Agent frameworks & infrastructure

Agent memory & context

4,032 agents · most starred first

Agent memory & context, page 32 of 41

llama-index-storage-chat-store-upstash

llama-index storage-chat-store upstash integration

llama-index-storage-chat-store-yugabytedb

llama-index storage-chat-store yugabytedb integration

llama-index-storage-kvstore-redis

llama-index kvstore redis integration

llama-index-storage-kvstore-s3

llama-index kvstore s3 integration

llama-index-storage-kvstore-tablestore

llama-index kvstore tablestore integration

llamaindex-dakera

LlamaIndex integration for the Dakera AI memory platform

llamaindex-goodmem

Native LlamaIndex retrieval, Document ingestion and agent tools for GoodMem.

llamaindex-soul

The soul ecosystem for LlamaIndex: persistent memory, identity, database schema intelligence, and SoulMate API integration.

llamapersonalization

User profile management, preference modeling, and personalization features for LlamaAI Ecosystem

llamate

A memory-augmented framework for LLMs

llm-cache-guard

Prevent LLM cache poisoning with Confidence Gap Analysis — intent-aware thresholds, zero false serves

llm-cache-lite

Lite library for local caching of LLM API requests

llm-cache-optimizer

Agent Cache Runtime for building cache-aware LLM applications.

llm-cache-plugin

Check whether you've already run this prompt before calling the LLM

llm-cache-pro

A drop-in, model-agnostic cache for Large Language Model API calls

llm-cache-proxy

Local SQLite cache for OpenAI and Anthropic API calls. One env var, 60-80% cheaper dev loops.

llm-cache-toolkit

Lightweight caching layer for LLM API responses with TTL and size limits

llm-context-engineering

A middleware layer for managing, budgeting, and optimizing LLM context windows.

llm-context-forge

Production-grade LLMOps infrastructure for context window management, token counting, document chunking, and compression

llm-context-manager

Add your description here

llm-context-providers
llm-context-router

Scope your AI context before it explodes

llm-contextkit

Composable building blocks for LLM context engineering

llm-cortex-memory

Portable, model-agnostic memory layer for LLM conversations

llm-ctx-mgr

A middleware layer for managing, budgeting, and optimizing LLM context windows.

llm-dialog-manager

A Python package for managing LLM chat conversation history

llm-elasticsearch-cache

[IMPORTANT: This library is now part of LangChain, follow its official documentation] A caching layer for LLMs that exploits Elasticsearch, fully compatible with LangChain caching, both for chat and embeddings models.

llm-engram

Durable, explainable long-term memory for the llm CLI, powered by Engram (Lumetra)

llm-hippocampus

LLM Hippocampus — a Context Engineering playground

llm-kelt

Framework for collecting and managing LLM context

llm-llm-ctx-mgr

A middleware layer for managing, budgeting, and optimizing LLM context windows.

llm-long-term-memory

Give your AI agents persistent, searchable long-term memory with pluggable storage backends

llm-lucid-memory

Lucid Memory - Modular reasoning graph for LLMs

llm-mapreduce

MapReduce-inspired framework for extending context windows in large language models

llm-mem-ai

A LLM Memory Cache package

llm-memory

A memory management system for large language models

llm-memory-sdk

Currently for internal use only.

llm-response-cache

SQLite-backed LLM response cache. Exact match + fuzzy match. Decorator API. Zero mandatory server dependencies.

llm-semantic-cache

Multi-tier caching platform for LLM embeddings, semantic search, and graph-based conversation memory

llm-smartmem

Smart memory management for LLM conversations - topic-aware compression that just works

llm-tools-memory

Memory tools for LLM

llm-user-memory

Transparent memory system for LLM

llmdrive

Cross-LLM memory portability tool — user-owned context vault across Claude, ChatGPT, Gemini, and Ollama

llmemory

High-performance document memory system with vector search capabilities for Python applications

llmesh-llive

Self-evolving modular memory LLM framework — biological memory × formal verification × industrial IoT mesh × TUI HITL

llmfile

WIP

llmfs

A filesystem-metaphor memory layer for LLMs and AI agents

llmunchies

A lightweight, model-agnostic context engine for LLMs. Feed your model tasty context.

long-running-agents

A Pydantic AI agent that remembers across sessions, can create its own tools, and delegates to specialists

madb-anthropic

Drop-in Anthropic client with MADB causal memory. One import, every turn persisted.

