### Clone LocalAGI Repository and Setup Frontend

Source: https://github.com/mudler/localagi/blob/main/README.md

Steps to clone the repository, navigate to the frontend directory, install dependencies, build the frontend, and start the development server.

```bash
git clone https://github.com/mudler/LocalAGI.git
cd LocalAGI

cd webui/react-ui

# Install dependencies
bun i

# Compile frontend (the build directory needs to exist for the backend to start)
bun run build

# Start frontend development server
bun run dev
```

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

### Clone Repository and Basic CPU Setup

Source: https://github.com/mudler/localagi/blob/main/README.md

Clone the LocalAGI repository and start the service using Docker Compose for CPU-only environments.

```bash
# Clone the repository
git clone https://github.com/mudler/LocalAGI
cd LocalAGI

# CPU setup (default)
docker compose up
```

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

### Start LocalAGI Development Server with Environment Variables

Source: https://github.com/mudler/localagi/blob/main/README.md

Instructions to start the LocalAGI development server, including creating a state directory and setting essential environment variables for model configuration, API URLs, and service settings.

```bash
cd LocalAGI

# Create a "pool" directory for agent state
mkdir pool

# Set required environment variables
export LOCALAGI_MODEL=gemma-3-4b-it-qat
export LOCALAGI_MULTIMODAL_MODEL=moondream2-20250414
export LOCALAGI_IMAGE_MODEL=sd-1.5-ggml
export LOCALAGI_LLM_API_URL=http://localai:8080
# Knowledge base is built-in; no separate LocalRecall service needed
export LOCALAGI_STATE_DIR=./pool
export LOCALAGI_TIMEOUT=5m
export LOCALAGI_ENABLE_CONVERSATIONS_LOGGING=false
export LOCALAGI_SSHBOX_URL=root:root@sshbox:22

# Start development server
go run main.go
```

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

### NVIDIA GPU Setup with Custom Models

Source: https://github.com/mudler/localagi/blob/main/README.md

Advanced NVIDIA GPU setup allowing custom multimodal and image models to be specified.

```bash
# NVIDIA GPU setup with custom multimodal and image models
MODEL_NAME=gemma-3-12b-it \
MULTIMODAL_MODEL=moondream2-20250414 \
IMAGE_MODEL=flux.1-dev-ggml \
docker compose -f docker-compose.nvidia.yaml up
```

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

### AMD GPU Setup

Source: https://github.com/mudler/localagi/blob/main/README.md

Launch LocalAGI with AMD GPU support.

```bash
# AMD GPU setup
docker compose -f docker-compose.amd.yaml up
```

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

### Example Custom Action: Weather Information

Source: https://github.com/mudler/localagi/blob/main/README.md

A Go code example demonstrating a custom action to fetch weather information. It includes parsing parameters, making an API call, and formatting the response. Ensure you replace 'YOUR_API_KEY' with your actual OpenWeatherMap API key.

```go
import (
    "encoding/json"
    "fmt"
    "net/http"
    "io"
)

type WeatherParams struct {
    City    string `json:"city"`
    Country string `json:"country"`
}

type WeatherResponse struct {
    Main struct {
        Temp     float64 `json:"temp"`
        Humidity int     `json:"humidity"`
    } `json:"main"`
    Weather []struct {
        Description string `json:"description"`
    } `json:"weather"`
}

func Run(config map[string]interface{}) (string, map[string]interface{}, error) {
    // Parse parameters
    p := WeatherParams{}
    b, err := json.Marshal(config)
    if err != nil {
        return "", map[string]interface{}{}, err
    }
    if err := json.Unmarshal(b, &p); err != nil {
        return "", map[string]interface{}{}, err
    }

    // Make API call to weather service
    url := fmt.Sprintf("http://api.openweathermap.org/data/2.5/weather?q=%s,%s&appid=YOUR_API_KEY&units=metric", p.City, p.Country)
    resp, err := http.Get(url)
    if err != nil {
        return "", map[string]interface{}{}, err
    }
    defer resp.Body.Close()

    body, err := io.ReadAll(resp.Body)
    if err != nil {
        return "", map[string]interface{}{}, err
    }

    var weather WeatherResponse
    if err := json.Unmarshal(body, &weather); err != nil {
        return "", map[string]interface{}{}, err
    }

    // Format response
    result := fmt.Sprintf("Weather in %s, %s: %.1f°C, %s, Humidity: %d%%", 
        p.City, p.Country, weather.Main.Temp, weather.Weather[0].Description, weather.Main.Humidity)

    return result, map[string]interface{}{}, nil
}

func Definition() map[string][]string {
    return map[string][]string{
        "city": []string{
            "string",
            "The city name to get weather for",
        },
        "country": []string{
            "string", 
            "The country code (e.g., US, UK, DE)",
        },
    }
}

func RequiredFields() []string {
    return []string{"city", "country"}
}

