Synap

MCP文档知识

提供方 未标注

文档知识 未标注 未标注 社区 / 第三方 Claude DesktopClaudeCursorVS Code

用于Synap长期代理记忆的可流式HTTP MCP服务器。提供存储、召回和遗忘工具,支持按租户隔离,由托管记忆服务提供支持。

一句话选型结论

按资料字段整理

Synap 属于文档知识类 MCP 服务器,传输方式未标注,鉴权方式未标注,可直接接入 Claude Desktop、Claude、Cursor 等,没有现成安装命令,需按官方文档接入。接入前先确认权限范围;涉及写入、删除或付款的操作,建议先在测试环境验证。

分类文档知识 传输方式未标注 鉴权未标注 部署方式未标注
GitHub 星标 未标注 仓库热度,无公开仓库时显示未标注
工具数 未标注 暴露给模型的工具数量
资源 / 提示词 0 / 0 资源与提示词模板数量
维护方 社区 / 第三方 核验等级 仅资料核对

工具与能力

文档知识
数量来自来源目录的标注,具体工具清单以官方文档为准
工具数量未标注暴露给模型可调用的工具个数
资源数量0可读取的资源条目
提示词数量0内置提示词模板数量

能力标签

支持客户端

适用场景

记忆

安装与配置

未标注 未标注
上游未给出传输方式
  1. 1
    准备运行环境

    按官方文档确认运行环境(常见为 Node.js 或 Python),装好后再执行安装命令。

  2. 2
    安装服务

    复制上面的安装命令执行;命令里带占位符的位置,换成自己的密钥或路径。

  3. 3
    写入客户端配置

    在客户端的 MCP 配置里填好启动命令和参数,保存后完全退出客户端再打开,让新配置生效。

  4. 4
    验证是否可用

    连接成功后随便调一个只读工具,确认能返回结果,再接入正式流程。

典型使用场景

3 类
按分类与标签整理的常见用法,具体以官方文档为准
文档检索问答

在你的文档库里按问题找答案。

知识库读写

把新资料写进知识库,随用随取。

内容整理

把零散资料归纳成结构化笔记。

选择建议

选之前先看这几条
按条目字段给出的判断,不替你决定用不用

值得选的地方

  • 已适配 Claude Desktop、Claude、Cursor,换客户端不用重新研究配置。

先想清楚的地方

  • 没有现成安装命令,需要按官方文档自己填启动命令和参数。
  • 资料没标注工具数量,实际能力要装好后确认。
  • 版本更新与行为细节以官方仓库为准。

更适合

  • 需要在文档知识场景里让模型直接调用外部能力的人。
  • 已经在用 Claude Desktop、Claude 的用户,接入路径最短。
  • 想先快速试一下、能接受在本地或自有环境跑服务的人。

不太适合

  • 需要厂商级 SLA 和技术支持的生产环境。

同类对比

6 个同类
同分类里挑最接近的几条,字段以各自详情页为准
MCP 服务器工具数传输方式部署方式安装命令最后核验
Synap当前 未标注 未标注 未标注 无 未标注
dify 未标注 stdio · 本地进程 本地部署 有 2026-04-11
open-webui 未标注 stdio · 本地进程 本地部署 有 2026-04-11
JeecgBoot 未标注 stdio · 本地进程 本地部署 有 2026-04-11
Cherry Studio 未标注 未标注 未标注 无 2026-05-17
mempalace 未标注 stdio · 本地进程 本地部署 有 2026-04-11

服务器档案

文档知识
字段来自项目仓库与公开索引,中文说明由本站标注
提供方未标注上游标注的维护方 未标注
分类文档知识本站按上游分类展示
连接方式未标注上游未给出传输方式
鉴权方式未标注远程服务建议用最小权限凭据
维护方社区 / 第三方核验等级 仅资料核对
包名 / 运行时未标注 · 未标注本地安装时用到的包标识与运行时
部署类型未标注上游给出的部署形态
最近核验未标注上游最后核验时间

详细介绍

12.8 KB
来自项目仓库与上游目录的原文,未做删改

Your agents forget between conversations. Synap makes them remember.

Docs ·
Quickstart ·
Benchmark results ·
Evals (reproduce our numbers) ·
Discussions ·
Dashboard


The memory layer for production AI agents

Synap gives your agents memory that lasts across conversations, sessions and devices. It scores 95.6% on LongMemEval and 93.2% on LoCoMo (every LongMemEval answer is published, reproduce with our open harness), fetches context in ~15ms P50 (internal measurement) before your agent asks, and ships native packages for 24 agent frameworks.

