TeleMem is a high-performance drop-in replacement for Mem0, featuring semantic deduplication, long-term dialogue memory, and multimodal video reasoning.
Quick Install
Copy the config for your editor. Some servers may need additional setup — check the README.
Claude Desktop
Claude Code
Cursor
Add to claude_desktop_config.json:
{
"mcpServers": {
"telemem": {
"command": "uvx",
"args": [
"telemem"
]
}
}
}📋 Copy
Run in terminal:
claude mcp add telemem uvx telemem📋 Copy
Add to .cursor/mcp.json:
{
"mcpServers": {
"telemem": {
"command": "uvx",
"args": [
"telemem"
]
}
}
}📋 Copy
Or install with pip: pip install telemem
README Excerpt
<p align="center"> <a href="https://github.com/TeleAI-UAGI/telemem"> <img src="./assets/TeleMem.png" width="40%" /> </a> </p> <h1 align="center"> TeleMem: Building Long-Term and Multimodal Memory for Agentic AI </h1> <p align="center"> <a href="https://arxiv.org/abs/2601.06037"> <img src="https://img.shields.io/badge/arXiv-Paper-red" alt="arXiv">
Tools (19)
TELEMEM_CONFIG batch clip_search_tool decode_video_to_frames filters frame_inspect_tool global_browse_tool infer init_single_video_db limit memory_type messages metadata process_video prompt query rerank threshold user_id
Topics
agent agent-memory ai-agents character-memory conversational-ai faiss llm long-term-memory mcp mem0 memory model-context-protocol multimodal rag semantic-search