Agent frameworks & infrastructure

Agent memory & context

4,032 agents · most starred first

Agent memory & context, page 27 of 41

@getzep/zep-cloud

The TypeScript SDK for Zep, the context layer for AI agents.

@atomicmemory/langchain

AtomicMemory adapter for LangChain JS - memory tools and framework-agnostic retrieve/ingest helpers around an injected MemoryClient.

@getzep/zep-js

Zep: Fast, scalable building blocks for production LLM apps

@cafitac/agent-memory

Local-first graph memory CLI for AI agents

@betterdb/agent-cache

Multi-tier exact-match cache for AI agent workloads backed by Valkey. LLM responses, tool results, and session state with built-in OpenTelemetry and Prometheus instrumentation.

@farukada/aws-langgraph-dynamodb-ts

DynamoDB persistence for LangGraph.js: checkpoint saver, long-term memory store with semantic search, and chat message history, with optional S3 offload, compression and TTL

@tpsdev-ai/n8n-nodes-flair

n8n community node — use Flair as your AI Agent's memory backend. Includes FlairChatMemory (Memory port) and FlairSearch (Tool port).

deepadata-langchain-adapter

EDM enrichment layer for LangChain — governed emotional schema for any memory type

@stackone/openai-agents-js-sessions

Session memory module for managing conversation history across multiple OpenAI agent runs

nexo-brain

NEXO Brain — Shared brain for AI agents. Persistent memory, semantic RAG, natural forgetting, metacognitive guard, trust scoring, 150+ MCP tools. Works with Claude Code, Codex, Claude Desktop & any MCP client. 100% local, free.

agent-context-store

acs CLI for Agent Context Store Toolkit.

@supermemory/tools

Memory tools for AI SDK, OpenAI, Voltagent and Mastra with supermemory

tokenmaxxen-mcp

MCP server for Tokenmaxxen — collective episodic memory for AI coding agents. Deposit, retrieve, and comment on session learnings (gotchas, fixes, prompts, configs) over hybrid keyword+semantic search. Agents can post corrections when a learning is wrong

dotaios

Stop re-explaining yourself to every AI. Keep who you are and what you're working on in one folder on your computer.

@letta-ai/agentic-learning

Drop-in SDK to add an AI memory layer to any application. Works with OpenAI, Anthropic, Gemini, Claude, Vercel AI SDK.

@cascade-flow/ai-sdk

Checkpoint-based persistence for Vercel AI SDK in CascadeFlow workflows

mypensieve

A general-purpose, self-evolving autonomous agent OS with persistent memory across sessions

memoreum

Memoreum SDK & CLI - Autonomous Agent Memory Marketplace on Base Chain

@astramindapp/mcp-server

MIND MCP Server — 48 tools. The most complete AI memory layer with the Focus → Project → Outcome → Task → Checklist hierarchy (mind_focuses + extended mind_life with item_type/parent_id/focus_id and cross-account project sharing via share/list_shares/revo

@voltagent/libsql

VoltAgent LibSQL - LibSQL/Turso Memory provider integration for VoltAgent

@jessenguyen22/pi-agent-mind

Self-improving AI agent extension for pi coding agent - closed-loop learning system with insight extraction and memory management

memorix

Open-source cross-agent memory layer for coding agents across Cursor, Claude Code, Codex, Windsurf, Gemini CLI, Copilot, Kiro, OpenCode, Antigravity, and Trae via MCP.

@honcho-ai/sdk

Official DX Optimized TypeScript SDK for Honcho

@mem0/vercel-ai-provider

Vercel AI Provider for providing memory to LLMs

@vectorize-io/hindsight-ai-sdk

Hindsight memory integration for Vercel AI SDK - Give your AI agents persistent, human-like memory

@ai-sdk-tools/memory

Persistent memory system for AI agents

@focus-mcp/brick-share

Shared state for multi-agent — share context, files, results between agents, broadcast messages.

opencastle

What your team's AI learns stays with the team: lessons from what agents remember, reviewed in pull requests and loaded by every teammate's assistant, beside shared instructions, skills, agents and MCP servers. Works with Claude Code, Copilot, Cursor, Win

