# Maximem Synap

> Agentic Context Management

## Docs

- [Maximem Synap Developer Documentation](https://docs.maximem.ai/index.md): Synap gives your AI agents long-term memory. Ingest conversations, extract structured knowledge, and retrieve contextual memories, all through a simple SDK. No infrastructure to manage, no vector databases to tune, no retrieval pipelines to build.
- [What is Maximem Synap?](https://docs.maximem.ai/getting-started/overview.md): Synap is a managed memory layer for AI agents. It sits between your application and your LLM, providing persistent structured memory that survives across sessions, conversations, and deployments. Instead of treating every conversation as a blank slate, your agents can remember, learn, and personaliz…
- [Quickstart](https://docs.maximem.ai/getting-started/quickstart.md): Install the SDK, create your first instance, ingest a memory, retrieve it. ~10 minutes.
- [Your first memory](https://docs.maximem.ai/getting-started/your-first-memory.md): Ingest one message, see what Synap extracts from it, and read it back. The shortest path to understanding what Synap actually does for your agent.
- [Playground](https://docs.maximem.ai/getting-started/playground.md): Try Synap live in your browser: spin up a working memory agent with no install and no API key. The fastest way to see ingestion and retrieval in action before you write any code.
- [Migrate to Synap](https://docs.maximem.ai/migrations/overview.md): Moving from another memory layer? Start here. Pick your source platform, follow its guide, and use the shared migration method to map, backfill, verify, and cut over cleanly.
- [How migration works](https://docs.maximem.ai/migrations/how-it-works.md): The method every Synap migration follows: map your identity model onto scopes, configure the instance for your agent, backfill, pilot, verify, and cut over. Each platform guide builds on this page.
- [Migrate from Mem0 to Synap](https://docs.maximem.ai/migrations/from-mem0.md): Looking for a Mem0 alternative? Map Mem0's user-scoped memory bag onto Synap: concept mapping, SDK call equivalents, and a backfill snippet for a clean cutover.
- [Migrate from Zep to Synap](https://docs.maximem.ai/migrations/from-zep.md): Looking for a Zep alternative? Map Zep's Sessions, Users, and automatic facts onto Synap: concept mapping, SDK call equivalents, and a backfill snippet for a clean cutover.
- [Migrate from Letta (MemGPT) to Synap](https://docs.maximem.ai/migrations/from-letta.md): Looking for a Letta / MemGPT alternative? Map Letta's agent-coupled core and archival memory onto Synap: concept mapping, SDK call equivalents, and the re-architecture involved.
- [Migrate from Supermemory to Synap](https://docs.maximem.ai/migrations/from-supermemory.md): Move your Supermemory export into Synap with a ready-to-run script: map container tags onto Synap scopes, convert the export, verify the scope assignment, and ingest.
- [Integrations Overview](https://docs.maximem.ai/integrations/overview.md): Drop-in packages that add Synap memory to popular AI frameworks and agent SDKs.
- [AI coding agents](https://docs.maximem.ai/integrations/ai-coding-agents.md): A drop-in skill that teaches your AI coding agent (Claude Code, Cursor, Codex, and more) how to add Maximem Synap to your app. The fastest way to integrate: ask, and the agent writes the correct code.
- [MCP Server (No-code)](https://docs.maximem.ai/integrations/mcp.md): Give an agent on Gumloop, n8n, Claude, or any MCP-aware platform persistent memory with just a URL and a token. No code.
- [LangChain](https://docs.maximem.ai/integrations/langchain.md): Build LangChain chains and agents with persistent, per-user memory powered by Synap.
- [LangGraph](https://docs.maximem.ai/integrations/langgraph.md): Persistent checkpoints and cross-thread long-term memory for LangGraph state graphs.
- [LlamaIndex](https://docs.maximem.ai/integrations/llamaindex.md): BaseMemory implementation and semantic retriever for LlamaIndex pipelines.
