LLM-driven context and memory management with wide-recall + precise-reranking RAG architecture. Features multi-dimensional retrieval (vector/timeline/knowledge graph), short/long-term memory, and complete MCP support (HTTP/WebSocket/SSE).
Run the underlying MCP server directly — without Agent-CoreX routing.
npx -y context-keeperAgent-CoreX intelligently routes which tools from redleaves/context-keeper your AI agent actually needs per request — reducing token usage and cost.
agent-corex.json
{
"mcpServers": {
"context-keeper": {
"command": "npx",
"args": [
"-y",
"context-keeper"
]
}
}
}Connect in 2 minutes. Only pay for the tools your agent actually uses.
Recommended: intelligent tool routing, lower costs
uvx agent-corex mcp add context-keeperAgent-CoreX selects only the tools your agent needs, cutting token usage by up to 60%.
Use redleaves/context-keeper directly without routing
npx -y context-keeperNew to Agent-CoreX? View setup guide →