Crosmos
About
Persistent memory for AI agents. Give your coding assistant organizational context that compounds — search memories with hybrid retrieval, store anything with auto entity extraction, and query a living knowledge graph that gets smarter over time.
Explore
- Graph-native memory with entity and relationship linking
- Temporal – every fact is timestamped for time‑travel queries
- Hybrid retrieval (semantic, keyword, graph, temporal)
- Automatic entity and relationship extraction from raw text
- Multi‑space isolation for projects, teams, or agents
- Four retrieval signals fused into a single ranked result
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
CrosmosCommand (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
``bash`
npx @crosmos/crosmos-mcp setup
This auto-detects your installed MCP clients and configures everything. Get your API key at console.crosmos.dev.
Manual Config
json``
{
"mcpServers": {
"crosmos-memory": {
"command": "npx",
"args": ["-y", "@crosmos/crosmos-mcp"],
"env": {
"CROSMOS_API_KEY": "csk_your_key_here"
}
}
}
}
Supported Clients
Claude Desktop · Claude Code · Cursor · VS Code · Windsurf · opencode · Cline · Roo-Cline · Zed
Why Crosmos?
- Graph-native — memories are linked as entities and relationships, not just stored as flat vectors
- Temporal — every fact is timestamped; query your knowledge graph as it existed at any point in time
- Hybrid retrieval — four parallel signals (semantic, keyword, graph, temporal) fused into a single ranked result
- Auto-extraction — send raw text; Crosmos extracts structured facts, entities, and relationships automatically
- Multi-space — isolate memory by project, team, or agent with named spaces
Links
- Website
- Docs
- Console
- GitHub
search_memories
Search memories in Crosmos Memory Engine using hybrid retrieval. Combines semantic (vector), keyword (full-text), and graph-based retrieval. Requires a space_id — call list_spaces if you don't have one yet.
add_memory
Add new memories to Crosmos Memory Engine. Content is processed through an extraction pipeline that identifies entities, relationships, and creates structured knowledge graph entries. Requires a space_id — call list_spaces if you don't have one yet.
health_check
Check the health status of the Crosmos Memory Engine API
list_spaces
List all memory spaces owned by the authenticated user. Call this to discover available space IDs needed by search_memories and add_memory.
| Tool | Description |
|------|-------------|
| crosmos_search_memories | Hybrid retrieval — semantic + keyword + graph traversal in one query |
| crosmos_add_memory | Store any content with automatic entity and relationship extraction |
| crosmos_list_spaces | List available memory spaces |
| crosmos_health_check | Verify API connectivity and status |
Claude Desktop / Cursor
Paste into your MCP client config file to install this server.
{
"mcpServers": {
"crosmos": {
"crosmos-memory": {
"command": "npx",
"args": [
"-y",
"@crosmos/crosmos-mcp"
],
"env": {
"CROSMOS_API_KEY": "<YOUR_API_KEY>"
}
}
}
}
}McpServers
{
"crosmos-memory": {
"command": "npx",
"args": [
"-y",
"@crosmos/crosmos-mcp"
],
"env": {
"CROSMOS_API_KEY": "<YOUR_API_KEY>"
}
}
}What is Crosmos?
Crosmos is a persistent memory layer for AI agents. Instead of starting every conversation from scratch, your agent can store and retrieve organizational knowledge across sessions — powered by a temporal knowledge graph with hybrid retrieval.Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.