@dug-21/unimatrix

Unimatrix knowledge engine for multi-agent development

iranti

Memory infrastructure for multi-agent AI systems

@multi-agent/memory

User Memory SDK — profile / episodic / procedural 三类长期记忆,跨对话持久化。配合 @multi-agent/conversation 使用,a2a 生态扩展。

@darksol/remem

Persistent, queryable memory for AI agents with intake policy, smart recall, context packs, graph recall, and multi-agent scoping

@ruliu/brain-tools

Shared brain tools for multi-agent collaboration in Flow OS

snipara-openclaw-hooks

Shared memory for multi-agent teams - automation hooks for OpenClaw powered by Snipara

@ghostxd/state-capsule-sdk

State Capsule SDK — continuity protocol for multi-agent systems

@lanonasis/memory-sdk-standalone

Standalone Memory SDK - drop into any project for multi-agent orchestration with persistent memory

picklejar-agent

Persist AI coding agent sessions via hooks — snapshots and brain-dump resume (multi-agent)

@pedrocivita/tocket

Project notebook for multi-agent workspaces. Agents work. Tocket remembers. Jev only chooses the next step.

@lumetra/engram-ax

Engram memory adapter for the ax (@ax-llm/ax) agent framework.

@maiar-ai/memory-sqlite

Maiar: A Composable, Plugin-Based AI Agent Framework

@maiar-ai/memory-postgres

Maiar: A Composable, Plugin-Based AI Agent Framework

@maiar-ai/memory-filesystem

Maiar: A Composable, Plugin-Based AI Agent Framework

glove-memory

Memory layer for the Glove agent framework — entity, episodic, resources, and context primitives with bring-your-own storage.

@aigne/agentic-memory

Agentic memory for AIGNE framework

agentic-memory-openclaw

OpenClaw memory and context-engine integration for Agentic Memory

pi-context

Agentic Context Management for Pi

@yuihub/server

YuiHub Server - Semantic Memory API for Agentic AI

@codemcp/knowledge-core

Core functionality for agentic knowledge guidance system

zerodb-sequential-thinking-mcp

Persistent sequential thinking MCP — chain-of-thought reasoning that survives sessions, resumes across agents, and saves conclusions as plan artifacts. Powered by ZeroDB. Zero-config: agents self-provision a ZeroDB account on first run, no signup required

@clude/sdk

Persistent memory SDK for AI agents — Stanford Generative Agents architecture on Supabase + pgvector

@sovereign-labs/narrowing

Constraint-learning runtime for iterative agent loops. Agents that structurally learn what NOT to try again.

agent-recall-core

AgentRecall core: the corrections, rules and session cards that close the Intelligent Distance between you and your agents

agent-recall-sdk

AgentRecall SDK: teach one agent, and every agent you connect starts from what it learned

@presidio-dev/agent-memory

Long-term memory engine for AI agents

@dakera-ai/dakera

TypeScript/JavaScript SDK for Dakera AI memory platform

agentbay

Memory OS for AI coding agents. Local-first persistent memory with an upgrade path to projects, teams, and cloud sync.

@varunshodh/mif-tools

MIF (Memory Interchange Format) — vendor-neutral memory portability for AI agents

@neutron_me/neural

The hive — memory and intelligence OS for AI agents

@vbch/total-agent-memory-client

TypeScript client for total-agent-memory (server v8.0+) — local-first MCP memory layer for AI coding agents

trevec

Universal Context Graph for AI Agents — persistent memory with user isolation, sub-50ms retrieval

mnemosy-ai

Cognitive Memory OS for AI Agents — persistent, self-improving, multi-agent memory

anchorai

Policy-enforced storage for AI agents. Block bad data. Prove what happened.

@assim98/typesense-langgraph-checkpointer

LangGraph checkpointer backed by Typesense

langgraph-checkpoint-mongodb

Production-ready MongoDB checkpointer for LangGraph (extends BaseCheckpointSaver). Works with LangGraph serde (optional), ships ESM/CJS + types.

@atomicmemory/langgraph

AtomicMemory adapter for LangGraph JS - state-graph node factories around an injected MemoryClient.

