Strada-Brain 是 AI Skill Hub 本期精选MCP工具之一。综合评分 7.5 分,整体质量较高。我们推荐使用将其纳入你的 AI 工具库,帮助提升工作效率。
Strada-Brain 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。
Strada-Brain 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/okandemirel/Strada.Brain
# 方式二:手动配置 claude_desktop_config.json
{
"mcpServers": {
"strada-brain": {
"command": "npx",
"args": ["-y", "strada.brain"]
}
}
}
# 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 Strada-Brain 执行以下任务... Claude: [自动调用 Strada-Brain 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": {
"strada-brain": {
"command": "npx",
"args": ["-y", "strada.brain"],
"env": {
// "API_KEY": "your-api-key-here"
}
}
}
}
// 保存后重启 Claude Desktop 生效
<p align="center"> <img src="icon/strada-brain-icon.png" alt="Strada.Brain Logo" width="200"/> </p>
<p align="center"> <strong>AI-Powered Development Agent for Unity / Strada.Core Projects</strong><br/> An autonomous coding agent that connects to a web dashboard, Telegram, Discord, Slack, WhatsApp, or your terminal — reads your codebase, writes code, runs builds, learns from its mistakes, and operates autonomously with a 24/7 daemon loop. Now with multi-agent orchestration, task delegation, memory consolidation, a deployment subsystem with approval gates, media sharing with LLM vision support, a configurable personality system via SOUL.md, control-plane clarification review, intelligent multi-provider routing with task-aware dynamic switching, confidence-based consensus verification, an autonomous Agent Core with OODA reasoning loop, an extensible skill ecosystem with SKILL.md manifests and a git-based registry, and Strada.MCP integration. </p>
<p align="center"> <img src="https://img.shields.io/badge/TypeScript-5.7-blue?style=flat-square&logo=typescript" alt="TypeScript"> <img src="https://img.shields.io/badge/Node.js-%3E%3D20-green?style=flat-square&logo=node.js" alt="Node.js"> <img src="https://img.shields.io/badge/tests-4527%2B-brightgreen?style=flat-square" alt="Tests"> <img src="https://img.shields.io/badge/license-MIT-blue?style=flat-square" alt="License"> </p>
<p align="center"> <strong>English</strong> | <a href="README.tr.md">Türkçe</a> | <a href="README.zh.md">中文</a> | <a href="README.ja.md">日本語</a> | <a href="README.ko.md">한국어</a> | <a href="README.de.md">Deutsch</a> | <a href="README.es.md">Español</a> | <a href="README.fr.md">Français</a> </p>
---
| Variable | Default | Description |
|---|---|---|
RAG_ENABLED | true | Enable semantic code search over your C# project |
EMBEDDING_PROVIDER | auto | Embedding provider: auto, openai, gemini, mistral, together, fireworks, qwen, ollama |
EMBEDDING_DIMENSIONS | (provider default) | Output vector dimensions (Matryoshka: 128-3072 for Gemini/OpenAI) |
MEMORY_ENABLED | true | Enable persistent conversation memory |
MEMORY_DB_PATH | .strada-memory | Directory for memory database files |
WEB_CHANNEL_PORT | 3000 | Web channel UI port |
DASHBOARD_ENABLED | false | Enable HTTP monitoring dashboard |
DASHBOARD_PORT | 3100 | Dashboard server port |
ENABLE_WEBSOCKET_DASHBOARD | false | Enable WebSocket real-time dashboard |
WEBSOCKET_DASHBOARD_PORT | 3100 | WebSocket dashboard server port |
WEBSOCKET_DASHBOARD_AUTH_TOKEN | (unset) | Optional bearer token for WebSocket dashboard auth; when present it also protects dashboard APIs, and when absent the embedded same-origin dashboard boot
%LOCALAPPDATA%\Strada\node). You can also point to a custom binary with STRADA_NODE_PATH.ANTHROPIC_API_KEY, OPENAI_API_KEY, GEMINI_API_KEY, etc.), a Claude subscription token (ANTHROPIC_AUTH_MODE=claude-subscription + ANTHROPIC_AUTH_TOKEN), an OpenAI ChatGPT/Codex subscription session (OPENAI_AUTH_MODE=chatgpt-subscription), or an ollama-only PROVIDER_CHAIN```bash
git clone https://github.com/okandemirel/Strada.Brain.git Strada.Brain
```bash
./strada setup
./strada setup --web ./strada setup --terminal
powershell
strada doctor
powershell
ANTHROPIC_AUTH_MODE=claude-subscription ANTHROPIC_AUTH_TOKEN=sk-ant-sid01-...
strada
```bash
strada skill install https://github.com/okandemirel/strada-skill-example
strada skill list
strada skill info <name>
An opt-in deployment system with human-in-the-loop approval gates and circuit breaker protection.
