### Install and Run AgentLoop

Source: https://github.com/fullstackhouse/agentloop/blob/main/README.md

Basic setup commands to get AgentLoop running locally. Ensure you have Node.js installed.

```bash
cp .env.example .env
cp config.example.json config.json
npm install
npm run dev
```

--------------------------------

### Setup and Run E2E Tests for AgentLoop

Source: https://github.com/fullstackhouse/agentloop/blob/main/CLAUDE.md

This section details the steps for running end-to-end tests. It requires starting the agent in one terminal and running the tests in another. The tests verify agent responses in a configured Slack channel.

```bash
# Terminal 1: Start the agent
npm run dev

# Terminal 2: Run tests
npm run test:e2e
```

--------------------------------

### Start AgentLoop Production Server

Source: https://github.com/fullstackhouse/agentloop/blob/main/CLAUDE.md

Runs the compiled JavaScript code. This command is used to start the agent after it has been built.

```bash
npm start
```

--------------------------------

### AgentLoop Configuration JSON

Source: https://github.com/fullstackhouse/agentloop/blob/main/README.md

Example configuration file for AgentLoop. Customize Claude model, platforms, Slack settings, and MCP server details.

```json
{
  "claude": { "model": "claude-sonnet-4-20250514" },
  "platforms": ["slack"],
  "slackChannels": ["#agentloop-test"],
  "slackUsers": ["Jacek Tomaszewski"],
  "workspaceDir": "/path/to/your/project",
  "mcpServers": {
    "slack": {
      "command": "npx",
      "args": ["slack-mcp-server@latest"],
      "env": {
        "SLACK_MCP_XOXC_TOKEN": "${SLACK_XOXC}",
        "SLACK_MCP_XOXD_TOKEN": "${SLACK_XOXD}",
        "SLACK_MCP_ADD_MESSAGE_TOOL": "true"
      }
    }
  }
}
```

--------------------------------

### Build AgentLoop Project

Source: https://github.com/fullstackhouse/agentloop/blob/main/CLAUDE.md

Compiles the TypeScript code into JavaScript for production deployment. This command should be run before starting the application in a production environment.

```bash
npm run build
```

--------------------------------

### Docker Compose Volume Mount and Command

Source: https://github.com/fullstackhouse/agentloop/blob/main/README.md

Example configuration for docker-compose.yml to mount a local repository as a read-only workspace and specify the command-line arguments.

```yaml
volumes:
  - /path/to/your/repo:/workspace:ro
command: ["--workspace", "/workspace"]
```

--------------------------------

### Serve AgentLoop with Options

Source: https://github.com/fullstackhouse/agentloop/blob/main/README.md

Command-line interface for serving AgentLoop. Customize workspace, configuration, model, and Slack channels.

```bash
agentloop serve [options]
```

```bash
agentloop serve --workspace /app/monorepo
```

```bash
agentloop serve -w ./my-project --channel "#dev"
```

--------------------------------

### Run AgentLoop with Docker Compose

Source: https://github.com/fullstackhouse/agentloop/blob/main/README.md

Instructions for running AgentLoop using Docker Compose. Mount your workspace directory for persistent access.

```bash
docker-compose up
```

--------------------------------

### Release Process for AgentLoop

Source: https://github.com/fullstackhouse/agentloop/blob/main/CLAUDE.md

Outlines the steps for releasing a new version of AgentLoop. This includes version bumping, committing, tagging, pushing to origin, and creating a GitHub release.

```bash
1. Bump version in `package.json`
2. Commit: `git commit -m "chore: bump version to X.Y.Z"`
3. Tag: `git tag -a vX.Y.Z -m "Release vX.Y.Z"`
4. Push: `git push origin main && git push origin vX.Y.Z`
5. Create GitHub release: `gh release create vX.Y.Z --title "vX.Y.Z" --notes "..."`
```

--------------------------------

### AgentLoop Configuration Schema

Source: https://github.com/fullstackhouse/agentloop/blob/main/SPEC.md

Defines the structure for the JSON configuration file, including settings for Claude, platforms, workspace directory, and MCP servers. Supports environment variable substitution for sensitive values.

```json
{
  "claude": { "model": "claude-sonnet-4-20250514" },
  "platforms": ["slack"],
  "slackChannels": ["#channel"],
  "slackUsers": ["Jacek Tomaszewski"],
  "workspaceDir": "/path/to/workspace",
  "mcpServers": {
    "name": {
      "command": "npx",
      "args": ["..."],
      "env": { "KEY": "${ENV_VAR}" }
    }
  }
}
```

--------------------------------

### Run AgentLoop End-to-End Tests

Source: https://github.com/fullstackhouse/agentloop/blob/main/CLAUDE.md

Executes end-to-end tests for the AgentLoop instance. Ensure the agent is running and connected to Slack before executing these tests.

```bash
npm run test:e2e
```

--------------------------------

### Run AgentLoop Development Server

Source: https://github.com/fullstackhouse/agentloop/blob/main/CLAUDE.md

Use this command to run the agent in development mode with tsx. This is useful for active development and debugging.

```bash
npm run dev
```

=== COMPLETE CONTENT === This response contains all available snippets from this library. No additional content exists. Do not make further requests.