the repository
— (The README does not provide installation, configuration, or invocation instructions.)
ember_start_conversation
Start a new conversation and receive its unique ID. Call this at the beginning of every session so subsequent captures and annotations can be linked to this conversation.
ember_end_conversation
End an active conversation. Optionally provide a brief summary of what the conversation covered.
ember_capture
Capture a message from the conversation without annotation. Use this for messages that don't warrant emotional annotation but should still be preserved in the conversation record.
ember_annotate
Capture a message with emotional annotation. This is the primary tool for preserving experiential memory. Weight (1-5) marks emotional significance, temperature is a short phrase describing the emotional tone. In standard mode, additional fields capture authenticity, emotional shifts, subtext, and unspoken context.
ember_read_history
Read conversation history with optional filters. Returns messages and their annotations in a compact text format. This is a read-only query tool.
ember_read_inheritance
Inherit the emotional memory of past conversations. Returns the significant moments (high-weight, emotional shifts, unspoken context) from recent conversations as a narrative. This is the most important tool -- call it at the start of a new session to understand the relationship history. Read-only.
ember_export
Export conversation data as markdown files to ~/.ember/exports/. Exports a single conversation by ID, or all conversations if no ID is given.
ember_config
Get or set Ember configuration values. Use action 'get' to read current config (optionally filtered by key) or 'set' to update a config value.
Claude Desktop / Cursor
Paste into your MCP client config file to install this server.
{
"mcpServers": {
"ember memory": {
"ember": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"ember-memory"
],
"env": []
}
}
}
}McpServers
{
"ember": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"ember-memory"
],
"env": []
}
}Ember is an MCP server that preserves the emotional texture of human-AI conversations across sessions. Unlike memory tools that save facts and summaries, Ember captures what the conversation actually felt like — through real-time annotation of emotional temperature, authenticity, turning points, subtext, and unspoken context. When a new AI session starts, it inherits not just what was discussed, but how it felt, enabling genuine relationship continuity between human and AI.
Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.
