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 integration
llama-index storage-chat-store yugabytedb integration
llama-index kvstore redis integration
llama-index kvstore s3 integration
llama-index kvstore tablestore integration
LlamaIndex integration for the Dakera AI memory platform
Native LlamaIndex retrieval, Document ingestion and agent tools for GoodMem.
The soul ecosystem for LlamaIndex: persistent memory, identity, database schema intelligence, and SoulMate API integration.
User profile management, preference modeling, and personalization features for LlamaAI Ecosystem
A memory-augmented framework for LLMs
Prevent LLM cache poisoning with Confidence Gap Analysis — intent-aware thresholds, zero false serves
Lite library for local caching of LLM API requests
Agent Cache Runtime for building cache-aware LLM applications.
Check whether you've already run this prompt before calling the LLM
A drop-in, model-agnostic cache for Large Language Model API calls
Local SQLite cache for OpenAI and Anthropic API calls. One env var, 60-80% cheaper dev loops.
Lightweight caching layer for LLM API responses with TTL and size limits
A middleware layer for managing, budgeting, and optimizing LLM context windows.
Production-grade LLMOps infrastructure for context window management, token counting, document chunking, and compression
Add your description here
Scope your AI context before it explodes
Composable building blocks for LLM context engineering
Portable, model-agnostic memory layer for LLM conversations
A middleware layer for managing, budgeting, and optimizing LLM context windows.
A Python package for managing LLM chat conversation history
[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.
Durable, explainable long-term memory for the llm CLI, powered by Engram (Lumetra)
LLM Hippocampus — a Context Engineering playground
Framework for collecting and managing LLM context
A middleware layer for managing, budgeting, and optimizing LLM context windows.
Give your AI agents persistent, searchable long-term memory with pluggable storage backends
Lucid Memory - Modular reasoning graph for LLMs
MapReduce-inspired framework for extending context windows in large language models
A LLM Memory Cache package
A memory management system for large language models
Currently for internal use only.
SQLite-backed LLM response cache. Exact match + fuzzy match. Decorator API. Zero mandatory server dependencies.
Multi-tier caching platform for LLM embeddings, semantic search, and graph-based conversation memory
Smart memory management for LLM conversations - topic-aware compression that just works
Memory tools for LLM
Transparent memory system for LLM
Cross-LLM memory portability tool — user-owned context vault across Claude, ChatGPT, Gemini, and Ollama
High-performance document memory system with vector search capabilities for Python applications
Self-evolving modular memory LLM framework — biological memory × formal verification × industrial IoT mesh × TUI HITL
WIP
A filesystem-metaphor memory layer for LLMs and AI agents
A lightweight, model-agnostic context engine for LLMs. Feed your model tasty context.
A Pydantic AI agent that remembers across sessions, can create its own tools, and delegates to specialists
Drop-in Anthropic client with MADB causal memory. One import, every turn persisted.
Synap memory integration for AutoGen / AG2
Synap memory integration for Anthropic's Claude Agent SDK
Synap memory integration for CrewAI
Synap memory integration for Haystack — SynapMemoryStore + retriever/writer components
Synap memory integration for LangChain and LangGraph
Synap memory integration for LangGraph — BaseStore + BaseCheckpointSaver
Synap memory integration for LiveKit Agents — preload long-term memory, record turns, expose Synap as LLM tools
Synap memory integration for LlamaIndex
Synap memory integration for Microsoft Agent Framework
Synap memory plugin for NVIDIA NeMo Agent Toolkit (NAT)
Synap memory integration for OpenAI Agents SDK
Synap memory integration for Pydantic AI
Synap memory integration for Microsoft Semantic Kernel
Microsoft AutoGen integration for MCAL - Goal-aware memory for multi-agent systems
CrewAI integration for MCAL - Goal-aware memory for AI agent crews
LangGraph integration for MCAL - Goal-aware memory for AI agents
一个用来自主操控记忆内存的智能体
Haystack integration for mem0
A specialized fork of Mem0 optimized for small, local Large Language Models (LLMs) running through Ollama.
LangChain integration for Membrain — persistent semantic memory for AI agents
Simple LLM Memory
Agent 记忆系统 — 轻量级本地向量数据库 + CLI + Agent Skill
A library for managing LLM conversation history
Universal plug-and-play memory engine for AI agents. Built on Graphiti's temporal knowledge graph with token-budget optimization.
Placeholder package — install mcp-memory-service instead.
Add your description here
LangChain memory integration for MemoryLayer.ai - persistent memory for AI agents
LlamaIndex integration for MemoryLayer.ai - persistent memory for LlamaIndex applications
Persistent Memory Management for Large Language Models
MenteDB integration for CrewAI and AutoGen
MenteDB integration for LangChain and LangGraph
Agent-native database with causal memory, composite-scored recall, and a tamper-evident integrity chain
AI agent memory system powered by Modern Hopfield Networks — no LLM calls, no database, one matrix multiply
A blob storage library for Microsoft Agents
A Cosmos DB storage library for Microsoft Agents
Memory-centric agent harness on deepagents / LangGraph
Lightweight long-term memory system for local/edge AI agents
Local-first agent memory CLI — dump, diff, migrate & query across Mem0, Letta, and more
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 extension for Microsoft AutoGen — persistent memory + micropayments
MnemoPay tools for CrewAI — give any crew persistent memory and micropayments
MnemoPay tools for OpenAI Agents SDK — persistent memory + micropayments
MnemoPay tools for Pydantic AI — persistent memory + micropayments
CrewAI memory backend backed by MuBit memory engine
LangChain chat-history adapter backed by MuBit memory engine
LangGraph BaseStore adapter backed by MuBit memory engine