TiMEM-AI/timem
Temporal-Hierarchical Memory Consolidation for Long-Horizon Conversational Agents
This project helps create AI assistants and conversational agents that can remember long-term interactions and user details. It takes raw conversation data and turns it into a structured, multi-level memory, allowing the AI to recall relevant information and maintain a consistent persona over time. It's designed for anyone building AI assistants, customer support bots, educational AI, or productivity tools that need to remember ongoing user contexts.
Use this if you need your AI assistant or agent to remember long-term conversation history, user preferences, and evolving personal details across multiple interactions or sessions.
Not ideal if your AI interactions are short, stateless, or do not require the agent to build a persistent understanding of the user over time.
Stars
82
Forks
4
Language
Python
License
—
Category
Last pushed
Feb 07, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/llm-tools/TiMEM-AI/timem"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
open-thought/reasoning-gym
[NeurIPS 2025 Spotlight] Reasoning Environments for Reinforcement Learning with Verifiable Rewards
Hmbown/Hegelion
Dialectical reasoning architecture for LLMs (Thesis → Antithesis → Synthesis)
LLM360/Reasoning360
A repo for open research on building large reasoning models
bowang-lab/BioReason
BioReason: Incentivizing Multimodal Biological Reasoning within a DNA-LLM Model | NeurIPS '25
TsinghuaC3I/Awesome-RL-for-LRMs
A Survey of Reinforcement Learning for Large Reasoning Models