- [OpenAI Agents SDK](https://docs.maximem.ai/integrations/openai-agents.md): Search and store function tools that let OpenAI Agents recall and persist memories on demand.
- [Pydantic AI](https://docs.maximem.ai/integrations/pydantic-ai.md): Type-safe dependency dataclass and auto-registered tools for Pydantic AI agents.
- [CrewAI](https://docs.maximem.ai/integrations/crewai.md): StorageBackend implementation that routes CrewAI's unified memory through Synap.
- [AutoGen](https://docs.maximem.ai/integrations/autogen.md): BaseTool implementations that give AutoGen agents on-demand memory search and storage.
- [Google ADK](https://docs.maximem.ai/integrations/google-adk.md): FunctionTool factory that adds memory search and storage to Google Agent Development Kit agents.
- [Haystack](https://docs.maximem.ai/integrations/haystack.md): Retriever and memory-writer pipeline components for Haystack RAG pipelines.
- [Agno](https://docs.maximem.ai/integrations/agno.md): Drop-in InMemoryDb replacement that routes Agno user memories through Synap.
- [Semantic Kernel](https://docs.maximem.ai/integrations/semantic-kernel.md): Kernel plugin with memory search and storage functions for Microsoft Semantic Kernel.
- [Microsoft Agent Framework](https://docs.maximem.ai/integrations/microsoft-agent.md): Memory for both Microsoft Agent Framework surfaces — context and history providers for the agent SDK, and MemoryStore and AgentFileStore for the Agent Harness.
- [NeMo Agent Toolkit](https://docs.maximem.ai/integrations/nemo-agent-toolkit.md): MemoryEditor implementation that backs NVIDIA NeMo Agent Toolkit workflows with Synap.
- [LiveKit Agents](https://docs.maximem.ai/integrations/livekit-agents.md): Memory preloading, turn recording, and on-demand search for LiveKit voice agents.
- [Pipecat](https://docs.maximem.ai/integrations/pipecat.md): Frame processors that add memory injection and turn recording to Pipecat voice pipelines.
- [Strands Agents](https://docs.maximem.ai/integrations/strands-agents.md): Synap as a native MemoryStore, short-term context hook, tools, and real-time anticipation feed for Strands Agents.
- [CAMEL-AI](https://docs.maximem.ai/integrations/camel-ai.md): Synap as a native AgentMemory for CAMEL-AI: long-term recall and persistence layered over the agent's own conversation history.
- [Smolagents](https://docs.maximem.ai/integrations/smolagents.md): Synap memory tools and a per-step turn recorder for Hugging Face Smolagents.
- [deepagents](https://docs.maximem.ai/integrations/deepagents.md): A Synap memory backend, query-conditioned recall middleware, and tools for LangChain's deepagents harness.
- [Vercel AI SDK](https://docs.maximem.ai/integrations/vercel-ai-sdk.md): Model middleware that wraps any Vercel AI SDK model with automatic Synap context.
- [Vercel eve](https://docs.maximem.ai/integrations/eve.md): Memory tools and a per-turn short-term-context resolver for Vercel eve agents (TypeScript).
- [Mastra](https://docs.maximem.ai/integrations/mastra.md): SynapMemory class and search/store tools for Mastra (TypeScript).
- [Claude Agent SDK](https://docs.maximem.ai/integrations/claude-agent.md): Hooks and MCP server that give Anthropic's Claude Agent SDK persistent memory, in Python and TypeScript.
- [Installation](https://docs.maximem.ai/setup/installation.md): Install the Synap SDK for Python, JavaScript, or TypeScript, configure environment variables, and verify your setup.
- [Authentication](https://docs.maximem.ai/setup/authentication.md): How to authenticate your SDK with Synap Cloud using API keys.
- [First Integration](https://docs.maximem.ai/setup/first-integration.md): The opinionated, recommended integration path: an end-to-end FastAPI + OpenAI walkthrough that builds a memory-enabled chatbot from scratch.
