Agent frameworks & infrastructure

Agent memory & context

4,032 agents · most starred first

Agent memory & context, page 36 of 41

agmry

Agentic Memory CLI — persistent memory for AI agents. As easy as git.

3tears-agent-memory

Memory system for LLM agents -- extraction, retrieval, hybrid search, and MMR reranking

3tears-agent-skills

Procedural memory for LLM agents -- skill definitions + invocation history

3tears-agent-wake

Long-running-agent foundation -- wake schedules, fires, webhook subscriptions

agent-context-recovery

Context recovery for AI agents — analyze fatigue, compress context, improve token efficiency

agent-ctx-compress

Smart context compression for LLM agents — preserve critical info, reduce tokens 40-80%

agent-driftwatch

Real-time memory health monitor and context rot detector for AI agents

agent-memory-sdk

Persistent semantic memory for AI agents with replay, restore, verify, and ignore decisions

agent-persona

Claude learns who you are from your own sessions and stays that way

agent-smriti

Plain-text memory for AI agents — small, filtered, compressed, self-pruning. No database, no embeddings, no dependencies.

agentstate-reducer

Framework-agnostic message reducer for AI agent state management. Works with LangGraph, CrewAI, and plain dicts.

anyllm-ctx

Git for LLM context. Snapshot a dying session, brief the next model in 30 seconds.

betterdb-agent-memory

Long-term memory tier for AI agents backed by Valkey Search: semantic recall with recency/importance ranking, scoped capacity eviction, and consolidation. Pairs with @betterdb/agent-cache.

cortexdb-autogen

AutoGen integration for CortexDB — long-term memory for AI agent conversations

cortexdb-langchain

LangChain integration for CortexDB — long-term memory for AI systems

couchbase-agent-memory

Python SDK for the Couchbase Agent Memory API

crewai-mimir

Mimir long-term memory as CrewAI tools — local-first, encrypted, persistent memory the agent can explicitly call.

crewai_persistence_cosmosdb

Azure CosmosDB persistence backend for CrewAI Flows with built-in message pruning via agentstate-reducer

crewai_persistence_firestore

Google Firestore persistence backend for CrewAI Flows with built-in message pruning via agentstate-reducer

engram-agent-memory

Persistent, queryable knowledge storage for AI agents. Markdown source + SQLite + manifest fallback.

extodan-agentsync

Drop-in LangGraph store that merges concurrent writes instead of silently dropping them.

langchain-mimir

Mimir persistent, local, encrypted memory for LangChain — tools and a retriever backed by the Mimir MCP engine.

langgraph-checkpoint-scylladb

ScyllaDB checkpointer for LangGraph

langgraph-surrealdb

SurrealDB checkpoint persistence and cross-thread stores for LangGraph.

langgraph_checkpoint_cosmosdb

LangGraph checkpoint saver for Azure CosmosDB with built-in message history pruning via agentstate-reducer

langgraph_checkpoint_firestore

LangGraph checkpoint saver for Google Firestore with built-in message history pruning via agentstate-reducer

open-agent-memory

Python SDK for OpenMemory and Hermes AI integration

pydantic-ai-mimir

Mimir persistent, local, encrypted memory for Pydantic AI agents — exposed as a Toolset.

qwen-memory-agent

Host-agnostic, self-correcting library/API memory daemon for coding agents (Qwen MemoryAgent)

swarmstate

Drop-in state backend for LangGraph, CrewAI & custom agent loops - Rust core, framework-agnostic, built for production.

zep-langgraph

LangGraph integration for Zep

zep-ms-agent-framework

Microsoft Agent Framework integration for Zep

zep-pydantic-ai

Pydantic AI integration for Zep

crewai-perseus-vault

Perseus Vault long-term memory as CrewAI tools — local-first, encrypted, persistent memory the agent can explicitly call.

langchain-perseus-vault

Perseus Vault persistent, local, encrypted memory for LangChain — tools and a retriever backed by the Perseus Vault MCP engine.

langgraph-checkpoint-grafomem

Grafomem (Fair Source) adapter for LangGraph Checkpointers

llm-context-vault

The intelligent context management framework for LLM applications.

pydantic-ai-perseus-vault

Perseus Vault persistent, local, encrypted memory for Pydantic AI agents — exposed as a Toolset.

stratarag

Agents that remember: memory-first agent & RAG framework with zero required dependencies.

