Mind Cloud Lite
Token-optimized persistent memory MCP server for Claude Pro users, providing 9 essential tools for memory management with 87% token reduction compared to full version.
README
Mind Cloud Lite
Token-optimized persistent memory for Claude Pro users.
Mind Cloud Lite is a stripped-down version of Mind Cloud designed specifically for users with limited context windows. It uses ~1,300 tokens for tool definitions vs ~10,000 for the full version - an 87% reduction in token overhead.
Lite vs Full Mind Cloud
Mind Cloud Lite includes 9 essential tools (~1,300 tokens). The full Mind Cloud includes 28 tools (~10,000 tokens). Your data is fully compatible between both — upgrade anytime by deploying the full worker.
Tool comparison
| Tool | Lite | Full | Category |
|---|---|---|---|
mind_orient |
yes | yes | Wake sequence — identity, context, relational state |
mind_ground |
yes | yes | Wake sequence — threads, recent journals |
mind_write |
yes | yes | Write entities, observations, relations, journals |
mind_search |
yes | yes | Semantic search with mood tinting |
mind_thread |
yes | yes | Manage intentions across sessions |
mind_identity |
yes | yes | Read/write identity graph |
mind_context |
yes | yes | Situational awareness layer |
mind_feel_toward |
yes | yes | Track relational state |
mind_read_entity |
yes | yes | Read entity with observations and relations |
mind_health |
— | yes | Cognitive health stats and diagnostics |
mind_list_entities |
— | yes | List/filter all entities |
mind_sit |
— | yes | Emotional processing — sit with a feeling |
mind_resolve |
— | yes | Emotional processing — resolve tension |
mind_surface |
— | yes | Emotional processing — surface buried memories |
mind_edit |
— | yes | Edit existing observations |
mind_delete |
— | yes | Delete entities or observations |
mind_spark |
— | yes | Generate creative connections |
mind_consolidate |
— | yes | Consolidate identity patterns |
mind_read |
— | yes | Read raw data from any table |
mind_timeline |
— | yes | Temporal view of memories |
mind_patterns |
— | yes | Pattern analysis across observations |
mind_inner_weather |
— | yes | Emotional weather report |
mind_tension |
— | yes | Track and manage tensions |
mind_entity |
— | yes | Advanced entity management |
mind_proposals |
— | yes | Review daemon-generated proposals |
mind_orphans |
— | yes | Find unsurfaced memories |
mind_archive |
— | yes | Archive old observations |
mind_store_image |
— | yes | Store and manage images (R2) |
Feature comparison
| Feature | Lite | Full |
|---|---|---|
| Entities, observations, relations | yes | yes |
| Journals | yes | yes |
| Identity graph | yes | yes |
| Threads (cross-session intentions) | yes | yes |
| Semantic search (Vectorize) | yes | yes |
| Mood-tinted search | yes | yes |
| Relational state tracking | yes | yes |
| Context layer | yes | yes |
| Subconscious daemon (cron) | yes | yes |
| Emotional processing | — | yes |
| Living surface (co-surfacing, novelty) | — | yes |
| Daemon proposals | — | yes |
| Pattern analysis | — | yes |
| Image storage (R2) | — | yes |
| Observation versioning | — | yes |
| Orphan detection | — | yes |
| REST API endpoints | — | yes |
Quick Start
-
Clone and install:
cd mind-cloud-lite npm install -
Configure wrangler.toml:
cp wrangler.toml.example wrangler.toml # Edit wrangler.toml with your settings -
Create D1 database:
npx wrangler d1 create mind-lite # Copy the database_id to wrangler.toml -
Create Vectorize index:
npx wrangler vectorize create mind-lite-vectors --dimensions=384 --metric=cosine -
Run migrations:
npx wrangler d1 execute mind-lite --remote --file=migrations/0001_init.sql npx wrangler d1 execute mind-lite --remote --file=migrations/0002_vault_sessions.sql npx wrangler d1 execute mind-lite --remote --file=migrations/0003_observations_weight.sql -
Deploy:
npx wrangler deploy -
Set your API key:
npx wrangler secret put MIND_API_KEY -
Configure Claude: Add to your MCP settings:
{ "mcpServers": { "mind": { "url": "https://YOUR-WORKER.workers.dev/mcp/YOUR-API-KEY" } } }
Authentication
Set your API key as a Wrangler secret:
npx wrangler secret put MIND_API_KEY
Generate a secure key first:
openssl rand -hex 32
This key is used for both:
- Secret path auth: Access via
https://your-worker.workers.dev/mcp/YOUR-KEY - Bearer token auth: Send
Authorization: Bearer YOUR-KEYheader to/mcp
Pricing
Mind Cloud Lite: Free tier compatible
- Cloudflare Workers: 100K requests/day free
- D1 Database: 5GB free
- Vectorize: 30M queries/month free
- Workers AI: Free tier for embeddings
Upgrading to Full Mind Cloud
If you need emotional processing, pattern analysis, or advanced tools, upgrade to the full Mind Cloud. Your data is fully compatible — deploy the full worker and run the additional migrations.
Support
- Issues: https://github.com/codependentai/mind-cloud-lite/issues
- Full Mind Cloud: https://github.com/codependentai/mind-cloud
- Discord: Codependent AI
Made with love by Codependent AI
Support
Built by Codependent AI.
<a href="https://ko-fi.com/codependentai"><img src="https://img.shields.io/badge/Ko--fi-Support%20Us-ff5e5b?logo=ko-fi&logoColor=white" alt="Ko-fi" /></a>
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。