Agent frameworks & infrastructure

Agent memory & context

4,032 agents · most starred first

Agent memory & context, page 37 of 41

agent-memory-ledger

An append-only, auditable ledger for LLM agent memory.

agent-memory-os

Local-first, MCP-native memory engine for AI agents with RAM cache and context-budgeted recall.

agent-notes-hraedon

Unified pgvector-backed CLI for agent notes (breadcrumbs, memories, reflections) shared across the sf2 constellation

agent-state-api

StateSync — the global state database for AI coding agents. Two-line SDK to unify memory across Cursor, Claude, OpenAI and Emergent.

agentcache-core

A Python REST + WebSocket + MCP cache server for AI agents, backed by SQLite

agentmem-core

A proactive memory layer for long-horizon coding agents, it knows when to remind.

agentram-sdk

Persistent memory for AI agents in two API calls. The official Python SDK for AgentRAM.

ai-agent-memory-mcp

独立于具体 Agent 的持久化记忆层 (MCP Server),可被 Claude Code / Qoder / Cursor 复用

aidememo-agent-sdk

Code-first agent memory SDK for AideMemo (aidememo)

allbrain-agent-runtime

Event-sourced memory and orchestration server for multi-agent AI systems

argon-agents

Argon adapters for AI agent frameworks: sandboxed, versioned MongoDB for LangGraph and Mem0

attestari-langchain

LangChain integration for Attestari — the auditable memory layer for AI agents.

barber-llm

Query-aware context trimming for LLM requests. Your context could use a trim.

bioma-langchain

Context apoptosis for LangChain: µs-scale, class-aware history pruning (B.I.O.M.A. kernel) as a drop-in Runnable.

crewai-mongodb-memory

MongoDB Atlas-backed StorageBackend (memory store) for CrewAI's Unified Memory System.

dinomem-crewai

DinoMem integration for CrewAI — drop-in memory tools for any Crew agent

echograph-rag

Official Python SDK & Local-First RAG Memory Engine for AI Agents

hermes-llmwiki

Karpathy-native local Markdown wiki memory provider for Hermes Agent

hippodb-agent-sdk

Agent development kit for building self-tuning AI agents with HippoDb biological memory

infolang-crewai

InfoLang-backed memory storage for CrewAI's unified Memory system.

infolang-openai-agents

InfoLang memory Session for the OpenAI Agents SDK.

june-langgraph

Give your LangGraph agent a June memory — mirror chat history from any LangGraph checkpointer into a searchable, cited June knowledge canvas. Three commands, no code changes.

june-openai-agents

Give your OpenAI Agents SDK agent a June memory — wrap any Session to mirror conversations into a searchable, cited June knowledge canvas, add a memory-search tool, and backfill existing session databases.

langchain-coalent

LangChain integration for Coalent — use any LangChain VectorStore/retriever, embeddings, and chat model as the substrate of a provenance-invalidated cognitive cache.

langchain-distil

Reversible distil context compression for LangChain and LangGraph

langchain-taguru

LangChain integration for the Taguru long-term semantic memory server

langgraph-checkpoint-dmdb

DM Database checkpoint and Store persistence for LangGraph.

langgraph-checkpoint-inspeximus

LangGraph checkpointer backed by inspeximus: durable thread state with queryable value history and receipted erasure.

langgraph-checkpoint-oceanbase-es

Library with an OceanBase/MySQL implementation of LangGraph checkpoint saver with Elasticsearch vector search support.

langgraph-checkpoint-upstash-redis

LangGraph checkpoint saver backed by Upstash Redis (REST API)

langgraph-store-inspeximus

LangGraph BaseStore backed by inspeximus: drop-in for InMemoryStore, plus queryable value history and receipted erasure.

langgraph-store-mnestic

LangGraph BaseStore backed by mnestic — embedded agent memory with atomic batches and one-call BM25+vector hybrid search.

langgraph-velesdb

LangGraph memory tools for VelesDB: drop the why() knowledge-graph memory wedge into any LangGraph agent.

langgraph_dynamodb_checkpoint

LangGraph checkpoint saver for Amazon DynamoDB with built-in message history pruning via agentstate-reducer - single table, auto create, TTL and delete handling

lethe-agent

Selective memory layer for AI agents: importance-scored, self-decaying, pluggable.

lithtrix-langgraph

LangGraph BaseStore adapter and swarm client for Lithtrix agent memory

llama-index-memory-infolang

InfoLang memory integration for LlamaIndex

llm-context-budget

Fit chat history into any model's context window: token estimation, sliding-window packing with a running summary, and overflow detection. Zero dependencies, no AI inside.

llm-ctxpack

Pack the most important text into a fixed LLM context-window token budget.

llm-memory-store

A personal, local-first memory store for LLM applications and agents

loregpt

Python SDK for Lore — coordination memory for multi-agent AI systems: create runs, write events, and fetch read-your-writes context packs.

m3-langchain

Recognizable alias for m3-memory's LangChain / LangGraph integration (drop-in Mem0 replacement, M3Store, M3Saver checkpointer, retriever, LCEL). Re-exports m3_memory.langchain.

maximem-synap-smolagents

Synap memory integration for Smolagents — memory tools and a turn recorder

maximem-synap-strands-agents

Synap memory integration for Strands Agents — long-term memory, short-term context, and real-time anticipation

memoflow-anthropic

Durable Anthropic Messages adapter for the MemoFlow Python SDK

memoflow-openai

Durable OpenAI Responses adapter for the MemoFlow Python SDK

memora-autogen

Poison-resistant, Byzantine-fault-tolerant shared memory for Microsoft AutoGen agent teams — implements the autogen_core Memory protocol; one rogue agent can't corrupt the team's recall.

memora-crewai

Poison-resistant, Byzantine-fault-tolerant shared memory + robust voting tools for CrewAI crews — one rogue agent can't corrupt what the crew remembers or how it votes.

memora-langchain

Poison-resistant, Byzantine-fault-tolerant shared chat memory for LangChain agent swarms — one prompt-injected agent can't corrupt the shared history.

mengram-crewai

Mengram memory tools for CrewAI agents — semantic, episodic, and procedural memory (workflows that learn from failures).

multi-agent-memory

Local-first shared long-term memory for multiple AI agent CLIs

nested-memvid-agent

Kestrel: a local-first, memory-native AI engineering agent runtime.

omni-memory-agent

Persistent, branch-aware, git-anchored memory & context layer for coding agents.

pi-py-storage-sqlite

Python port of @earendil-works/pi-storage-sqlite-node — SQLite session storage backend

progress-memory-langchain

LangChain integration for the Progress Memory SDK

recall-rag

Trustworthy retrieval for an AI agent's own memory — verdict, confidence and provenance per hit, or an explicit abstention

reconcile-agent-memory

A pluggable memory layer for LLM agents with usage verification, contradiction resolution, and multi-tenant access control

roborean-storage-base

Persistence ports for Roborean projects and runs

roborean-storage-dict

JSON/YAML filesystem persistence for Roborean

roborean-storage-sqlalchemy

SQLAlchemy persistence adapter for Roborean

sp-llmgraph

Gestor de contexto para agentes IA basado en grafos comprimidos generados desde Markdown

spectron-openai-agents-sdk

Spectron agent memory for the OpenAI Agents SDK

spectron-pydantic-ai

Spectron agent memory for Pydantic AI: toolset, auto-recall history processor, and persistence helpers.

spectron-strands-agents

Spectron agent memory as tools for the Strands Agents SDK.

strands-agents-session

Backend-agnostic session management for Strands Agents — a SessionStorage interface + KeyValueSessionManager to build session backends (DynamoDB, Redis, MongoDB, …)

strands-dynamodb-storage

Amazon DynamoDB storage backend for the Strands Agents SDK

temporal-cache-llm

Time-aware semantic LLM cache — automatically invalidates stale AI answers

unified-agent-context

Shared memory and skills across Claude Code and Codex

watchllm-klyd

Architectural memory system for autonomous coding agents.

zaniidb-agent-memory

ZaniiDB Agent Memory - layered long-term memory (L0-L3) for AI agents: SQLite + hybrid BM25/vector recall, LLM extraction pipeline, FastAPI gateway, Python SDK.

hansard

Local-first archive, search, and recall for AI-agent conversations.

@neurealistic/finding-memo

Brain-inspired associative memory layer for an LLM agent. Automatic (implicit) tier: capture -> embed -> recall. Codename Factor-X.

titen-memory

Agent memory with no API key, no LLM, and no embedding provider. Serves MCP over stdio against a local SQLite store, or Cloudflare Workers + D1. Drop-in for @modelcontextprotocol/server-memory; every memory keeps its source, its scope, and the evidence th

@neo4j-labs/agent-memory

Neo4j Labs: TypeScript client for the Neo4j Agent Memory Service (NAMS)

billion-context

A context-compression plugin — small context windows (a 100K context is enough), 5x fewer tokens, month-long single sessions (billions of tokens), and compression quality — for all agents: pi, OpenCode, Codex, Claude Code, and more. billion-context is all

@kovartravis/neuron

Local-only agent memory store CLI

backboard-sdk

JavaScript SDK for the Backboard API - Build conversational AI applications with persistent memory and intelligent document processing

memory-store-skill

Conversation memory skill for multi-agent AI workflows — store, share, and recall across sessions and agents

xrlf-server

XRLF Protocol — Universal OpenAI-compatible proxy that gives any LLM foveated ring memory, active recall, and cognitive steering. Point LM Studio, Ollama, or any OpenAI SDK at http://127.0.0.1:8300/v1 and it just works.

@usecarry/agents

Proof-carrying memory for any agent framework — gate memory before generation, get an Answer Receipt. Adapters for LangGraph, the OpenAI Agents SDK, and anything else.

agent-decision-log

Your agent's decisions survive the session - append-only decisions with SUPERSEDES chains

agent-learning

Evidence-driven reasoned and learned decisions for AI agents with inspectable autonomy.

agentmemory-client-nullwinters

AgentMemory 微服务的 Python 客户端 SDK

agentmemorymanager

面向 LangChain / LangGraph 开发者的 AI Agent 三层记忆管理微服务

bysulf-storage-sqlite

SQLite persistence adapter for bysulf runs

citadeldb-crewai

CrewAI memory backed by Citadel: encrypted at rest, with deletes that destroy the key

citadeldb-langgraph

LangGraph store backed by Citadel: encrypted at rest, semantic search, cryptographic deletes

cognee-integration-hermes-agent

Cognee memory provider plugin for Hermes Agent. After installing, run `hermes memory setup cognee`; Cognee Cloud needs nothing else, local mode runs cognee from a private environment the plugin installs on request.

gragdb

Local-first graph memory for AI agents: embedded Cypher engine, MCP tools, cited budget-bounded retrieval and versioned project memory

journeyman-agents

Turn any agent into a self-learning system that learns from user feedback - safely, with two lines of code.

langchain-yantrikdb

YantrikDB integration for LangChain — cognitive memory as a VectorStore and ChatMessageHistory. Stored memories decay, consolidate, and get contradiction-checked.

langgraph-checkpoint-supabase

LangGraph checkpoint saver backed by Supabase (Postgres via PostgREST).

langgraph-store-upstash

LangGraph BaseStore implementation backed by Upstash Redis (REST client).

litellm-paritok

Paritok context compression as a LiteLLM Proxy callback — tool filter + content/history compression + non-destructive recall + edit recovery, transparently on every request through LiteLLM Proxy.

llm-compounding-wiki

A self-healing local-LLM wiki that compounds your documents across working, episodic, semantic, and procedural memory tiers.

maximem-synap-deepagents

Synap memory integration for deepagents — a memory backend, retrieval middleware, and tools

memnet-agent

Model-agnostic text agents with associative graph memory, consolidation and dataset export

needlepath-langchain

Needlepath context selection for LangChain agents (AgentMiddleware) and LangGraph.

saihm-crewai

Installs saihm-adapters[crewai], the consolidated package that now holds the SAIHM CrewAI adapter. Import from saihm_adapters (was saihm_memory).

saihm-langgraph

Installs saihm-adapters[langgraph], the consolidated package that now holds the SAIHM LangGraph adapter. Import from saihm_adapters (was saihm_memory).

More in Agent frameworks & infrastructure