Agent frameworks & infrastructure
Agent memory & context
4,032 agents · most starred first
Agent memory & context, page 33 of 41
Independent AI Agent with Persistent First-Person Memory and Multi-User Interaction
Python SDK + CLI for AI Agents with persistent memory (Supabase + OpenAI).
A comprehensive memory system for AI agents using Neo4j
Storage layer for NeoBot — SQLAlchemy + Alembic
Drop-in CrewAI memory integration for Neruva agent memory + reasoning substrate. v0.2.0 adds AUTO-PILOT: NeruvaAutoPilot (classify intent + reflect + extract via your LLM) + NeruvaAutoPilotHooks (after_task callback that auto-extracts facts from task output to KG; reflect_on_crew_finish for cross-task self-curation). Plus NeruvaShortTermMemory / NeruvaLongTermMemory / NeruvaEntityMemory / NeruvaStorage as CrewAI memory backends. Substrate stays $0/call (pattern-C).
Drop-in LangChain integration for Neruva agent memory substrate. v0.2.0 adds AUTO-PILOT: NeruvaAutoPilot (classify intent + reflect + extract via your LangChain LLM) and NeruvaAutoPilotCallback (BaseCallbackHandler). Plus NeruvaChatMessageHistory + NeruvaContextRetriever for memory + KG recall, NeruvaCodeGraph (5 code nav methods), NeruvaCognitive (13 cognitive primitives). Pattern-C: substrate stays $0/call.
Drop-in LangGraph integration for Neruva agent memory + reasoning substrate. v0.2.0 adds AUTO-PILOT: NeruvaAutoPilot (classify intent + reflect + extract via your LLM) + classify_intent_node / reflect_node factories for drop-in graph wiring. Plus NeruvaCheckpointSaver (BaseCheckpointSaver) + NeruvaContextStore (BaseStore) for graph state persistence. Substrate stays $0/call (pattern-C). Deterministic from seed. Works with every LangGraph StateGraph.
A lightweight, standalone, framework-agnostic agent memory library — the SQLite of agent memory
Python SDK for AgentBox private agent state and scoped sharing.
让 Agent 记得人、记得事、记得语境,并且成本可控
Build AI agents with persistent memory, rollback, and audit trails — powered by Novyx
Persistent memory + rollback + audit trail for CrewAI agents using Novyx Core
Persistent memory + rollback + audit trail for LangChain agents using Novyx Core
Persistent memory + rollback + audit trail for LlamaIndex agents using Novyx Core
Governance, audit, and rollback for OpenAI Agents SDK — powered by Novyx Core
LangChain integration for OneBrain — persistent AI memory layer
LlamaIndex integration for OneBrain — persistent AI memory layer
Context compaction for the OpenAI Agents SDK Runner loop
Session management for OpenAI Agents SDK using Redis.
Redis and DynamoDB session backends for openai-agents-python
Django ORM-based session backend for OpenAI Agents SDK
Sgraal memory governance for OpenAI Agents SDK
Асинхронная архитектура памяти для OpenAI-агентов на базе ChromaDB и SQLite
Python client library for Oracle AI Database Agent Memory
OtiLLM v2.4: A governed cognitive runtime for evidence-native, memory-augmented and explainable frontier AI systems.
LangChain memory with emotional intelligence by NeurobloomAI
A storage lib
Context window manager for LLMs. Memory for free.
Pensyve memory backend for Microsoft AutoGen
Pensyve memory backend for CrewAI
Pensyve memory backend for LangChain / LangGraph
PiQrypt Verifiable AI Agent Memory bridge for LangChain
MCP based Pocket Agent in vector db ( chroma) as storage
Shared asymmetrically-compressed KV cache pool for multi-agent LLM inference
ProcessFork memory adapter for CrewAI ≥0.130 — time-travel debugging across crew runs.
ProcessFork checkpointer for LangGraph — full four-layer snapshots at every node boundary.
Shared memory foundation for AI development teams
Supabase-backed config, logging, and memory for Claude Agent SDK agents
A local-first self-improvement kernel for agents. Turns traces into tested memory so agents improve without fine-tuning.