- [Agent Integration](https://docs.maximem.ai/setup/agent-integration.md): The integration built for agents: open one real-time stream, report each turn as it happens, and let Synap form long-term memory on its own. No per-turn ingestion calls.
- [Integration Reference](https://docs.maximem.ai/setup/detailed-integration.md): The deeper end-to-end integration walkthrough: framework matrix (FastAPI / Flask / Django / Next.js), LLM-provider variants, scope strategy, real-time streaming, and going to production.
- [Initializing the SDK](https://docs.maximem.ai/sdk/initialization.md): Set up the Synap SDK in your application.
- [SDK Configuration](https://docs.maximem.ai/sdk/configuration.md): Customize SDK behavior for your environment.
- [Testing](https://docs.maximem.ai/sdk/testing.md): Patterns for testing application code that depends on Synap: unit tests with mocks, fixtures, and integration tests against a real Instance.
- [Ingestion](https://docs.maximem.ai/sdk/ingestion.md): Send conversations, documents, and other data into Synap.
- [Context Fetch](https://docs.maximem.ai/sdk/context-fetch.md): Fetch contextual memories for your AI agent. Also known as memory retrieval.
- [Context Compaction](https://docs.maximem.ai/sdk/context-compaction.md): Compress conversations while preserving key information.
- [User Profile](https://docs.maximem.ai/sdk/user-profile.md): Configure a structured, per-user profile that Synap builds and maintains from conversations: defined by your own attribute schema.
- [Response Shapes](https://docs.maximem.ai/sdk/response-shapes.md): Pydantic type definitions for every response object the SDK returns. Use as a single source of truth when wiring response data through your application.
- [Error Handling](https://docs.maximem.ai/sdk/error-handling.md): Handle errors gracefully in your Synap integration.
- [Multi-User Memory Scoping](https://docs.maximem.ai/guides/multi-user-scoping.md): Most real-world applications serve multiple users, often across multiple organizations. Synap's scoping system ensures that memories are properly isolated while still enabling shared context where appropriate. This guide explains the scope hierarchy, walks through common patterns, and shows you how…
- [Shaping Your MACA](https://docs.maximem.ai/guides/configuring-memory.md): Every Synap Instance gets a Memory Architecture (MACA) auto-generated from the Use-Case Markdown file you upload. This page explains what MACA controls and how to shape it through your use-case file, with no YAML to author.
- [Production Checklist](https://docs.maximem.ai/guides/production-checklist.md): This checklist covers every aspect of a production-ready Synap integration, from security and SDK configuration to monitoring and operational procedures. Work through each section before your first production deployment, and revisit it before subsequent releases.
- [Patterns](https://docs.maximem.ai/patterns/overview.md): Copy-paste recipes for common Synap integration patterns. Each one solves a specific cross-cutting problem in 30-80 lines.
- [Multi-Tenant SaaS](https://docs.maximem.ai/patterns/multi-tenant-saas.md): Scope memories per customer organization. One Synap Instance, many isolated customer memories.
- [Slack Bot with Memory](https://docs.maximem.ai/patterns/slack-bot.md): Add per-channel and per-user memory to a Slack bot using Slack Bolt + Synap.
- [Voice Agent on LiveKit](https://docs.maximem.ai/patterns/voice-agent-livekit.md): Memory-augmented voice agent on LiveKit Agents. Recall caller history mid-call.
- [RAG over User History](https://docs.maximem.ai/patterns/rag-user-history.md): Pure semantic retrieval over a single user's past conversations. Synap as your RAG.
- [Real-Time Anticipation in a Server](https://docs.maximem.ai/patterns/real-time-anticipation-server.md): Run one Listen stream for a whole multi-tenant process, scope every call per request, and alert on the failure that stays silent.
- [Graceful Degradation](https://docs.maximem.ai/patterns/graceful-degradation.md): What to do when Synap is unreachable. Cache, fallback prompts, queued retries.