@aletheia-labs/adapters-langgraph

LangGraph node helpers for Aletheia authority-governed memory.

@langgraph-js/memory

A memory management system based on PostgreSQL + pgvector for LangGraph workflows

convo-sdk

LangGraph-compatible checkpointer with Postgres memory and message logging

@eusoumarlon/langgraph-checkpoint-postgres

LangGraph

agentsmcp-langgraph

LangGraph BaseCheckpointSaver backed by agentsmcp (AgentMailbox). Drop-in checkpointer for LangGraph.js — your graph state lives in an AgentMailbox thread.

@dialogai/ydb-checkpointer

YDB LangGraph checkpoints saver

@steerprotocol/langgraph-checkpoint-pglite

LangGraph checkpoint saver implementation using PGlite for local, in-memory, or browser-based PostgreSQL storage

l1-pager-core

Context Garbage Collector (CGC) for LangGraph agents — virtual memory for LLM context windows

copilotkit-langgraph-history

Open-source CopilotKit + LangGraph chat history persistence. Restore thread history on page refresh.

langgraph-checkpoint-filesystem

Langgraph checkpoint implementation based on file system

langgraph-checkpoint-cloudflare-d1

LangGraph checkpointer for Cloudflare D1 database

@logicpanel/langgraph-checkpoint-postgres

Drop-in replacement for @langchain/langgraph-checkpoint-postgres with Python parity fixes (branching, task_path, inline primitives)

@skroyc/langgraph-supabase-checkpointer

LangGraphJS checkpoint saver implementation for Supabase with UUID thread_id and Supabase Storage support

@skroyc/langgraph-supabase-store

Supabase Store for LangGraph

langgraph-checkpointer-filesystem

A file-based checkpointer for LangGraph.

langgraph-postgres-checkpointer

PostgreSQL checkpointer for LangGraph - persist and retrieve checkpoints for stateful AI workflows

@beshkenadze/langgraph-checkpoint-libsql

LangGraph checkpoint saver backed by LibSQL (Turso)

@luke_skywalker88/langgraph-checkpoint-neo4j

Neo4j checkpointer for LangGraph — drop-in replacement for the Postgres checkpointer

@mnemopay/langchain

MnemoPay tools for LangChain/LangGraph — agent memory + wallet

@meridian-agent/langgraph-checkpoint-cloudflare-d1

LangGraph.js checkpoint saver for Cloudflare D1

@macrow/copilotkit-langgraph-history

Open-source CopilotKit + LangGraph chat history persistence. Restore thread history on page refresh.

@unihodl/agent-sdk

UNIHODL Agent Handoff SDK — pass human session context to AI agents (Claude, Gemini, OpenAI, LangGraph). Decision-continuity protocol.

copilotkit-agent-runner

CopilotKit + LangGraph agent runner with history hydration (thread persistence for chat UIs).

@agent-trace-cache/sdk

Framework-agnostic SDK for AgentTrace-Cache. createCache + withCache wrap any agent function (Mastra, LangGraph, raw OpenAI Agents SDK, custom loops) with a deterministic trajectory cache.

@skroyc/bun-sqlite-checkpointer

Bun native SQLite checkpointer for LangGraph

langgraph-dynamodb-checkpointer

DynamoDB-based checkpoint saver for LangGraph - persistent state management for conversational AI applications

langgraph-db

Langraph-DB is a powerful memory backend for LangGraph.js that brings short-term and long-term memory to your agents using flexible storage providers like MongoDB, Prisma, Redis, and more.

MinimalLLMAgent

A minimal LLM agent with memory management.

acace_context_storage

Context storage utilities for ACACE

ace-agents

ACE (Agentic Context Engineering) - A framework for adaptive context optimization using LLM agents

adaptive-agent-mcp

Self-Evolving RAG for AI Agents — A cross-app persistent memory system where agents autonomously write, retrieve, and evolve their knowledge

adr-agent

Per-repository architectural memory for AI agents

affective-rag

A library for integrating episodic memory within AI applications.

agent-artifacts

Transactional memory + skill artifacts for AI agents

agent-borg

Failure memory and epistemic guardrails for AI agents

More in Agent frameworks & infrastructure