Memory layer for Pydantic AI agents.
Recursive Language Model (RLM) toolset for Pydantic AI - handle extremely large contexts
Create LLM agents with long-term memory and custom tools
Create LLM agents with long-term memory and custom tools
QAOA-powered memory management for AI agents — clustering, compaction, and recall
Production-grade RAG memory system for Hermes Agent with hybrid TF-IDF + Neural retrieval, auto-capture, and zero-configuration setup
RAGFL Memory
Local-first memory and RAG system for Claude Code - semantic search over code, docs, and team knowledge
Recursive Language Models for unbounded context processing
Enterprise-grade persistent memory for LangChain agents
Semantic caching for LLMs. Ask once, recall forever.
Python Client SDK for Redis Agent Memory Service
A user-friendly package designed to save chat history conversation and truncate conversation if user exceeds max token when using OpenAI chat completion.
Persistent knowledge memory and code dependency graph for AI agents - Rust, Postgres, pgvector, MCP
Python SDK for SAGE — Sovereign Agent Governed Experience. Persistent, consensus-validated memory for AI agents.
Sayou workspace toolset for Pydantic AI agents — persistent memory, file storage, and search
SeedOS Memory integration for LangChain - AI Memory System with Identity and Semantic Search
Enterprise AI memory for Microsoft ecosystem: Semantic Kernel planning + ZeusDB vector storage with Azure-native performance.
Tiny IDs for big language models. Maps UUIDs to short, category-prefixed aliases optimized for LLM context windows.
Single-Input-Reasoning: one LLM call, full action graph execution with evolutionary memory
Active Skill Listener & Trainer — structured memory layer for AI coding assistants
CrewAI integration for Smara Memory API — persistent memory for AI agents
LangChain integration for Smara Memory API — persistent memory for AI agents
Persistent identity and memory for any LLM agent — markdown-native, provider-agnostic
LangChain integration for Spokest Brain memory
Versioned memory and state management for AI agents. Git-like history over event-sourced memory units.
Python SDK for the Gum Memory API.
A framework for building agents that persist state between interactions.
Add your description here
SUBSTRATE memory components for Haystack -- causal memory, emotion, and identity retrieval and storage.
CrewAI integration for Sulcus thermodynamic memory — shared persistent memory for agent crews
Sulcus thermodynamic memory middleware for LangChain Deep Agents — replace flat AGENTS.md with a real memory engine
LangChain memory backend for Sulcus thermodynamic memory
LlamaIndex storage integration for Sulcus thermodynamic memory
Automatic Conversation Summarization and History Management for Pydantic AI
Memory tools and middleware for Microsoft Agent Framework with supermemory
Memory tools for OpenAI function calling with supermemory
Swarmauri Community Clipboard State
Swarms Memory - Pytorch
Synap memory integration for LangChain and LangGraph
Synap memory integration for LangGraph — BaseStore + BaseCheckpointSaver
Agent capture layer — cross-device memory mesh with viewer and MCP
A Python SDK for agent storage
Tablestore for Agent Memory in AI Agent.
Text analogue of dill library
OpenAI integration for text2mem
OpenAI integration for text2memory
Tree-of-Thought Location Agent — an inspectable, correctable memory engine that learns places through observation and correction.
On-chain memory infrastructure for AI agents — built on the Internet Computer
存储模块的技术实现层,提供 Memory/YAML/Git 三种技术路线的实现
LangGraph checkpointer backed by Typesense
UNIHODL Agent Handoff SDK — pass human session context to AI agents (Claude, Gemini, OpenAI, LangGraph). Decision-continuity protocol.
Local-first memory governance for AI agents: shared, reviewable, auditable memory via SQLite and MCP.
Velixar AI memory retriever and memory module for LangChain
Cognitive infrastructure for AI agents — awareness daemon, frame-based tool filtering, signal protocol, session handoff, and MCP server
Python client for Vigil Cloud — cognitive infrastructure for AI agents