LangChain · LangGraph · LlamaIndex · CrewAI · AutoGen · Haystack · Google ADK · OpenAI Agents · Semantic Kernel · Pydantic AI · Agno · LiveKit · Pipecat · Claude Agent · Mastra · Vercel AI SDK · NeMo Agent Toolkit · Microsoft Agent Framework

What's open, what's hosted

This repo (Apache 2.0) Synap Cloud (managed)
Python + JS SDKs, 24 framework packages, MCP adapter ✅ open source uses them
Memory engine: ingestion, entity resolution, retrieval, anticipation — ✅ runs here
What you need pip install maximem-synap an API key. Free Trial plan: 12,500 credits/month, 1 agent, no card required (pricing)

Every plan, including the free one, gets every Synap capability. Plans differ on volume and support, not features.


Benchmarks

Synap's scores on the two standard long-term memory benchmarks, produced with our open-source harness on the official dataset releases.

Benchmark Synap accuracy Scope Answer model / judge
LongMemEval, all 500 questions (results) 95.6% (478 / 500) Full set, 6 categories gemini-3.8-flash / gpt-4o
LongMemEval, answerable questions (results) 95.7% (450 / 470) 30 abstention questions excluded gemini-3.8-flash / gpt-4o
LongMemEval retrieval, Recall@20 (results) 98.1% (461 / 470) Abstention excluded none / gpt-4o
LoCoMo (results) 93.2% Cat 1–4, adversarial excluded gpt-5-mini / gpt-5-mini

The LongMemEval run is from October 2026 and the LoCoMo run from 2026-06-20. For LongMemEval, the retrieved memories, answer and judge verdict for every one of the 500 questions are published, so you can recompute the score.

Other vendors publish their own numbers under different answer models and judges. Our harness ships adapters for Mem0, Zep and Supermemory, so you can run them side by side yourself. How scores differ across setups →

Category breakdown, methodology and every scope decision → eval_benchmark_runs_output


Install```bash

Python

pip install maximem-synap

JavaScript / TypeScript

npm install @maximem/synap-js-sdk


### Using a coding agent?

Paste this into Claude Code, Codex or Cursor:

> Add Synap memory to this project. Run `pip install maximem-synap` (or `npm i @maximem/synap-js-sdk`), then install the Synap skill (`npx skills add maximem-ai/maximem_synap_sdk --skill synap -y`, or https://github.com/maximem-ai/maximem_synap_sdk/tree/main/skills/synap) and follow it to wire memory into the agent framework this repo uses. If I have a one-time code, use it. If I already have an instance and a key in `.env`, use those. Never ask me to paste a key into the chat.

Claude Code```bash
git clone --depth 1 https://github.com/maximem-ai/maximem_synap_sdk /tmp/synap && cp -r /tmp/synap/skills/synap ~/.claude/skills/synap

Codex```bash
git clone --depth 1 https://github.com/maximem-ai/maximem_synap_sdk /tmp/synap && mkdir -p ~/.agents/skills && cp -r /tmp/synap/skills/synap-codex ~/.agents/skills/synap


Cursor / any MCP client

Add the Synap MCP server URL and your API key from the dashboard. See `packages/mcps/synap-mcp-server/`.

---

## 60-second quickstart

Your agent forgets. Synap remembers across conversations, sessions, and devices.

The SDK connects to the hosted Synap cloud service, so you'll need an API key. There's no local server to run: memory processing happens in Synap's cloud, not in this package.```python
import asyncio
from maximem_synap import MaximemSynapSDK

sdk = MaximemSynapSDK(api_key="your-api-key")

async def main():
    await sdk.initialize()

    # Monday's standup
    await sdk.conversation.record_message(
        conversation_id="mon-standup",
        user_id="alice",
        role="user",
        content="I'm migrating our auth service to OAuth2 this sprint.",
    )

    # Friday: completely different conversation, same user
    context = await sdk.fetch(
        conversation_id="fri-review",
        user_id="alice",
        search_query=["what is alice working on?"],
    )

    print(context.formatted_context)
    # → "Alice is migrating the auth service to OAuth2 this sprint."

asyncio.run(main())

JavaScript / TypeScript```javascript
const { createClient } = require('@maximem/synap-js-sdk');

const client = createClient({ apiKey: 'your-api-key' });
await client.init();

// Record
await client.conversation.recordMessage({
conversationId: 'mon-standup',
userId: 'alice',
role: 'user',
content: "I'm migrating our auth service to OAuth2 this sprint.",
});

// Fetch later, anywhere
const context = await client.fetchUserContext({
userId: 'alice',
query: 'what is alice working on?',
});

console.log(context.formattedContext);


---

## How it works: anticipatory memory

Most memory layers wait for the agent to ask. Synap works out what the agent will need next and has it ready. Six parts make that work.