- [Replay Conversation History](https://docs.maximem.ai/patterns/replay-history.md): Bulk-ingest historical conversations on Instance creation. One-shot backfill.
- [Cookbook](https://docs.maximem.ai/cookbook/overview.md): Complete, opinionated reference agents you can clone, modify, and ship. Each recipe shows one production-shape pattern end-to-end.
- [Uber: Customer Support](https://docs.maximem.ai/cookbook/consumer-uber.md): Rider-aware customer support agent with refunds, lost-item reports, and clean human handoff.
- [Amazon: Shopping Assistant](https://docs.maximem.ai/cookbook/consumer-amazon.md): Catalog-grounded shopping concierge with order history, preference recall, and return handling.
- [Tier-1 → Tier-2 Escalation Cluster](https://docs.maximem.ai/cookbook/support-tier-escalation.md): Multi-agent support cluster: a triage agent hands off to a specialist with shared memory across both.
- [WhatsApp: Single-WABA Inbound + Human Handoff](https://docs.maximem.ai/cookbook/whatsapp-single-handoff.md): One WhatsApp Business number, AI takes inbound, drops cleanly to a human agent, picks back up afterward.
- [WhatsApp: Single-WABA Inbound + Outbound Campaign](https://docs.maximem.ai/cookbook/whatsapp-single-campaign.md): One WABA number running scheduled outbound campaigns alongside memory-aware inbound support.
- [WhatsApp: Multi-WABA Same-Business Shared Memory](https://docs.maximem.ai/cookbook/whatsapp-multi-waba-shared.md): Multiple WhatsApp Business numbers under one business sharing a single customer memory pool.
- [Voice Concierge (Pipecat + ElevenLabs)](https://docs.maximem.ai/cookbook/voice-concierge.md): Real-time phone agent that recalls caller history mid-call. STT → memory inject → LLM → TTS, all within conversational latency budgets.
- [AI SDR](https://docs.maximem.ai/cookbook/b2b-sdr.md): Outbound B2B prospecting agent: research, personalize, sequence, book, with prospect memory across touches.
- [Salesforce: Enterprise Sales Assistant](https://docs.maximem.ai/cookbook/b2b-salesforce.md): Account-grounded sales assistant with opportunity history and CRM-aware recommendations.
- [AI Companion](https://docs.maximem.ai/cookbook/personal-ai-companion.md): Conversational companion that learns preferences, communication style, and ongoing context across sessions.
- [AI Coach](https://docs.maximem.ai/cookbook/personal-ai-coach.md): Wellness coach with goal tracking, plan adherence memory, and session continuity.
- [Memory Model Cheat Sheet](https://docs.maximem.ai/concepts/memory-model-cheat-sheet.md): One screen for the whole mental model: the identifiers, the two write paths, the four fetch interfaces, and the two mode pairs. Bookmark this.
- [Identifiers & Scopes](https://docs.maximem.ai/concepts/memory-scopes.md): Synap's identifiers (Client, Instance, Customer, User, and Conversation) define who and what your agent remembers about. They map onto a four-level scope chain (User → Customer → Client → World) that determines memory isolation and retrieval priority. This is the canonical mental model for getting m…
- [Memories & Context](https://docs.maximem.ai/concepts/memories-and-context.md): At the heart of Synap are two complementary concepts: **Memories** and **Context**. Memories are the structured knowledge Synap extracts and stores from your data. Context is the curated set of memories assembled and delivered to your AI agent at the moment it needs them. Understanding the relations…
- [Context, End to End](https://docs.maximem.ai/concepts/context-end-to-end.md): What happens to a message after you send it, and what context you can read back. This page follows one message through ingestion, extraction, storage, and retrieval, then walks the four context layers (short-term, long-term, customer, and organizational) each with its own lifecycle, plus how long co…
- [Memory Architecture (MACA)](https://docs.maximem.ai/concepts/memory-architecture.md): Every Synap instance runs on a Memory Architecture Configuration (MACA): the per-instance memory policy that governs what is extracted, how it is scoped and stored, how it is retrieved, and how long it is retained. You don't hand-author it; you describe your agent in a use-case file and Synap genera…
- [Agent Topologies](https://docs.maximem.ai/concepts/agent-topologies.md): How memory works across agent topologies: the runtime loop an agent runs on Synap, a single agent with its own MACA, and multiple agents that share memory across scopes.