@memorymsh/sdk

TypeScript SDK for MemoryMesh durable agent memory, receipts, checkpoints, and Cognee-backed runtime state.

langgraph-checkpoint-sqlite-native

LangGraph Checkpoint saver using native SQLite for Node.js and Bun.

3tears-langgraph

Three-tier LangGraph checkpoint saver: L1 SQLite -> L2 NATS KV -> L3 PostgreSQL

bfast-llm

⚡ B-FAST Context Compression Layer for Large Language Models (LLMs)

contextmate

Zero-knowledge encrypted sync for AI agent context

inkstone-mcp

Agentic MCP memory server with dream cycle — decay, consolidation, and archival

memctrl-llm

Task-aware memory management for LLMs. Extend conversations 5.7x longer with 88% recall.

mirage-haystack

Haystack integration for Mirage, a unified virtual filesystem for AI agents

sibyl-memory-langgraph

LangGraph BaseStore backed by Sibyl Memory (SQLite + FTS5, no vector database, no embeddings).

poolsplit

Pool-split retrieval for agent memory: reserved per-type token budgets so low-priority entries surface and corrections never get crowded out.

@svgph/tokensaveos

An Enterprise AI Agent Optimization Platform & Context Intelligence Operating System

ctx-zip

Keep your AI agent context small and cheap by managing tool bloat and large outputs.

cimux-mcp

Local-first mailbox for intentional AI agent context handoffs.

@barekit/omnicontext

CLI and MCP server for OmniContext — AI agent project memory layer

hco-mcp

Give your AI agent a memory. And a seatbelt.

cogmem

cogmem — agent-native memory kernel for a single local-first AI agent

@lyupro/dacapo

Context deduplication for LLM agent sessions: repeated tool output is replaced with a short ref token

agentic-cortex

Persistent self-improving agent memory with tree-of-thoughts reasoning: MCTS/beam search, PRM step verification, self-consistency voting, s1 budget forcing, REPL program-aided reasoning, reflexion self-correction, failure classification, experience replay

@rulvar/store-postgres

Rulvar PostgreSQL store implementing JournalStore and LeasableStore with a fencing epoch, for multi-process and multi-host deployments.

renma

Manage human-curated context assets for LLMs and agents in Git.

inline-agent

정크 컨텍스트 제거 — LLM 에이전트를 위한 보이지 않는 정보 정돈 레이어

@rulvar/store-sqlite

Rulvar SQLite store implementing JournalStore and LeasableStore with a fencing epoch.

@skein-js/storage-memory

In-memory SkeinStore + queue driver for development and tests.

@skein-js/storage-postgres

Postgres SkeinStore driver with pgvector semantic search, reusing PostgresSaver for checkpoints.

@archildata/langchain

Archil filesystem adapter for LangChain

langchain-taguru

LangChain.js integration for the Taguru long-term semantic memory server

@wolbarg/langchain

Official LangChain JS / LangGraph JS adapters for Wolbarg shared memory — BaseMemory + BaseStore.

grok-loop-kit

Auto-apply Grok 4.5 context compaction to xAI Responses API agent loops. Drop-in client that compacts every N turns or when a token budget is exceeded.

@mongodb-developer/vercel-ai-memory

MongoDB-backed persistent memory provider for the Vercel AI SDK (plus a Vercel Eve provider that is not yet production-ready) — Session, Semantic, Procedural, Episodic, and Scratchpad memory with Atlas Vector Search (optional Atlas Automated Embedding).

@holoscript/agent-runtime

Provider-neutral second-brain runtime and contract helpers for human and agent operators.

