Open source code for ICLR 2026 Paper: Evaluating Memory in LLM Agents via Incremental Multi-Turn Interactions
-
Updated
May 21, 2026 - Python
Open source code for ICLR 2026 Paper: Evaluating Memory in LLM Agents via Incremental Multi-Turn Interactions
ATM-Bench: A benchmark for long-term personalized memory QA spanning ~4 years of multimodal data (images, videos, emails). Features referential queries, evidence-grounded answering, and multi-source reasoning. Paper: "According to Me: Long-Term Personalized Referential Memory QA"
Production-ready agent implementations: SimpleAgent, ReactAgent, MultiAgent, MemoryAgent, RAG variants, and more
Template for agentic Chat & Memory Agents with Dapr runtime, UV simplicity, and OpenAI Agents SDK.
A framework for resonance-based decision-making in artificial agents, combining celestial influences, memory feedback, and symbolic emergence.
A production-ready LangGraph agent with long-term memory - built from scratch on Redis.
🐘 Local-first causal knowledge graph for AI developer memory. Tracks decisions, rejected alternatives & reasoning — not just facts. MCP-native for Claude, Cursor & VS Code.
[ICLR 2026 LLA] MemoryCD: Benchmarking Long-Context User Memory of LLM Agents for Lifelong Cross-Domain Personalization
Sovereign, persistent, worldview-aligned AI agent. Runs on your hardware. No cloud. No moral relativism. Pure truth hierarchy.
Provide community-built automation skills for OpenClaw agents to enhance task handling through browser and API integrations.
Add a description, image, and links to the memory-agent topic page so that developers can more easily learn about it.
To associate your repository with the memory-agent topic, visit your repo's landing page and select "manage topics."