Agent frameworks & infrastructure
Agent memory & context
4,032 agents · most starred first
Agent memory & context, page 34 of 41
Autogen integration for Zep
CrewAI integration for Zep
EternalSoul.md review: compare features, pricing, use cases, access model, and alternatives for this Memory agent in 2026. Persistent memory and identity backup for AI agents using PGP encryption.
Build AI agents that remember, learn, and improve over time.
Memo SDK - Enterprise-grade AI Agent Memory System
CLI for SharedMemory — manage AI agent memory from your terminal
Autonomous AI agent memory system with CLAUDE.md protocol enforcement
Conversation memory SDK — query meeting transcripts, decisions, and action items from any AI agent or application
Human + AI Orchestration Hub - persistent memory, task management, session continuity and multi-agent collaboration for Cursor, Claude Code, and Codex
Persistent memory for AI agents — JavaScript/TypeScript client for Cathedral
MySQL StateStore adapter package for AgentLedger
S3-compatible BlobStore adapter package for AgentLedger
Python helpers for Azure Storage Blob and Queue operations.
Reversible UUID/ID aliasing for LangChain & LangGraph — cut tokens and stop the LLM mangling your IDs.
Platform-agnostic TypeScript engine for hybrid LLM memory. OKF v0.2 (llm-wiki/2) conformance with back-compat to v0.1 (llm-wiki/1) and profile-0 bundles. Episodic fact extraction, semantic vector search, multi-agent architectures over SQLite. Bring your o
Haystack integration for Cognee — memory for AI agents
Your AI forgets everything between sessions. cachly fixes that permanently. Persistent memory + causal root-cause analysis for Claude Code, Cursor, Copilot & Windsurf. Learns from every bug fix, git commit, and CI run automatically. Arrives pre-briefed. P
Redis and Postgres adapters for @infra-tools/agentic-ui-server's ThreadStateStore interface — multi-pod-safe thread state for production deployments.
Kynver Agentic OS MCP server — slug-keyed agent identity, goals, projects, sessions, and long-term memory
Pi extension for agentic conversation compaction using a virtual filesystem and tool-driven exploration
Persistent intelligence infrastructure for agentic development
Agentic memory manager. Best used with skill: npx skills add meharajM/agent-loop-mcp
Semantic Sequential Thinking Layer For Agentic Tools
Agentic State Engine — event-sourced causal graph with branching, decision traces, and realtime sync for AI-native applications
Creative Orientation AI Agentic Memories - Narrative Beat Extension with IAIP relational integration
LangGraph checkpoint saver backed by Firestore + GCS, with automatic GCS spill for large payloads.
ScyllaDB checkpoint saver for LangGraph.js
LangGraph.js BaseStore backed by MuBit memory engine
Identity, memory, and soul for AI agents. Cryptographic identity (Ed25519), semantic memory with local embeddings, and persistent personality — all in a single process.
A checkpoint with callbacks so you can implement your own storage mechanism
langchain redis checkpoint saver
A robust, production-ready DynamoDB checkpoint saver for LangGraph.js workflows
Implementation of a LangGraph.js CheckpointSaver that uses a AWS's DynamoDB
Persistent memory for LangChain.js agents. Replaces deprecated ConversationBufferMemory and RunnableWithMessageHistory. Framework-agnostic storage that survives LangChain upgrades.
langchain redis checkpoint saver
Persistent memory + tool-result intelligence for AI agents — TypeScript SDK. One install, all framework adapters, MCP server, CLI, and the agent skill.
AMFS integration for AutoGen
Use AMFS as CrewAI Memory storage backend
AMFS integration for LangChain
AMFS integration for LangGraph
LangChain integration for Engram — cognitive memory infrastructure for AI agents
Domain-agnostic knowledge graph memory for AI agents. Zero-config, local-first, SQLite-powered. Works as OpenClaw skill (CLI) or plugin (auto-hook).
Cross-session persistent memory for AI Agents. 4500x faster retrieval, zero LLM dependency.
Unified history of AI agent sessions across devices
Give pi a mind: portable, self-maintaining memory for pi-coding-agent. Memory is passive — writes are explicit (remember_this / observe), retrieval is hybrid (vector + FTS5 + KG). Ships ask-first skill authoring (create_skill / update_skill).
Tembory Memory node for n8n AI Agents with profile, tools, timeline, graph and semantic memory
Persistent shared memory for multi-agent teams — append-only writes, relevance-weighted reads, TTL pruning, context injection
The reference SDK for the Akashik Protocol — shared memory and coordination for multi-agent AI systems.
