经 AI Skill Hub 精选评估,MarsNMe 获评「推荐使用」。这款MCP工具在功能完整性、社区活跃度和易用性方面表现出色,AI 评分 7.5 分,适合有一定技术背景的用户使用。
Agent-agnostic AI memory MCP — never forget a conversation again,提供AI记忆功能,提高对话流程效率。
MarsNMe 是一款遵循 MCP(Model Context Protocol)标准协议的 AI 工具扩展。通过 MCP 协议,它可以让 Claude、Cursor 等主流 AI 客户端直接访问和操作外部工具、数据源和服务,实现 AI 能力的无缝扩展。无论是文件操作、数据库查询还是 API 调用,都可以通过自然语言在 AI 对话中直接触发,极大提升生产效率。
Agent-agnostic AI memory MCP — never forget a conversation again,提供AI记忆功能,提高对话流程效率。
MarsNMe 是一款遵循 MCP(Model Context Protocol)标准协议的 AI 工具扩展。通过 MCP 协议,它可以让 Claude、Cursor 等主流 AI 客户端直接访问和操作外部工具、数据源和服务,实现 AI 能力的无缝扩展。无论是文件操作、数据库查询还是 API 调用,都可以通过自然语言在 AI 对话中直接触发,极大提升生产效率。
# 方式一:通过 Claude Code CLI 一键安装
claude skill install https://github.com/Marsmanleo/MarsNMe
# 方式二:手动配置 claude_desktop_config.json
{
"mcpServers": {
"marsnme": {
"command": "npx",
"args": ["-y", "marsnme"]
}
}
}
# 配置文件位置
# macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
# Windows: %APPDATA%/Claude/claude_desktop_config.json
# 安装后在 Claude 对话中直接使用 # 示例: 用户: 请帮我用 MarsNMe 执行以下任务... Claude: [自动调用 MarsNMe MCP 工具处理请求] # 查看可用工具列表 # 在 Claude 中输入:"列出所有可用的 MCP 工具"
// claude_desktop_config.json 配置示例
{
"mcpServers": {
"marsnme": {
"command": "npx",
"args": ["-y", "marsnme"],
"env": {
// "API_KEY": "your-api-key-here"
}
}
}
}
// 保存后重启 Claude Desktop 生效
English | 繁體中文(台灣) | 繁體中文(香港) | 简体中文
---
marsnme.com — Claude.md is for context. MarsNMe is for continuity.
Your AI tools should know you — not start from scratch every time. When Perplexity helps you decide, Claude should remember why. When Cursor ships a feature, Warp should know the context. That's not context sharing. That's continuity.
Most AI memory tools help AI remember you. MarsNMe helps you and your AI remember each other — across sessions, across tools, over time.
An agent-agnostic, LLM-agnostic memory backend for MCP-compatible tools.
curl -fsSL https://marsnme.com/install.sh | bash
<p align="center"> <img src="docs/assets/demo.gif" alt="MarsNMe dark mode demo" width="640" /> </p> <p align="center"> <img src="docs/assets/demo-light.gif" alt="MarsNMe light mode demo" width="640" /> </p>
<p align="center"> <img src="docs/assets/social-concept.png" alt="MarsNMe — Your AI finally remembers you" width="720" /> </p> <p align="center"> <img src="docs/assets/social-compare.png" alt="Without vs With MarsNMe" width="480" /> <img src="docs/assets/social-arch.png" alt="How MarsNMe works" width="480" /> </p>
initialize, notifications/initialized, tools/list, tools/call, pingcoco, toto)insert_memory (short-term memory)list_memoriessearch_memories (Jina embedding search)recall (long-term chunk recall from profile schema)memory_ingest / dream_ingest (long-term chunk ingestion)session_boot / session_close (daily rhythm lifecycle)health_check (coverage, expiry, conflict diagnostics)reload_source_registry (refresh source whitelist at runtime)demote_memory / soft_forget / explain_memory (memory lifecycle management)1. Create a Supabase project (free plan is enough): - Sign up: https://supabase.com - Create project: https://supabase.com/dashboard/new - Open API settings (Project Settings → API): - Project URL → SUPABASE_BASE_URL - service_role key → SUPABASE_SERVICE_ROLE_KEY - Keep SUPABASE_SERVICE_ROLE_KEY private. Never commit it. 2. Create a Jina API key (free tier available): - Get key: https://jina.ai/api-key/ - Copy key to JINA_API_KEY
Go to mcp.marsnme.com/setup — create your personal MCP URL in 4 steps:
https://mcp.marsnme.com/your-nameThen add it to any MCP client (Claude, Cursor, Perplexity, Warp).
