A minimal Go HTTP gateway service that bridges HTTP requests to Claude CLI. Enables any HTTP-compatible application to use Claude CLI's headless mode capabilities. Ideal for integrating AI into web, mobile, or IoT applications.
git clone https://github.com/myysophia/cli-agent.gitCLI Gateway is a minimal Go HTTP service that converts HTTP requests into calls to various AI command-line interfaces, including Claude, Cursor, Codex, Gemini, and Qwen. It provides a unified HTTP interface with streaming support via Server-Sent Events, allowing web applications, mobile apps, IoT devices, and backend systems to leverage headless CLI capabilities without direct CLI access. The gateway handles conversation history conversion, system prompts, MCP tool integrations (WebFetch, Playwright), and session management. It includes Admin UI for configuration and MCP management, Release Notes tracking for all supported CLIs, and is deployable via Docker or direct binary execution.
Install Go 1.16+ and at least one supported CLI tool (Claude, Cursor, Codex, Gemini, or Qwen). Build with 'go build -o cli-agent' and start with './start.sh' (default port 8080) or 'PORT=3000 ./start.sh'. Access the Admin UI at /v1/admin to configure CLIs and MCP servers, then send HTTP POST requests to /invoke or /chat endpoints with your prompts.
Integrate AI into web and mobile applications via HTTP API
Add AI capabilities to IoT devices and edge computing systems
Create custom nodes for low-code platforms (Dify, n8n, Zapier)
Automate CI/CD pipelines and scheduled tasks with AI analysis
No install command available. Check the GitHub repository for manual installation instructions.
git clone https://github.com/myysophia/cli-agentCopy the install command above and run it in your terminal.
Launch Claude Code, Cursor, or your preferred AI coding agent.
Use the prompt template or examples below to test the skill.
Adapt the skill to your specific use case and workflow.
Act as a CLI Agent for [COMPANY] in the [INDUSTRY] sector. I will send you HTTP requests with [DATA] to process. Respond with the appropriate HTTP status code and JSON-formatted response body. Begin now.
```http
HTTP/1.1 200 OK
Content-Type: application/json
{
"status": "success",
"data": {
"analysis": "Based on the provided sales data, Q3 shows a 15% increase in revenue compared to Q2.",
"recommendations": [
"Consider expanding marketing efforts in Region 4",
"Investigate the sudden drop in Product B sales",
"Prepare for potential supply chain disruptions in Q4"
],
"confidence": 0.87
}
}
```AI assistant built for thoughtful, nuanced conversation
Get more done every day with Microsoft Teams – powered by AI
Automate security compliance and monitor real-time security posture seamlessly.
Automate your spreadsheet tasks with AI power
Agentic AI Workflow platform
Connected workspace for docs, wikis, and projects
Take a free 3-minute scan and get personalized AI skill recommendations.
Take free scan