agent-memory
There are 5 repositories under agent-memory topic.
kayba-ai / agentic-context-engine
🧠 Make your agents learn from experience. Based on the Agentic Context Engineering (ACE) framework.
Language:Python 557- eionLanguage:Go 131
Shy2593666979 / AgentChat
AgentChat 是一个基于 LLM 的智能体交流平台，内置默认 Agent 并支持用户自定义 Agent。通过多轮对话和任务协作，Agent 可以理解并协助完成复杂任务。项目集成 LangChain、Function Call、MCP 协议、RAG、Memory、Milvus 和 ElasticSearch 等技术，实现高效的知识检索与工具调用，使用 FastAPI 构建高性能后端服务。
Language:Python 77aiurda / cursor10x-mcp
The Cursor10x MCP is a persistent multi-dimensional memory system for Cursor that enhances AI assistants with conversation context, project history, and code relationships across sessions.
Language:JavaScript 69baryhuang / mcp-openmemory
Simple standalone MCP server giving Claude the ability to remember your conversations and learn from them over time.
Language:JavaScript 63DevContext is a cutting-edge Model Context Protocol (MCP) server designed to provide developers with continuous, project-centric context awareness. Unlike traditional context systems, DevContext continuously learns from and adapts to your development patterns and delivers highly relevant context providing a deeper understanding of your codebase.
Language:HTML 37nunyabiznessyoubeezy / mcp-server-macos-use
AI agent that controls computer with OS-level tools, MCP compatible, works with any model
Language:Swift 22AIAnytime / Agent-Memory-Playground
Agent Memory Playground: AI Agent Memory Design & Optimization Techniques
Language:Python 21nowledge-co / nowledge-mem
Memory and context manager just works.
langchain-ai / agents-from-scratch-ts
LangGraph Typescript Agents Notebooks: email, human in the loop, memory
Language:Jupyter Notebook 18TeleAI-UAGI / Awesome-Agent-Memory
Curated papers, systems, and benchmarks on memory for LLMs/MLLMs—long-term context, retrieval, and reasoning.
Hassanali4 / applescript-mcp
MCP server that execute applescript giving you full control of your Mac
Language:Python 11honeybluesky / my-apple-remembers
A lightweight MCP server that integrates with Apple Notes to create a personal memory system for AI. Easily recall and save information from your Mac using simple AppleScript commands. Compatible with all macOS versions with minimal setup requirements.
Language:Python 9alanchelmickjr / memoRable
Excuse me sir? Did you order Special Sauce with that Agentic workflow?
Language:JavaScript 7ksm26 / LLMs-as-Operating-Systems-Agent-Memory
This repository introduces the Letta framework, empowering developers to build LLM-based agents with long-term, persistent memory and advanced reasoning capabilities. It leverages concepts from MemGPT to optimize context usage and enable multi-agent collaboration for real-world applications like research, HR, and task management.
ai-applicationsai-frameworkai-innovationai-researchartificial-intelligenceintelligent-agentsllmsmemgptmemory-managementmulti-agent-systemspersistent-memoryadvanced-reasoningagent-memoryai-with-memorycollaborative-agentscontext-optimizationletta-frameworkllm-innovationmemory-agentsmemory-enhanced-agentsLanguage:Jupyter Notebook 6Poppyqueen / LLM_Memory_Manager
This project is a concept demonstration of a layered memory system for Large Language Models. It includes a CLI chatbot and an AI playing Zork I with 'FROTZ' as examples. The true value lies in the memory_handle.py module, designed for easy integration into any Python project requiring LLM memory management (AI agents, games, etc.).
Language:Python 6Abbas-Asad / Agentic-AI
Learn Agentic AI with notes, resources, and practice code covering Generative AI basics, OpenAI agents SDK, prompt engineering, memory, model settings, design patterns and many more.
Language:Python 5Rathesh2727 / devcontext
DevContext is a cutting-edge Model Context Protocol (MCP) server designed to provide developers with continuous, project-centric context awareness. Unlike traditional context systems, DevContext continuously learns from and adapts to your development patterns and delivers highly relevant context providing a deeper understanding of your codebase.
Language:JavaScript 4BjornMelin / codeforge
🤖 CodeForge AI: An autonomous multi-agent coding system powered by LangGraph for agentic software development and automated workflows. SOTA custom agentic GraphRag, shared-state memory, auto-model routing for cost optimization, and a range of custom tooling.
Language:Python 3Million19 / llm_to_mcp_integration_engine
The llm_to_mcp_integration_engine is a communication layer designed to enhance the reliability of interactions between LLMs and tools (like MCP servers or functions).
Language:Python 3coalesce-labs / catalyst
Token-efficient Claude Code workspace with parallel agents and persistent memory. Research → Plan → Implement → Validate workflow.
Language:Shell 2Brandtweary / cymbiont
Knowledge graph agent for personal knowledge management
Language:Rust 1- Language:Python 1
OctavianTocan / mem0-api
A production-ready FastAPI service for semantic memory management using Mem0. Store, search, and retrieve AI agent memories with vector embeddings and LLM-powered inference. Perfect for building context-aware conversational AI.
Language:Python 1puppe1990 / memory_bank_rails
Rails engine that bootstraps AI-ready docs and project memory with SPEC-driven workflows and guides for Rails teams.
Language:Ruby 1redis-developer / my-jarvis-alexa-skill
My Jarvis is an Alexa skill that can remember and recall memories from users, providing more contextual answers. It utilizes the Redis Agent Memory Server as a memory layer to provide instant-like responses, making your Alexa device appear more human-like in conversation.
Language:Java 1sushant1827 / RAG-AI-Agent-2.0
AI-powered assistant that indexes Google Drive files to a vector store on upload and answers user queries based on the content.
Ajay6093 / Agentic-Context-Engineering
💬 Engage in continuous chat while dynamically building a JSONL playbook, enhancing insights and strategies with each interaction.
Language:Pythond-o-hub / rust-self-learning-memory
A modular Rust-based self-learning episodic memory system for AI agents, featuring hybrid storage with Turso (SQL) and redb (KV), async execution tracking, reward scoring, reflection, and pattern-based skill evolution. Designed for real-world applicability, maintainability, and scalable agent workflows.
Language:Rustnemori-ai / nemori-reason-over-memory-tool
Reason over memory to produce contextual guidance — a Nemori-AI subproject on memory.