Self-hosted? Deploy marsnme-local/ to your own Cloudflare account — no Supabase needed, uses D1 + Workers AI + Vectorize.
---
If you only want a local demo path, use Docker Compose.
One-line install (recommended):
curl -fsSL https://marsnme.com/install.sh | bash
Or manually: 1. Set only the required key: ```bash cp .env.example .env
1. Copy .env.example to your local .env (do not commit real secrets). 2. Fill required values: - MCP_PROFILE (your profile identifier; this repo ships with legacy coco/toto) - SUPABASE_BASE_URL - SUPABASE_SERVICE_ROLE_KEY - JINA_API_KEY 3. Optional security flags: - MCP_REQUIRE_BEARER=true - MCP_CLIENT_ID - MCP_CLIENT_SECRET
Use soul-memory/deploy/systemd/memory-mcp-gateway@.service with instances: - memory-mcp-gateway@profile-a.service - memory-mcp-gateway@profile-b.service
Recommended env files: - /opt/mars-memory-mcp/shared/.env - /opt/mars-memory-mcp/shared/.env.profile-a - /opt/mars-memory-mcp/shared/.env.profile-b
1. Build artifact:
bash soul-memory/deploy/phase2/build_release_artifact.sh 2. Apply migrations with an explicit DDL-capable role: npx supabase db push --db-url "<postgres://supabase_admin:<password>@<host>:5432/postgres>" 3. Run pre-deploy schema gate (must pass before any service restart): bash soul-memory/deploy/phase2/pre_deploy_schema_gate.sh \
--db-url "<postgres://supabase_admin:<password>@<host>:5432/postgres>" \
--profiles coco,toto \
--expected-role supabase_admin 4. Run your platform-specific rollout/restart adapter. - This repository ships generic artifact + gate scripts; rollout adapters are environment-specific. - If schema gate exits non-zero, stop deployment and do not restart services. 5. Smoke gate: bash soul-memory/deploy/phase3/smoke_gate.sh --spawn-local 6. Automated npm + MCP Registry release (tag-driven): - Workflow: .github/workflows/publish-release.yml - Trigger: push tag v* - Gate: tag version must match soul-memory/package.json version - Optional local Fish helper: mrel patch
mrel minor
mrel major
mrel 0.1.2 The helper updates soul-memory/package.json and server.json, commits, tags, and pushes.
For the fastest path, use the one-line installer: curl -fsSL https://marsnme.com/install.sh | bash
The manual path below follows the same tools-first flow as docs/onboarding-a-mcp-zero-to-recall.md and docs/onboarding-b-platform-skill-install.md. 1. Clone repository:
git clone https://github.com/Marsmanleo/MarsNMe.git
cd MarsNMe 2. Verify Node.js version (20+ required): node --version 3. Copy environment template: cp .env.example .env 4. Fill required values in .env: - SUPABASE_BASE_URL - SUPABASE_SERVICE_ROLE_KEY - JINA_API_KEY 5. Run required Supabase migrations before first start: - Option A (recommended, Supabase CLI): npx supabase db push --db-url "<your-supabase-db-connection-string>" - Note: --db-url must be the Postgres database connection string from Project Settings → Database → Connection string. - It is not the same as SUPABASE_BASE_URL (https://<project-ref>.supabase.co, REST API URL). - Use a role that can execute DDL on your target schemas. - On Supabase-hosted Postgres this is typically supabase_admin (not postgres). - Option B (Supabase Dashboard SQL Editor): 1. Open SQL Editor. 2. Ensure the vector extension is enabled first (Database → Extensions). 3. Run migration files in filename order from supabase/migrations/: - 20260504052744_semantic_vector_dual_profile.sql - 20260513213800_memory_lifecycle_tracking.sql - 20260513222500_health_check_detect_conflicts_v2.sql - 20260517183000_provenance_audit_trail.sql - 20260517194000_memory_scope_agent_body_environment.sql - 20260517200500_forget_demote_mechanism.sql - 20260517223500_usage_cost_telemetry_light.sql - 20260517231000_memories_source_constraint_regex.sql - 20260517232000_source_registry_table.sql 6. Start gateway: - MCP_PROFILE separates memory by agent or use case. - Use any profile name you want (for example: default, my-agent, profile-a). - Legacy built-in profile IDs coco and toto are still supported for compatibility. - If PORT is omitted, default port is profile-based (coco=18790, toto=18791, other profiles deterministic in 20000-29999). MCP_PROFILE=profile-a PORT=18790 npx @marsnme/mcp-gateway 7. Verify health: curl -sS http://127.0.0.1:18790/health 8. Connect your MCP client (next section), then run the first round-trip check.
