Stashbird: Efficient Speaker-Indexed Memory for Conversational Agents
cs.AI, cs.LG
Submitted: 2026-09-28
Updated: 2026-09-28
Code: https://github.com/memodb-io/memobase
Sources
- AgentBench: Evaluating LLMs as Agents
- From Local to Global: A Graph RAG Approach to Query-Focused Summarization
- Mem0: Building Production-Ready AI Agents with Scalable Long-Term Memory
- Zep: A Temporal Knowledge Graph Architecture for Agent Memory
- Hindsight is 20/20: Building Agent Memory that Retains, Recalls, and Reflects
- Mnemis: Dual-Route Retrieval on Hierarchical Graphs for Long-Term LLM Memory
- Governing Evolving Memory in LLM Agents: Risks, Mechanisms, and the Stability and Safety Governed Memory (SSGM) Framework
- MemOS: A Memory OS for AI System
- Evaluating Long-Horizon Memory for Multi-Party Collaborative Dialogues
- GroupMemBench: Benchmarking LLM Agent Memory in Multi-Party Conversations
- What Deserves Memory: Adaptive Memory Distillation for LLM Agents
- A-MEM: Agentic Memory for LLM Agents
Related papers
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- Agents' Last Exam
- The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
- MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
- Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems