Synap · Integrations # Native memory for every agent framework you ship on. Maximem Synap ships 22 native framework integrations today — each with a dedicated docs page and, for our flagship integrations, a deep-dive blog post. Every integration is in production and verified against [docs.maximem.ai/integrations](https://docs.maximem.ai/integrations/overview). - ![LangChain](https://registry.npmmirror.com/@lobehub/icons-static-png/1.24.0/files/dark/langchain-color.png) ## LangChain Drop-in memory provider for LangChain chains and agents — replaces ConversationBufferMemory with persistent, cross-session recall. [Read the docs](https://docs.maximem.ai/integrations/langchain)[Read the deep dive](https://www.maximem.ai/blog/langchain-maximem-synap-memory-integration) - ![LangGraph](https://www.maximem.ai/assets/images/icons/frameworks/langgraph.svg) ## LangGraph Persistent memory across LangGraph nodes — state that survives graph reruns, checkpoints, and human-in-the-loop pauses. [Read the docs](https://docs.maximem.ai/integrations/langgraph)[Read the deep dive](https://www.maximem.ai/blog/langgraph-synap-memory-integration) - ![LlamaIndex](https://www.llamaindex.ai/brand/llamaindex-logo-white.svg) ## LlamaIndex Long-term agent memory for LlamaIndex query engines, workflows, and agentic retrievers. [Read the docs](https://docs.maximem.ai/integrations/llamaindex)[Read the deep dive](https://www.maximem.ai/blog/llamaindex-memory-synap-integration) - ![OpenAI Agents](https://registry.npmmirror.com/@lobehub/icons-static-png/1.24.0/files/dark/openai.png) ## OpenAI Agents Native memory tool for the OpenAI Agents SDK — drop into any agent loop without rewriting tool definitions. [Read the docs](https://docs.maximem.ai/integrations/openai-agents)[Read the deep dive](https://www.maximem.ai/blog/openai-agents-memory-synap-integration) - ![Pydantic AI](https://pydantic.dev/docs/ai/img/pydantic-ai-light.svg) ## Pydantic AI Typed memory backing for Pydantic AI agents — model-validated reads and writes, no string parsing. [Read the docs](https://docs.maximem.ai/integrations/pydantic-ai)[Read the deep dive](https://www.maximem.ai/blog/pydantic-ai-memory-synap-integration) - ![CrewAI](https://cdn.prod.website-files.com/69a111972d2e0bbcc6adb934/69a111972d2e0bbcc6adbbba_Logo.svg) ## CrewAI Shared memory across CrewAI crews and tasks — every agent in the crew sees the same evolving context. [Read the docs](https://docs.maximem.ai/integrations/crewai) - ![AutoGen](https://www.ag2.ai/_next/image?url=%2Fag2-logo-black.png&w=256&q=75) ## AutoGen Cross-conversation memory for AutoGen multi-agent groups — durable state outside a single GroupChat run. [Read the docs](https://docs.maximem.ai/integrations/autogen) - ![Google ADK](https://storage.googleapis.com/gweb-developer-goog-blog-assets/images/ADK-512-color_banner.original.png) ## Google ADK Memory layer for Google Agent Development Kit agents — built for ADK sessions and tool-calling loops. [Read the docs](https://docs.maximem.ai/integrations/google-adk) - ![Haystack](https://haystack.deepset.ai/images/logos/haystack.png) ## Haystack Persistent context for Haystack pipelines and agents — memory components that compose with existing nodes. [Read the docs](https://docs.maximem.ai/integrations/haystack) - ![Agno](https://www.maximem.ai/assets/images/icons/frameworks/agno.svg) ## Agno Memory provider for Agno agent workflows — keeps team and session memory in sync across runs. [Read the docs](https://docs.maximem.ai/integrations/agno) - ![Semantic Kernel](https://registry.npmmirror.com/@lobehub/icons-static-png/1.24.0/files/dark/microsoft-color.png) ## Semantic Kernel