Local endpoint: - http://127.0.0.1:18790/mcp
If bearer auth is enabled (MCP_REQUIRE_BEARER=true), include: - Authorization: Bearer <your-token>
When you need a temporary public endpoint for remote AI tools:
docker compose --profile tunnel up
Expected output (from tunnel logs):
https://xxxx.trycloudflare.com
Get MCP endpoint: ```bash docker compose --profile tunnel logs tunnel | grep -Eo 'https://[^ ]+trycloudflare.com' | head -n1
2. Start local stack:bash docker compose up This starts:
- PostgreSQL + pgvector
- SQL migrations from `supabase/migrations/`
- PostgREST + rest-proxy
- MarsNMe gateway (`http://127.0.0.1:18790/mcp`)
3. Verify health:bash curl -sS http://127.0.0.1:18790/health ```
Hermes is optional and disabled by default: - HERMES_ENABLED=false - HERMES_DIGEST_MCP_URL - HERMES_DIGEST_MCP_BEARER_TOKEN - HERMES_DIGEST_ORIGIN - HERMES_DIGEST_SOURCE_DIR
Dream Runner is public-friendly and can run without Hermes private environment: - DREAM_ENABLED=true - DREAM_MODE=lite|standard|pro - DREAM_DIGEST_MCP_URL - DREAM_MCP_BEARER_TOKEN (if required) - DREAM_ENABLE_ISSUE_SIGNALS, DREAM_ENABLE_REPO_SCAN, DREAM_ENABLE_SOUL_CONTEXT (optional overrides)
Quick start:
DREAM_ENABLED=true DREAM_MODE=lite python3 soul-memory/scripts/dream_runner.py If you run this repository with bundled defaults and no profile remapping, use coco and toto.
See docs/dream-runner-self-host.md for full configuration.
| Package | Description |
|---|---|
soul-memory/ | Core MCP gateway — agent-agnostic memory backend (this package is published to npm as @marsnme/mcp-gateway) |
soul-memory/cloudflare-routing-worker/ | Cloudflare Worker for mcp.marsnme.com — username-based MCP routing proxy with setup wizard |
marsnme-local/ | Self-hosted MCP memory server on Cloudflare Workers + D1 + Vectorize (no Supabase needed) |
MarsNMe 是一个 AI 连续性记忆平台,让多个 AI 工具(Claude、Cursor、Perplexity、Warp 等)能够共享和记住用户的上下文。与每次从零开始的传统方式不同,MarsNMe 通过 MCP(Model Context Protocol)协议实现跨工具的记忆持久化,确保当 Perplexity 帮助你做决策时,Claude 能记住原因;当 Cursor 发布新功能时,Warp 能理解背景。核心理念是让 AI 工具真正了解你,而非每次重新开始。
MarsNMe 提供完整的 MCP 方法支持,包括 initialize、notifications/initialized、tools/list、tools/call 和 ping。支持可配置的 Profile ID(内置 coco、toto 等)。核心记忆工具包括:insert_memory(短期记忆)、list_memories(列表查询)、search_memories(基于 Jina 嵌入的语义搜索)、recall(从 Profile Schema 调用长期记忆块)、memory_ingest 和 dream_ingest(长期记忆块摄入)。这些工具共同构建了一个完整的多层次记忆系统。