### 🎯 Anticipatory Retrieval

Synap **pre-fetches context before your agent requests it**. ~15ms P50 latency in production (Maximem internal measurement). For voice AI agents, this is the difference between natural conversation and awkward pauses.

### 🔗 Entity Resolution

When a user says *"my manager"* in turn 3 and *"Sarah"* in turn 12, Synap resolves them automatically. Cross-session, cross-conversation, without the agent doing any work.

### ⏳ Temporal Awareness

Context from 30 minutes ago and context from 30 days ago should not carry equal weight. Synap applies temporal decay and relevance scoring so your agent surfaces the right information at the right time.

### 🧠 Conscious Forgetting

When a user says *"ignore what I said about the budget,"* Synap processes that as a retraction, not just more context to store. Contradiction handling is built into the pipeline.

### 🏗️ Custom Memory Architectures

No universal memory model. Synap builds customized memory architectures per use case. Customer support agents and voice AI agents need different context strategies. Synap handles both.

### 🏢 Multi-Tenant Scoping

Built for B2B from day one. Memory is scoped across a four-level hierarchy:```
client          → shared knowledge across your entire platform
  └── customer  → per-company context (multi-tenant B2B)
        └── user       → per-user memory and preferences
              └── conversation → in-session history

One fetch() call merges all relevant scopes in parallel.


Framework integrations

Installable packages, not code snippets. Deep framework surfaces with callbacks, graph nodes, retrievers, memories, and plugins.

LangChain```bash

pip install maximem-synap maximem-synap-langchain
``````python
from maximem_synap import MaximemSynapSDK
from synap_langchain import SynapChatMessageHistory
from langchain_openai import ChatOpenAI
from langchain_core.runnables.history import RunnableWithMessageHistory

sdk = MaximemSynapSDK(api_key="your-api-key")
await sdk.initialize()

chain = RunnableWithMessageHistory(
ChatOpenAI(),
lambda session_id: SynapChatMessageHistory(
sdk=sdk, conversation_id=session_id, user_id="alice",
),
)


### CrewAI```bash
pip install maximem-synap maximem-synap-crewai
``````python
from synap_crewai import SynapStorageBackend

crew = Crew(
    agents=[...], tasks=[...],
    memory=True,
    storage=SynapStorageBackend(sdk=sdk, user_id="alice"),
)

LlamaIndex```bash

pip install maximem-synap maximem-synap-llamaindex
``````python
from synap_llamaindex import SynapChatMemory

memory = SynapChatMemory(sdk=sdk, user_id="alice")
agent = ReActAgent.from_tools(tools, memory=memory)
```

All integrations

Framework Package Install
LangChain maximem-synap-langchain pip install maximem-synap-langchain
LangGraph maximem-synap-langgraph pip install maximem-synap-langgraph
LlamaIndex maximem-synap-llamaindex pip install maximem-synap-llamaindex
CrewAI maximem-synap-crewai pip install maximem-synap-crewai
AutoGen maximem-synap-autogen pip install maximem-synap-autogen
Haystack maximem-synap-haystack pip install maximem-synap-haystack
Google ADK maximem-synap-google-adk pip install maximem-synap-google-adk
OpenAI Agents SDK maximem-synap-openai-agents pip install maximem-synap-openai-agents
Semantic Kernel maximem-synap-semantic-kernel pip install maximem-synap-semantic-kernel
Pydantic AI maximem-synap-pydantic-ai pip install maximem-synap-pydantic-ai
Agno maximem-synap-agno pip install maximem-synap-agno
LiveKit Agents maximem-synap-livekit-agents pip install maximem-synap-livekit-agents
Pipecat maximem-synap-pipecat pip install maximem-synap-pipecat
Claude Agent (Python) maximem-synap-claude-agent pip install maximem-synap-claude-agent
Claude Agent (TypeScript) @maximem/synap-claude-agent npm i @maximem/synap-claude-agent
Mastra @maximem/synap-mastra npm i @maximem/synap-mastra
Vercel AI SDK @maximem/synap-vercel-adk npm i @maximem/synap-vercel-adk
Vercel eve @maximem/synap-eve npm i @maximem/synap-eve
NVIDIA NeMo Agent Toolkit maximem-synap-nemo-agent-toolkit pip install maximem-synap-nemo-agent-toolkit
Microsoft Agent Framework maximem-synap-microsoft-agent pip install maximem-synap-microsoft-agent
Strands Agents maximem-synap-strands-agents pip install maximem-synap-strands-agents
CAMEL-AI maximem-synap-camel-ai pip install maximem-synap-camel-ai
Smolagents maximem-synap-smolagents pip install maximem-synap-smolagents
Deepagents maximem-synap-deepagents pip install maximem-synap-deepagents
Remote MCP Server maximem-synap-mcp-server pip install maximem-synap-mcp-server

