telemem
TeleMem is a high-performance drop-in replacement for Mem0, featuring semantic deduplication, long-term dialogue memory, and multimodal video reasoning.
What is telemem?
TeleMem is a high-performance drop-in replacement for Mem0, featuring semantic deduplication, long-term dialogue memory, and multimodal video reasoning.
Overview of telemem
What it is
TeleMem is an agent memory management layer that serves as a high-performance drop-in replacement for Mem0. It is designed for complex scenarios involving multi-turn dialogues, character modeling, long-term information storage, and semantic retrieval. TeleMem implements video understanding, multimodal reasoning, and visual question answering capabilities through a pipeline of video frame extraction, caption generation, and vector database construction. The project aims to use an agent's hindsight to improve its foresight. It runs fully local by default, using Qwen and FAISS, with no cloud service or paid tier. The API is compatible with Mem0, so existing Mem0 code can continue to work with a single import change.
Key features
- Automatic memory extraction: extracts and structures key facts from dialogues.
- Semantic clustering and deduplication: uses LLMs to semantically merge similar memories, reducing conflicts and improving consistency.
- Character-profiled memory management: builds independent memory archives for each character in a dialogue, ensuring precise isolation and personalized management.
- Efficient asynchronous writing: employs a buffer and batch-flush mechanism for high-performance, stable persistence.
- Precise semantic retrieval: combines FAISS and JSON dual storage for fast recall and human-readable auditability.
- Mem0-compatible API: add() and search() accept the same arguments and return the same result shapes.
- Multimodal video memory: full video processing pipeline with ReAct-style multi-step reasoning QA.
Use cases
- Multi-character virtual agent systems - Long-memory AI assistants (e.g., customer service, companionship, creative co-pilots)
- Complex narrative and world-building in virtual environments - Dialogue scenarios with strong contextual dependencies - Video content QA and reasoning - Multimodal agent memory management - Long video understanding and information retrieval
Getting started
pip install telemem uvx telemem
License and pricing
Licensed under Apache-2.0. Open source and free.
Based on the project's public README and repository metadata.