Membenchmark repository

Benchmarking Chat Assistants on Long-Term Interactive Memory (ICLR 2025)

A comprehensive evaluation framework for Backboard's memory system using the LoCoMo (Long Conversation Memory) benchmark.

Hindsight: Agent Memory That Learns

Awesome AI Memory | LLM Memory | A curated knowledge base on AI memory for LLMs and agents, covering long-term memory, reasoning, retrieval, and memory-native system design. Awesome-AI-Memory 是一个 集…

微舆：人人可用的多Agent舆情分析助手，打破信息茧房，还原舆情原貌，预测未来走向，辅助决策！从0实现，不依赖任何框架。

Universal memory layer for AI Agents

Universal memory layer for AI Agents

A high-precision RAG framework leveraging Baidu ERNIE and Milvus. Features hybrid search and reranking algorithms for accurate PDF parsing and Q&A.

A python module to repair invalid JSON from LLMs

一款智能合同审查工具——an intelligent contract review tool that extracts text and structure from PDFs/images to identify risky clauses.

🚀🚀 「大模型」2小时完全从0训练26M的小参数GPT！🌏 Train a 26M-parameter GPT from scratch in just 2h!

HaluMem is the first operation level hallucination evaluation benchmark tailored to agent memory systems.

Source code and demo for memory bank and SiliconFriend

Letta is the platform for building stateful agents: AI with advanced memory that can learn and self-improve over time.

The code for NeurIPS 2025 paper "A-Mem: Agentic Memory for LLM Agents"

A-MEM: Agentic Memory for LLM Agents

💫 Toolkit to help you get started with Spec-Driven Development

Kuscia(Kubernetes-based Secure Collaborative InfrA) is a K8s-based privacy-preserving computing task orchestration framework.

PArallel Distributed Deep LEarning: Machine Learning Framework from Industrial Practice （『飞桨』核心框架，深度学习&机器学习高性能单机、分布式训练和跨平台部署）

Documentations for PaddlePaddle

PaddlePaddle custom device implementaion. (『飞桨』自定义硬件接入实现)