TeleAI-UAGI/telemem
TeleMem is a high-performance drop-in replacement for Mem0, featuring semantic deduplication, long-term dialogue memory, and multimodal video reasoning.
Implements context-aware summarization, semantic clustering via LLM-based deduplication, and character-profiled memory isolation for multi-agent scenarios. Achieves millisecond-level retrieval through FAISS vector indexing with JSON metadata dual-storage, plus a complete video processing pipeline—frame extraction through caption generation to vector embedding—enabling agents to reason over video content with ReAct-style multi-step QA. Maintains API compatibility with Mem0 while targeting agentic AI systems handling long-horizon dialogues, multi-character interactions, and multimodal reasoning.
453 stars and 13 monthly downloads. Available on PyPI.
Stars
453
Forks
28
Language
Python
License
Apache-2.0
Category
Last pushed
Jan 28, 2026
Monthly downloads
13
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/GPTCache
Semantic cache for LLMs. Fully integrated with LangChain and llama_index.
zilliztech/memsearch
A Markdown-first memory system, a standalone library for any AI agent. Inspired by OpenClaw.
ascottbell/maasv
Memory Architecture as a Service — cognition layer for AI assistants. 3-signal retrieval,...
RichmondAlake/memorizz
MemoRizz: A Python library serving as a memory layer for AI applications. Leverages popular...