memgpt 开源项目推荐（41 个）

letta-ai /letta-code

随经验自我改进的智能体

NirDiamant /Agent_Memory_Techniques

面向 LLM 的智能体记忆：30 个可运行的 Jupyter notebook，涵盖对话缓冲区、向量存储、知识图谱、情景记忆与语义记忆、MemGPT、Mem0、Letta、Zep、Graphiti、LoCoMo 基准以及生产模式。

PromptEngineer48 /MemGPT-AutoGEN-LLM

Run MemGPT-AutoGEN-Local LLM Together

Josephrp /DataTonic

🌟DataTonic : A Data-Capable AGI-style Agent Builder of Agents , that creates swarms , runs commands and securely processes and creates datasets, databases, visualisations, and analyses.

Utshav-paudel /300DaysOFMachineLearning-DeepLearning-LLM

Hello everyone this repo will contain my journey of machine learning and DeepLearning with some exciting projects

Josephrp /scitonic

👩🏻‍🔬🧪SciTonic is a highly adaptive technical operator of agents that can produce complexe analyses on technical data with high performance & on-the-fly . You can ask it what you want and it will respond with quality everytime.

tevfik /gleann

A lightweight, high-performance AI/RAG workspace and autonomous agent framework implemented in Go. Inspired by the Leann RAG backend architecture

steviepinero /AutogenMemgpt

My implementation of autogen and memgpt agents that work together to create simple scripts and help plan out larger projects.

MonishKanungo /MarkMem

A memory layer for chatbots that stores memory as plain markdown in a git repo

ksm26 /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.

pgmnemo /pgmnemo

Multi-agent memory substrate for PostgreSQL — provenance-gated, vector-hybrid recall

iampantherr /SecureContext

Persistent memory + security layer for Claude Code (MCP plugin). Agents remember your project across sessions (~87% fewer context tokens), every tool call lands in a tamper-evident HMAC audit chain, and skills are AST-scanned + HMAC-verified before they run. 100% local: PostgreSQL + Ollama, no cloud, MIT.

csnyder256 /RAG-OS

Build your own always-on personal AI OS: a self-hosted agent that dispatches coding tasks, maintains a git-Markdown knowledge base, and runs on your hardware. A DIY alternative to Letta, mem0, Hermes Agent, and AutoGPT.

omerakben /opus-nx

🧠 Open-source AI reasoning research platform — persistent reasoning graphs, multi-agent swarms, Graph-of-Thoughts, and MemGPT-style memory. Built with Claude Opus 4.6 by Anthropic. Explore, verify, and fork AI thinking in real-time.

actuallyrizzn /broca-2

Plugin-based, MCP'able comms middleware for Letta agents.

H0NEYP0T-466 /lettaXrag

🤖 Full-stack conversational AI using a Letta (MemGPT) + RAG hybrid architecture for long-term memory, context persistence, and grounded responses. Built with FastAPI, React, FAISS, and MongoDB, featuring Isabella — a personality-driven assistant with document ingestion, structured memory, logging, and a terminal-style streaming chat UI.

Anandesh-Sharma /awesome-agentic-memory

🧠 The definitive curated map of memory for LLM agents — frameworks, research papers, benchmarks, taxonomy & deep dives.

ejentum /letta-ejentum

Letta integration for the Ejentum Reasoning Harness. 8 Python functions (4 harnesses × dynamic + adaptive) registered via tools.upsert_from_function.

ssmurfgg04-gif /context-m

Deterministic agent memory. μ=0. Free, local, forever. Mem0-compatible.

tryAGI /Letta

C# SDK for the Letta API -- stateful AI agents with persistent memory, tools, and multi-agent groups