TeleAI-UAGI/telemem
TeleMem is a high-performance drop-in replacement for Mem0, featuring semantic deduplication, long-term dialogue memory, and multimodal video reasoning.
This project helps create AI assistants and agents that can remember long conversations, understand different characters, and even process video content. It takes in dialogue and video, then outputs an AI that remembers interactions and visual information over time, without getting confused. Developers building advanced conversational AI, virtual companions, or complex narrative agents would use this.
453 stars. Available on PyPI.
Use this if you are building AI agents or virtual assistants that need to maintain consistent personalities, remember long, multi-character dialogues, or perform reasoning based on video content.
Not ideal if your AI interactions are short, single-turn, or exclusively text-based with no need for advanced memory management or multimodal understanding.
Stars
453
Forks
28
Language
Python
License
Apache-2.0
Category
Last pushed
Jan 28, 2026
Commits (30d)
0
Dependencies
10
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/embeddings/TeleAI-UAGI/telemem"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related tools
aiming-lab/SimpleMem
SimpleMem: Efficient Lifelong Memory for LLM Agents
zilliztech/memsearch
A Markdown-first memory system, a standalone library for any AI agent. Inspired by OpenClaw.
microsoft/kernel-memory
Research project. A Memory solution for users, teams, and applications.
zilliztech/GPTCache
Semantic cache for LLMs. Fully integrated with LangChain and llama_index.
RichmondAlake/memorizz
MemoRizz: A Python library serving as a memory layer for AI applications. Leverages popular...