MCP server

Give no-code and low-code agents (Gumloop, n8n, and any MCP-compatible client) persistent memory with nothing but an MCP URL and your Synap API key. No SDK, no code. The server exposes Synap's memory as four MCP tools (log_exchange, check_memory_status, recall_context, list_recent_memories) over Streamable HTTP.

It's a stateless adapter over the hosted Synap API: each call maps to one REST operation and your Bearer token is forwarded verbatim, so there's no separate backend to run. Use the managed endpoint (grab the URL and token from your dashboard), or self-host the adapter from source.

→ Source & self-hosting: packages/mcps/synap-mcp-server/


Deep dives

Understand the system before building on it:

  • 📘 Why we built Synap: the problem with current AI memory systems
  • ⚙️ How Synap works under the hood: architecture, retrieval pipeline, and design decisions
  • 📊 Benchmark results: 95.6% on LongMemEval, 93.2% on LoCoMo, methodology, and reproducibility
  • 🧪 Evaluation harness: run LoCoMo and LongMemEval yourself against Synap, Mem0, Zep and Supermemory

Agent skills

Drop-in instructions that teach coding agents how to wire Synap into your codebase. Install steps are in Using a coding agent?.

  • Synap skill for Claude Code: SDK setup, scoping (User/Customer/Client), ingestion, retrieval, and one-page wiring guides for all supported frameworks.
  • Synap skill for Codex: the same guide, packaged for Codex (~/.agents/skills/synap).

Requirements

  • Python SDK: Python 3.11+
  • JavaScript SDK: Node 20+ (Python 3.11+ for the bridge layer)
  • A Synap API key: get one at maximem.ai

Resources & community

  • 📖 Documentation
  • 🚀 Dashboard
  • 💬 GitHub Discussions: questions, ideas, show what you built
  • 🔒 Security policy
  • 🤖 AGENTS.md and llms.txt for coding agents
  • 𝕏 Twitter / X
  • 💼 LinkedIn

Contributing

This repo is a published mirror of Maximem's monorepo, so everything under packages/ is overwritten on each sync and pull requests against it are closed. Bug reports, gaps, and new-framework requests are very welcome as issues, and questions go to Discussions. See CONTRIBUTING.md for how to run the code locally and what a new integration needs.


License

Apache 2.0 (see LICENSE). Each package declares its own license in its metadata; the core Python and JS SDKs and the Vercel AI SDK integration are MIT.


Built by Maximem AI

常见问题

6 问
答案由本站依据条目字段整理,不引用上游原文
Synap 怎么安装?

资料没有给出安装命令,请到官方仓库或文档按说明接入;这类条目多数是生态应用,或尚未发布可安装包。

Synap 怎么在 Claude Desktop、Claude、Cursor 里配置?

它的传输方式未标注,在客户端的 MCP 配置里填好启动命令和参数,保存后完全退出客户端再打开,配置才会生效。

Synap 收费吗?

本站不代收费用,也没有标注具体价格。是否收费取决于服务本身和背后的接口额度,正式使用前按官方说明确认。

Synap 需要 API Key 吗?

资料没有标注鉴权方式,是否需要密钥取决于服务本身,接入前按官方文档确认。

Synap 支持哪些客户端?

资料标注支持 Claude Desktop、Claude、Cursor、VS Code、Gemini CLI、Codex;其他客户端只要能配置 MCP Server,也能用同样的命令或地址接入。

Synap 能提供哪些能力?

资料显示能力标签包括 记忆。具体工具清单以官方文档为准。

热门专题

按标签挑服务器
全部专题 →

服务器信息以作者仓库与官方文档为准;分类、传输方式与鉴权方式的中文说明为中文整理,最近核验 未标注。