maximem-synap-autogen

Synap memory integration for AutoGen / AG2

maximem-synap-claude-agent

Synap memory integration for Anthropic's Claude Agent SDK

maximem-synap-crewai

Synap memory integration for CrewAI

maximem-synap-haystack

Synap memory integration for Haystack — SynapMemoryStore + retriever/writer components

maximem-synap-langchain

Synap memory integration for LangChain and LangGraph

maximem-synap-langgraph

Synap memory integration for LangGraph — BaseStore + BaseCheckpointSaver

maximem-synap-livekit-agents

Synap memory integration for LiveKit Agents — preload long-term memory, record turns, expose Synap as LLM tools

maximem-synap-llamaindex

Synap memory integration for LlamaIndex

maximem-synap-microsoft-agent

Synap memory integration for Microsoft Agent Framework

maximem-synap-nemo-agent-toolkit

Synap memory plugin for NVIDIA NeMo Agent Toolkit (NAT)

maximem-synap-openai-agents

Synap memory integration for OpenAI Agents SDK

maximem-synap-pydantic-ai

Synap memory integration for Pydantic AI

maximem-synap-semantic-kernel

Synap memory integration for Microsoft Semantic Kernel

mcal-ai-autogen

Microsoft AutoGen integration for MCAL - Goal-aware memory for multi-agent systems

mcal-ai-crewai

CrewAI integration for MCAL - Goal-aware memory for AI agent crews

mcal-ai-langgraph

LangGraph integration for MCAL - Goal-aware memory for AI agents

mem-agent

一个用来自主操控记忆内存的智能体

mem0-haystack

Haystack integration for mem0

mem0llama

A specialized fork of Mem0 optimized for small, local Large Language Models (LLMs) running through Ollama.

membrain-langchain

LangChain integration for Membrain — persistent semantic memory for AI agents

memento-llm

Simple LLM Memory

memex-agent-memory

Agent 记忆系统 — 轻量级本地向量数据库 + CLI + Agent Skill

memexllm

A library for managing LLM conversation history

memgraph-agent

Universal plug-and-play memory engine for AI agents. Built on Graphiti's temporal knowledge graph with token-budget optimization.

memory-for-agents

Placeholder package — install mcp-memory-service instead.

memoryagent-lib

Add your description here

memorylayer-langchain

LangChain memory integration for MemoryLayer.ai - persistent memory for AI agents

memorylayer-llamaindex

LlamaIndex integration for MemoryLayer.ai - persistent memory for LlamaIndex applications

memoryllm

Persistent Memory Management for Large Language Models

memoryos-agent
memoryos-openai
memos-agent
memos-openai
mentedb-crewai

MenteDB integration for CrewAI and AutoGen

mentedb-langchain

MenteDB integration for LangChain and LangGraph

meta-agents-db

Agent-native database with causal memory, composite-scored recall, and a tamper-evident integrity chain

mhn-ai-agent-memory

AI agent memory system powered by Modern Hopfield Networks — no LLM calls, no database, one matrix multiply

microsoft-agents-storage-blob

A blob storage library for Microsoft Agents

microsoft-agents-storage-cosmos

A Cosmos DB storage library for Microsoft Agents

mimir-agent

Memory-centric agent harness on deepagents / LangGraph

minimem-agent

Lightweight long-term memory system for local/edge AI agents

mnemo-agent

Local-first agent memory CLI — dump, diff, migrate & query across Mem0, Letta, and more

mnemo-claude

mnemo keeps what your Claude Code sessions learned, puts the relevant piece in front of the next prompt, and fans out sessions that start out knowing it.

mnemopay-autogen

MnemoPay extension for Microsoft AutoGen — persistent memory + micropayments

mnemopay-crewai

MnemoPay tools for CrewAI — give any crew persistent memory and micropayments

mnemopay-openai-agents

MnemoPay tools for OpenAI Agents SDK — persistent memory + micropayments

mnemopay-pydantic-ai

MnemoPay tools for Pydantic AI — persistent memory + micropayments

mubit-crewai

CrewAI memory backend backed by MuBit memory engine

mubit-langchain

LangChain chat-history adapter backed by MuBit memory engine

mubit-langgraph

LangGraph BaseStore adapter backed by MuBit memory engine

More in Agent frameworks & infrastructure