@llmtrim/js

WebAssembly/JS bindings for the llmtrim-core compression engine (wasm-bindgen).

@tormentnexus/openhands

TormentNexus for OpenHands — Persistent AI memory, MCP tools, and context harvesting in your autonomous agent

klypix-mcp

Active state management for multi-agent coding: a shared, versioned project brain over MCP.

@x12i/memorix-metadata

Canonical Memorix metadata contracts, effective multi-agent resolution, and metadata-only abstract unions (Phase 3).

@lov3kaizen/agentsea-memory

Advanced memory management system for AI agents with semantic retrieval, hierarchical structures, and multi-agent support

synabun

Local-first persistent vector memory, MCP tooling, and multi-agent workflows for AI assistants

neurohive

Multi-agent memory intelligence layer — shared knowledge, expertise tracking, and conflict detection for AI agent teams

oracle-memory

File-backed Memory MCP Server for multi-agent coordination

@cognitivx/cli

CogX CLI for the Persistent Memory Protocol (PMP): durable AI identity, memory, and multi-agent orchestration.

@ouro.bot/friends

The who's-who / identity / relationship substrate for agents — trust ladder (family/friend/acquaintance/stranger), multi-party and multi-agent, consumed via the FriendStore interface + FriendResolver.

nuvlore

Memory-native agent framework runtime.

ai-management

myai — a self-owned, git-versioned AI memory + multi-agent framework. Plug any agent (Claude, Cursor, Gemini, Codex, opencode) into your own portable brain so it boots already knowing your projects, decisions, and context. Local-first (Docker), MCP-native

@aigne/afs-memory

AIGNE AFS Memory Provider — agentic knowledge lifecycle management

@context-router/crewai-adapter

CREWAI adapter for Context Router - brings structured state to CREWAI crews and agents

agent-handoff-pack

Compress a completed agent's trace into a compact, framework-agnostic briefing that the next agent can load in one call. Solves the cross-framework agent-to-agent handoff problem. Paid via x402 ($0.10/pack) on Base USDC.

@mi8y/cds-langgraph-persistence

CDS Plugin for LangGraph checkpoint persistence in SAP CAP applications

@engramviz/adapter-langgraph

Evidence-preserving LangGraph Store adapter for Engram.

@surrealdb/langgraph

SurrealDB checkpoint saver, store and node cache for LangGraph.js, plus a SurrealDB Agent Memory store

arborkit

A versioned, searchable JSON workspace for AI agents: scoped edits, semantic discovery, audit history, time-travel, and delta persistence.

3tears-agent-identity

Versioned identity blocks for LLM agents -- self-evolution via a linear version chain with propose/consent/apply, rationale, and rollback

3tears-agent-intention

Standing-wants corpus for LLM agents -- intention lifecycle, salience decay, embedding dedup, and private deliberation tools

3tears-agent-knowledge

Governed-knowledge retrieval + injection for LLM agents -- concepts, playbook entries, three-scope shadow merge, and before_model middleware

agent-acid

ACID-style transaction guarantees (rollback + session-memory guardrails) for autonomous AI agents

agent-checkpoint-mcp

Local MCP server that saves work-in-progress checkpoints so any AI agent can resume a multi-step plan exactly where a previous session was cut off.

agent-core-bus

Core infrastructure for AI agents - memory, knowledge compilation, and tooling

agent-framework-azure-cosmos-memory

Azure Cosmos DB Agent Memory Toolkit integration for Microsoft Agent Framework - semantic memory with fact extraction and user profiles.

agent-kg

Conversational memory as a knowledge graph

agent-logbook

Local SQLite long-term memory for AI assistants, served over MCP

agent-memguard

Local-first MCP memory backend and governance console for coding agents

agent-memory-engine-ljf

Two-stage retrieval + gating long-term memory engine for coding agents.

agent-memory-fs

Agent Memory File System - a local-first memory store for AI agents, with semantic search.

More in Agent frameworks & infrastructure