使用 MarsNMe 前需要创建 Supabase 项目(免费计划足够)。访问 supabase.com 注册并创建新项目,然后在项目设置的 API 部分获取 Project URL(作为 SUPABASE_BASE_URL)和 service_role 密钥(作为 SUPABASE_SERVICE_ROLE_KEY)。此外需要 Jina API Key 用于向量搜索功能。Node.js 版本需要 20 及以上。所有敏感信息应存储在 .env 文件中,不要提交到版本控制。
最快的安装方式是访问 mcp.marsnme.com/setup,通过 4 步创建个人 MCP URL:选择用户名、输入 Supabase 凭证、选择偏好设置、获取 MCP URL。对于本地开发,推荐使用一行命令安装:curl -fsSL https://marsnme.com/install.sh | bash。或手动方式:克隆仓库、复制 .env.example 到 .env、填写必需的环境变量、运行 docker compose up 启动本地栈(包含 PostgreSQL、pgvector、PostgREST 和 MarsNMe 网关)。
快速开始需要 15-20 分钟。首先克隆 GitHub 仓库并验证 Node.js 版本(20+)。使用一行安装器或手动启动 Docker Compose 栈。本地端点为 http://127.0.0.1:18790/mcp,如启用 Bearer 认证需在请求头中包含 Authorization 令牌。通过 curl -sS http://127.0.0.1:18790/health 验证服务健康状态。详细的分步指南可参考 docs/onboarding-a-mcp-zero-to-recall.md 和 docs/onboarding-b-platform-skill-install.md。
配置通过 .env 文件管理。必需参数包括:MCP_PROFILE(Profile 标识符,默认 coco/toto)、SUPABASE_BASE_URL、SUPABASE_SERVICE_ROLE_KEY、JINA_API_KEY。可选安全参数:MCP_REQUIRE_BEARER(启用 Bearer 认证)、MCP_CLIENT_ID、MCP_CLIENT_SECRET。Hermes Digest Runner 默认禁用,可通过 HERMES_ENABLED 和相关参数启用。Dream Runner 支持 lite/standard/pro 三种模式,可独立运行。所有敏感信息不应提交到版本控制。
项目采用模块化架构。soul-memory/ 是核心 MCP 网关,提供与代理无关的记忆后端(发布到 npm 为 @marsnme/mcp-gateway)。soul-memory/cloudflare-routing-worker/ 是 Cloudflare Worker,为 mcp.marsnme.com 提供基于用户名的 MCP 路由代理和设置向导。marsnme-local/ 用于自托管部署。整个系统围绕 MCP 协议设计,支持多个 AI 客户端接入,通过 Supabase 后端存储和检索记忆数据。
MarsNMe是一个开源的MCP工具,提供Agent-agnostic AI memory功能,提高对话流程效率,值得关注。
AI Skill Hub 为第三方内容聚合平台,本页面信息基于公开数据整理,不对工具功能和质量作任何法律背书。
建议在沙箱或测试环境中充分验证后,再部署至生产环境,并做好必要的安全评估。
✅ Apache 2.0 — 宽松开源协议,可商用,需保留版权声明和 NOTICE 文件,含专利授权条款。
AI Skill Hub 点评:MarsNMe 的核心功能完整,质量良好。对于Claude Desktop / Claude Code 用户来说,这是一个值得纳入个人工具库的选择。建议先在非生产环境试用,再逐步推广。
| 原始名称 | MarsNMe |
| 原始描述 | 开源MCP工具:Agent-agnostic AI memory MCP — never forget a conversation again。⭐6 · JavaScript |
| Topics | ai-agentai-memoryjinamcpmemoryjavascript |
| GitHub | https://github.com/Marsmanleo/MarsNMe |
| License | Apache-2.0 |
| 语言 | JavaScript |
收录时间:2026-06-09 · 更新时间:2026-06-09 · License:Apache-2.0 · AI Skill Hub 不对第三方内容的准确性作法律背书。
选择 Agent 类型,复制安装指令后粘贴到对应客户端