ReadinessChecker: - Validates system readiness before deployment (build status, test results, resource availability) - Configurable readiness criteria
DeployTrigger: - Integrates with the daemon's trigger system as a new trigger type - Fires when deployment conditions are met (e.g., all tests pass, approval granted) - Includes an approval queue: deployments require explicit human approval before execution
DeploymentExecutor: - Executes deployment steps in sequence with rollback capability - Environment variable sanitization prevents credential leakage in deployment logs - Circuit breaker: consecutive deployment failures trigger automatic cooldown to prevent cascading failures
Security: Deployment is disabled by default and requires explicit opt-in via configuration. All deployment actions are logged and auditable.
---
cd Strada.Brain
powershell
JWT_SECRET=<generate with: openssl rand -hex 64> ```
./strada --daemon
All configuration is via environment variables. See .env.example for the full list.
| Variable | Description |
|---|---|
UNITY_PROJECT_PATH | Absolute path to your Unity project root (must contain Assets/) |
ANTHROPIC_API_KEY=sk-ant-...
./strada start --channel cli
./strada # Canonical source-checkout launcher
.\strada.ps1 # Canonical Windows PowerShell source-checkout launcher
strada.cmd # Windows Command Prompt companion launcher inside the checkout
node strada.js # Universal Node.js entry point (works on any OS without shell wrappers)
./strada install-command # Install a user-local bare `strada` command
.\strada.ps1 install-command # Windows source-checkout bare-command install
./strada uninstall # Remove the installed bare command and managed PATH/profile changes
.\strada.ps1 uninstall # Windows source-checkout bare-command uninstall
strada uninstall --purge-config # Also remove Strada runtime state and source-checkout generated artifacts for a zero-install rerun
strada # Smart launcher after install-command
strada --daemon # Start the configured default channel in daemon mode
strada --web # Open the web channel, or continue web-first setup on a fresh machine
strada --terminal # Open the terminal channel, or force terminal setup on a fresh machine
./strada setup --web # Launch the browser wizard directly
./strada setup --terminal # Use the terminal wizard directly
.\strada.ps1 setup --web # Windows PowerShell browser wizard
.\strada.ps1 setup --terminal # Windows PowerShell terminal wizard
./strada doctor # Verify install/build/config readiness
.\strada.ps1 doctor # Windows PowerShell readiness check
./strada start # Start the agent
./strada supervise # Run with auto-restart supervisor
./strada update # Check and apply updates
./strada update --check # Check for updates without applying
./strada version-info # Show version, install method, update status
Strada.Brain detects an installed Strada.MCP, verifies the package root, and loads only MCP action tools that are executable in the current Brain runtime into the main toolchain. Detection can be pinned with STRADA_MCP_PATH, while missing Strada.Core / Strada.Modules installs use the explicit STRADA_CORE_REPO_URL and STRADA_MODULES_REPO_URL config values instead of hidden env fallbacks. Installed Strada.Core and Strada.MCP docs/sources remain authoritative knowledge even when bridge or runtime constraints keep some MCP prompts/resources/tools out of the live worker tool surface.
---
该项目是一个开源的MCP工具,使用AI进行自动编码,支持Unity/Strada.Core,但需要进一步的开发和测试
该工具未明确声明开源协议,商业使用前请联系原作者确认授权范围,避免侵权风险。
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。
经综合评估,Strada-Brain 在MCP工具赛道中表现稳健,质量良好。如果你已有明确的使用需求,可以直接上手体验;如果还在评估阶段,建议对比同类工具后再做决策。
| 原始名称 | Strada-Brain |
| Topics | mcpagentic-aiagentic-workflowclaudegame-developmentgamedevtypescript |
| GitHub | https://github.com/okandemirel/Strada.Brain |
| 语言 | TypeScript |
收录时间:2026-05-22 · 更新时间:2026-05-22 · License:未公布 · 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