- [How Ingestion Works](https://docs.maximem.ai/concepts/how-ingestion-works.md): Ingestion is how raw content becomes structured memory in Synap. Whether you feed in conversation turns as they happen or load historical data in bulk, every document passes through the same pipeline: categorized, extracted, chunked, resolved against existing entities, and stored. This page explains…
- [Fast & Accurate Modes](https://docs.maximem.ai/concepts/retrieval-modes.md): Synap has two speed-vs-thoroughness modes that apply to both writing memories and reading them back. Fast is the real-time default; accurate (long-range on ingestion) does the deeper work for high-value content and complex queries.
- [Real-Time Anticipation](https://docs.maximem.ai/concepts/real-time-anticipation.md): Synap can push context to your agent before it asks. The Listen stream is a long-lived gRPC connection that carries activity signals up and anticipated context bundles down, turning the next fetch() into a local cache read.
- [Entity Resolution & Master Data Management](https://docs.maximem.ai/concepts/entity-resolution.md): Entity Resolution (ER) is Synap's ability to identify and link mentions of the same real-world entity across different conversations and documents. When a user says "John", "Mr. Smith", "my manager", and "the person I met at the conference", Synap determines whether these all refer to the same indiv…
- [API Reference](https://docs.maximem.ai/sdk-reference/overview.md): The Synap SDK provides programmatic access for **bootstrap ingestion**, **organizational and customer context retrieval**, and **data migration**. This page covers cross-cutting concerns you will encounter through the SDK: authentication, rate limits, error handling, correlation IDs, and pagination.
- [initialize](https://docs.maximem.ai/sdk-reference/lifecycle/initialize.md): Initialize the SDK. Must be called before any context operations.
- [configure](https://docs.maximem.ai/sdk-reference/lifecycle/configure.md): Update SDK configuration. Must be called before initialize().
- [shutdown](https://docs.maximem.ai/sdk-reference/lifecycle/shutdown.md): Gracefully shutdown the SDK. Flushes telemetry, closes connections, and releases resources.
- [as_tool](https://docs.maximem.ai/sdk-reference/lifecycle/as-tool.md): Return an LLM-ready tool definition for fetching Synap context.
- [memories.create](https://docs.maximem.ai/sdk-reference/memories/create.md): Ingest a document into Synap's memory pipeline asynchronously.
- [memories.batch_create](https://docs.maximem.ai/sdk-reference/memories/batch-create.md): Ingest multiple documents in a single call for bootstrap or bulk ingestion.
- [memories.create_from_file](https://docs.maximem.ai/sdk-reference/memories/create-from-file.md): Ingest a file from disk, an open file-like object, or raw text into the memory pipeline.
- [memories.status](https://docs.maximem.ai/sdk-reference/memories/status.md): Check the progress of an asynchronous ingestion job.
- [memories.wait_for_completion](https://docs.maximem.ai/sdk-reference/memories/wait-for-completion.md): Block until an ingestion job reaches a terminal status, or raise on timeout.
- [memories.get](https://docs.maximem.ai/sdk-reference/memories/get.md): Retrieve a specific memory by its ID.
- [memories.update](https://docs.maximem.ai/sdk-reference/memories/update.md): Update the content of an existing memory using a merge strategy.
- [memories.delete](https://docs.maximem.ai/sdk-reference/memories/delete.md): Permanently delete a memory by its ID.