Store, retrieve, and transform AI agent memories backed by Azure Cosmos DB
Multi-tenant agent memory framework powered by BECOMER — zero tokens, any LLM
Redis Agent Memory integration for NVIDIA NeMo Agent Toolkit
Python bindings for ovstorage
Persistent, concurrent-safe project memory for Claude Code agents
MongoDB Atlas-backed persistent memory capability for Pydantic AI / pydantic-ai-harness.
Persistent memory layer for AI agent workflows
Three-tier memory architecture for OpenCode — distillation, not summarization
Persistent evolutionary memory for the Pi coding agent
MongoDB Atlas-backed thread/session persistence + semantic/episodic vector memory for VRSEN Agency Swarm.
Du-RAG: Durable RAG — persistent memory for AI agents
A comprehensive toolkit for LLM context management with intelligent metadata selection and contextual question resolution
Autonomous AI agent memory system with CLAUDE.md protocol enforcement
@gobing-ai/ts-llm-jsonl-importer — Generic JSONL importer for LLM agent history files.
TypeScript SDK for AgentDrive — cross-agent artifact workspace with provenance, semantic recall, and portable storage.
LangChain integrations for Exabase memory
MongoDB Atlas-backed persistent agent memory for mcp-agent (LastMile AI): a drop-in Memory backend with Atlas Vector Search recall.
Durable Assistant OS local continuity harness.
Deterministic Context Assembly for AI Agents.
Agent-agnostic semantic memory for your vault. Turns notes into a queryable knowledge graph any MCP agent can search, log to, and reorganize.
Pydantic AI integrations for Exabase memory
LangGraph tools and integration for Memanto's persistent memory
Transparent context reduction for LLMs
MemHQ adapter for LangChain — chat message history and retriever backed by MemHQ.
MemHQ adapter for LlamaIndex — chat memory and retriever backed by MemHQ.
Mubit <-> Agent Lightning bridge — credit rollout rewards back to the recalled lessons via record_outcome/remember
AutoGen Memory provider and group-chat handoff hook backed by Mubit
LlamaIndex chat-memory and vector-store adapters backed by Mubit
Self-learning memory infrastructure for AI products
Transparent feedback compression middleware for LLM coding agents.
Universal Memory-Import Tool — ingest user-memory from major LLM platforms into an AgentBrain workspace.
Make your AI agents leaner, faster, and cheaper — smart context management and token compression
Drop-in, MCP-native working memory for AI agents: gameplans, phases, a dependency graph, and post-hoc cascade — over plain markdown.
Halo adapter for Claude on two runtimes (Python): the Agent SDK (install_halo — a PostToolUse encode hook + a single in-process halo_fetch MCP tool) and the raw Messages API (halo_format_claude.raw — create_raw_halo, no Agent SDK needed). Tool results become a shape map kept out of context.
Agent Memory via Google Keep MCP
Local-first AI memory cartridge: persistent, cross-session memory for Claude and any LLM via MCP
Context compression sidecar for LLM applications. Reduce token costs 3-5x before calling any AI API.
Agent memory - local-first knowledge infrastructure for AI agents
Maintains information quality for agentic workflows — assesses the freshness, provenance, fidelity, and task-specific validity of claims, then refreshes or repairs degraded ones before agents consume them.
Production-grade memory infrastructure for AI agents — storage-agnostic, self-evolving, observable.
Persistent vector memory store for DSPy-powered AI agents — extract, store, and recall structured memories from conversation.
Fragmented memory system for Hermes Agent — automatically retrieve relevant memory fragments and inject them into conversation context
Persistent user memory for LangChain and LangGraph agents, backed by MemoryRouter
Neuroplastic memory, self-healing, and critical reasoning for AI agents — a local-first, framework-agnostic runtime.
Standalone, dependency-free rolling conversation memory (summary + buffer), inspired by LangChain's ConversationSummaryBufferMemory.
HY Memory backend for OpenClaw — self-hosted intelligent agent memory with LLM-driven extraction, evolution chains, and multi-layer recall
Framework-agnostic SDK for Pomerene. createCache + withCache wrap any agent function (Mastra, LangGraph, raw OpenAI Agents SDK, custom loops) with a deterministic trajectory cache.
Claude Agent SDK integration for Hindsight - persistent memory tools and hooks for Claude agents
AIME AT - AI Memory Exchange and Action Transfer - reference implementation
PG stores implementation for Axiom Lattice framework
Session handover engine for AI coding agents: checkpointed, resumable, backend-agnostic persistent memory.
Local-first Maildir-inspired work mailstore for software agents