Memory plugin for Microsoft Semantic Kernel — works in both the Python and .NET SDKs. [Read the docs](https://docs.maximem.ai/integrations/semantic-kernel) - ![Microsoft Agent Framework](https://www.maximem.ai/assets/images/icons/frameworks/microsoft.png) ## Microsoft Agent Framework Memory backing for the Microsoft Agent Framework — drop-in for any AgentChat or Group conversation. [Read the docs](https://docs.maximem.ai/integrations/microsoft-agent) - ![NeMo Agent Toolkit](https://www.maximem.ai/assets/images/icons/frameworks/nvidia.svg) ## NeMo Agent Toolkit Memory toolkit for NVIDIA NeMo Agent Toolkit — integrates with NeMo agent and workflow primitives. [Read the docs](https://docs.maximem.ai/integrations/nemo-agent-toolkit) - ![LiveKit Agents](https://www.maximem.ai/assets/images/icons/frameworks/livekit.svg) ## LiveKit Agents Sub-100ms memory for LiveKit voice agents — anticipatory retrieval fast enough for real-time turn-taking. [Read the docs](https://docs.maximem.ai/integrations/livekit-agents) - ![Pipecat](https://www.maximem.ai/assets/images/icons/frameworks/pipecat.svg) ## Pipecat Real-time conversational memory for Pipecat pipelines — built for voice-first agent loops. [Read the docs](https://docs.maximem.ai/integrations/pipecat) - ![Claude Agent SDK](https://www.maximem.ai/assets/images/icons/frameworks/anthropic.svg) ## Claude Agent SDK Memory tool for the Claude Agent SDK — usable from any Claude agent loop without bespoke glue code. [Read the docs](https://docs.maximem.ai/integrations/claude-agent) - ![Mastra](https://www.maximem.ai/assets/images/icons/frameworks/mastra.svg) ## Mastra TypeScript memory module for Mastra agent flows — typed reads and writes from any Mastra workflow node. [Read the docs](https://docs.maximem.ai/integrations/mastra) - ![Vercel AI SDK](https://www.maximem.ai/assets/images/icons/frameworks/vercel.svg) ## Vercel AI SDK Server-side memory layer for the Vercel AI SDK — wraps streamText / generateText with persistent context. [Read the docs](https://docs.maximem.ai/integrations/vercel-adk) - ![Vercel eve](https://www.maximem.ai/assets/images/icons/frameworks/vercel.svg) ## Vercel eve Memory tools plus a per-turn short-term-context resolver for Vercel eve agents, in TypeScript. [Read the docs](https://docs.maximem.ai/integrations/eve) - ![Strands Agents](https://www.maximem.ai/assets/images/icons/frameworks/strands.svg) ## Strands Agents Native MemoryStore for Strands Agents — short-term context hook, memory tools, and a real-time anticipation feed. [Read the docs](https://docs.maximem.ai/integrations/strands-agents) - ![CAMEL-AI](https://www.maximem.ai/assets/images/icons/frameworks/camel.png) ## CAMEL-AI Native AgentMemory for CAMEL-AI — long-term recall layered over the agent's own conversation history. [Read the docs](https://docs.maximem.ai/integrations/camel-ai) - ![Smolagents](https://registry.npmmirror.com/@lobehub/icons-static-png/1.24.0/files/dark/huggingface.png) ## Smolagents Memory tools and a per-step turn recorder for Hugging Face Smolagents — persistence across agent runs. [Read the docs](https://docs.maximem.ai/integrations/smolagents) ## Building on a framework we don't list yet? The [Synap SDK](https://docs.maximem.ai/sdk/initialization) (Python and TypeScript) and REST API work from anywhere — and most new framework adapters land within a release. Tell us what you're shipping on. [Start with the docs](https://docs.maximem.ai)[Request a framework](https://www.maximem.ai/about#contact)[Back to Synap](https://www.maximem.ai/synap) --- Source: [https://www.maximem.ai/synap/integrations](https://www.maximem.ai/synap/integrations)