Open source code for ICLR 2026 Paper: Evaluating Memory in LLM Agents via Incremental Multi-Turn Interactions
-
Updated
Sep 25, 2026 - Python
Open source code for ICLR 2026 Paper: Evaluating Memory in LLM Agents via Incremental Multi-Turn Interactions
Cortex: A Bidirectionally Aligned Embodied Agent Framework for Long-horizon Manipulation
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.
[EMNLP 2026] MemoryCD: Benchmarking Long-Context User Memory of LLM Agents for Lifelong Cross-Domain Personalization
A production-ready LangGraph agent with long-term memory - built from scratch on Redis.
Building Customer Support AI That Remembers With Hindsight
Claude Code MCP native extension delivering a zero-human closed loop: Auto Bug Retrieval → Intelligent Troubleshooting → Automated Structured Accumulation. Equips Claude Code with long-term troubleshooting memory and establishes a reusable bug knowledge library for individuals and teams.
🐘 Local-first causal knowledge graph for AI developer memory. Tracks decisions, rejected alternatives & reasoning — not just facts. MCP-native for Claude, Cursor & VS Code.
Vraksha remembers so you can focus on creating.
آزمایشگاه عملی ساخت AI Agentها به زبان فارسی
Fictional people live on the other side of the page. NMA is the door.
Sovereign, persistent, worldview-aligned AI agent. Runs on your hardware. No cloud. No moral relativism. Pure truth hierarchy.
Persistent memory layer for AI coding assistants — Chrome extension + FastAPI backend + local Ollama LLM, 100% private
Librarian: a Qwen Cloud memory agent that writes knowledge into a Markdown wiki and retires superseded claims from answers but keeps those claims auditable (Global AI Hackathon Series, Track 1: MemoryAgent)
Qwen Cloud-powered persistent memory agent for codebases (Global AI Hackathon 2026, Track 1: MemoryAgent). Files report, projects know, tasks prove, humans ask.
A memory agent that revises itself — conflict-aware memory and decay-based compression, built on Qwen Cloud
To associate your repository with the memory-agent topic, visit your repo's landing page and select "manage topics."