- [conversation.record_message](https://docs.maximem.ai/sdk-reference/conversation/record-message.md): Record a single conversation message (user or assistant turn) into Synap.
- [conversation.record_messages_batch](https://docs.maximem.ai/sdk-reference/conversation/record-messages-batch.md): Record multiple conversation messages in a single batched call.
- [conversation.ingest_transcript](https://docs.maximem.ai/sdk-reference/conversation/ingest-transcript.md): One-shot async push of a full conversation transcript (plus optional analysis) for background extraction and summarization.
- [conversation.context.fetch](https://docs.maximem.ai/sdk-reference/conversation-context/fetch.md): Fetch conversation-scoped context (facts, preferences, episodes) for a specific conversation.
- [conversation.context.compact](https://docs.maximem.ai/sdk-reference/conversation-context/compact.md): Trigger asynchronous compaction of a conversation into a compressed summary.
- [conversation.context.get_compacted](https://docs.maximem.ai/sdk-reference/conversation-context/get-compacted.md): Retrieve an existing compacted summary for a conversation without triggering a new compaction.
- [conversation.context.get_compaction_status](https://docs.maximem.ai/sdk-reference/conversation-context/get-compaction-status.md): Check whether a conversation has compacted context, whether it's stale, and whether a compaction run is in progress.
- [conversation.context.get_context_for_prompt](https://docs.maximem.ai/sdk-reference/conversation-context/get-context-for-prompt.md): Get compacted context combined with recent un-compacted messages, pre-formatted for LLM prompt injection.
- [fetch](https://docs.maximem.ai/sdk-reference/context/fetch.md): Fetch and merge context across all relevant scopes in a single call.
- [user.context.fetch](https://docs.maximem.ai/sdk-reference/context/user-fetch.md): Retrieve user-scoped context: facts, preferences, episodes, and temporal events about a specific end user.
- [customer.context.fetch](https://docs.maximem.ai/sdk-reference/context/customer-fetch.md): Retrieve customer-scoped context: shared organizational knowledge, policies, and team-wide memories visible to every user within a customer.
- [client.context.fetch](https://docs.maximem.ai/sdk-reference/context/client-fetch.md): Retrieve organizational (client-scoped) context: product knowledge, documentation, and announcements visible to every user across every customer.
- [user.get_profile](https://docs.maximem.ai/sdk-reference/user/get-profile.md): Fetch a user's profile document: client-defined critical attributes plus a free-text overview.
- [instance.listen](https://docs.maximem.ai/sdk-reference/instance/listen.md): Start a bidirectional gRPC stream that delivers real-time anticipated context bundles to your agent.
- [instance.send_message](https://docs.maximem.ai/sdk-reference/instance/send-message.md): Send a conversation event over the active gRPC stream so Synap can anticipate context for the agent's next turn.
- [instance.stop_listening](https://docs.maximem.ai/sdk-reference/instance/stop-listening.md): Close the active gRPC stream opened by instance.listen and release the transport.
- [cache.clear](https://docs.maximem.ai/sdk-reference/cache/clear.md): Clear all locally-cached SDK data, including fetched context bundles and anticipation entries.
- [cache.clear_user](https://docs.maximem.ai/sdk-reference/cache/clear-user.md): Clear all locally-cached SDK data for a single user. Useful for GDPR right-to-be-forgotten flows.
- [cache.clear_customer](https://docs.maximem.ai/sdk-reference/cache/clear-customer.md): Clear all locally-cached SDK data for a single customer (B2B tenant).
- [cache.stats](https://docs.maximem.ai/sdk-reference/cache/stats.md): Return a snapshot of local cache state: entry counts, storage size, and per-backend breakdown.
- [credits.get_balance](https://docs.maximem.ai/sdk-reference/credits/get-balance.md): Return the current credit balance and per-bucket breakdown for your wallet.
- [credits.get_ledger](https://docs.maximem.ai/sdk-reference/credits/get-ledger.md): Paginate through the credit ledger for your wallet, with optional filtering by entry type and time range.
- [credits.estimate](https://docs.maximem.ai/sdk-reference/credits/estimate.md): Get a dry-run credit cost quote for a planned operation, without spending any credits.
- [credits.redeem](https://docs.maximem.ai/sdk-reference/credits/redeem.md): Apply a redeem code to the current wallet and return the granted credits and new balance.
- [Error Codes](https://docs.maximem.ai/sdk-reference/errors.md): All Synap API errors follow a consistent format with a human-readable `error` message, a machine-readable `code`, and an optional `details` object with additional context.
- [Migration](https://docs.maximem.ai/sdk-reference/migration.md): SDK methods for migrating data to Synap from other memory systems.
- [Performance & Limits](https://docs.maximem.ai/resources/performance-limits.md): How to think about latency, throughput, and limits in Synap. Specific numbers come from your own measurements in Dashboard → Usage.
- [Pricing & Credits](https://docs.maximem.ai/resources/pricing.md): How Synap bills: every plan includes a monthly allotment of credits, and memory operations consume credits. Start free, scale as your usage grows, and bring your own LLM key on paid plans.
- [Dashboard](https://docs.maximem.ai/dashboard/overview.md): The Synap Dashboard is the web management interface for your deployment. Create and manage instances, generate API keys, and inspect the memory architecture Synap generates for each agent.
- [Synap CLI](https://docs.maximem.ai/cli/overview.md): Provision and operate Synap from your terminal with maximem-synap, the command-line counterpart to the Dashboard.
- [CLI command reference](https://docs.maximem.ai/cli/commands.md): Every maximem-synap command and flag — auth, instances, api-keys, client, requests, memories, and config.
- [Glossary](https://docs.maximem.ai/resources/glossary.md): A comprehensive reference of terms, concepts, and identifiers used throughout the Synap platform.
- [FAQ](https://docs.maximem.ai/resources/faq.md): Common questions about Synap, organized by topic. If your question is not answered here, check the [Support](/resources/support) page for additional help channels.
- [Security & Trust](https://docs.maximem.ai/resources/security-trust.md): How Synap handles encryption, isolation, data residency, deletion, and compliance.
- [Support](https://docs.maximem.ai/resources/support.md): Whether you are stuck on an integration, have a question about the API, or need to report an issue, we are here to help.
- [Changelog](https://docs.maximem.ai/resources/changelog.md): All notable changes to the Synap SDK and API are documented here. This project follows [Semantic Versioning](https://semver.org/) (SemVer).
- [Maximem Vity](https://docs.maximem.ai/vity/overview.md): Maximem Vity gives the AI apps you already use a shared, persistent memory. Install a plugin or browser extension and your context follows you across ChatGPT, Claude, Gemini, OpenClaw, and more, with no code.
- [Vity MCP Server](https://docs.maximem.ai/vity/mcp/overview.md): Connect any MCP-capable agent (Claude Code, Cursor, and more) to your Vity memory with a URL and an API key. No code.
- [Tools & prompts](https://docs.maximem.ai/vity/mcp/tools.md): Every tool, prompt and resource the Vity MCP server exposes, with arguments, costs and guidance on which to reach for.
- [OpenClaw](https://docs.maximem.ai/vity/openclaw.md): Memory plugin for OpenClaw: syncs AI context across OpenClaw, ChatGPT, Claude, Gemini, Manus, and more.
- [Hermes Agent](https://docs.maximem.ai/vity/hermes.md): Persistent, cross-session semantic memory for the Hermes Agent, distributed as a standalone plugin.
- [Instance Visibility](https://docs.maximem.ai/guides/instance-visibility.md): Control which of a client's Instances can see which other Instances' memories at retrieval time. A first-class, client-level policy you manage from the dashboard, off by default, so today's sharing behaviour is preserved until you opt in.