```

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

### NVIDIA GPU Setup

Source: https://github.com/mudler/localagi/blob/main/README.md

Use this command to set up LocalAGI with NVIDIA GPU acceleration.

```bash
# NVIDIA GPU setup
docker compose -f docker-compose.nvidia.yaml up
```

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

### Start with a Specific Model

Source: https://github.com/mudler/localagi/blob/main/README.md

Initiate LocalAGI with a predefined model by setting the MODEL_NAME environment variable.

```bash
# Start with a specific model (see available models in models.localai.io, or localai.io to use any model in huggingface)
MODEL_NAME=gemma-3-12b-it docker compose up
```

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

### Get All Agents

Source: https://github.com/mudler/localagi/blob/main/README.md

Retrieves a list of all available agents. Use this endpoint to get an overview of your agents.

```bash
curl -X GET "http://localhost:3000/api/agents"
```

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

### Intel GPU Setup

Source: https://github.com/mudler/localagi/blob/main/README.md

Configure LocalAGI for Intel GPUs, including Arc and integrated graphics.

```bash
# Intel GPU setup (for Intel Arc and integrated GPUs)
docker compose -f docker-compose.intel.yaml up
```

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

### Basic LocalAGI Agent Creation

Source: https://github.com/mudler/localagi/blob/main/README.md

Example of creating a single AI agent with basic configuration, including model, API details, system prompt, and character.

```go
import (
    "github.com/mudler/LocalAGI/core/agent"
    "github.com/mudler/LocalAGI/core/types"
)

// Create a new agent with basic configuration
agent, err := agent.New(
    agent.WithModel("gpt-4"),
    agent.WithLLMAPIURL("http://localhost:8080"),
    agent.WithLLMAPIKey("your-api-key"),
    agent.WithSystemPrompt("You are a helpful assistant."),
    agent.WithCharacter(agent.Character{
        Name: "my-agent",
    }),
    agent.WithActions(
        // Add your custom actions here
    ),
    agent.WithStateFile("./state/my-agent.state.json"),
    agent.WithCharacterFile("./state/my-agent.character.json"),
    agent.WithTimeout("10m"),
    agent.EnableKnowledgeBase(),
    agent.EnableReasoning(),
)

if err != nil {
    log.Fatal(err)
}

// Start the agent
go func() {
    if err := agent.Run(); err != nil {
        log.Printf("Agent stopped: %v", err)
    }
}()

// Stop the agent when done
agent.Stop()
```

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

### Advanced LocalAGI Agent Pool Management

Source: https://github.com/mudler/localagi/blob/main/README.md

Example demonstrating the creation and management of an agent pool for multiple agents, including configuration and lifecycle operations.

```go
import (
    "github.com/mudler/LocalAGI/core/state"
    "github.com/mudler/LocalAGI/core/types"
)

// Create a new agent pool (call pool.SetRAGProvider(...) for knowledge base; see main.go)
pool, err := state.NewAgentPool(
    "default-model",           // default model name
    "default-multimodal-model", // default multimodal model
    "transcription-model",     // default transcription model
    "en",                     // default transcription language
    "tts-model",              // default TTS model
    "http://localhost:8080",  // API URL
    "your-api-key",           // API key
    "./state",                // state directory
    func(config *AgentConfig) func(ctx context.Context, pool *AgentPool) []types.Action {
        // Define available actions for agents
        return func(ctx context.Context, pool *AgentPool) []types.Action {
            return []types.Action{
                // Add your custom actions here
            }
        }
    },
    func(config *AgentConfig) []Connector {
        // Define connectors for agents
        return []Connector{
            // Add your custom connectors here
        }
    },
    func(config *AgentConfig) []DynamicPrompt {
        // Define dynamic prompts for agents
        return []DynamicPrompt{
            // Add your custom prompts here
        }
    },
    func(config *AgentConfig) types.JobFilters {
        // Define job filters for agents
        return types.JobFilters{
            // Add your custom filters here
        }
    },
    "10m",  // timeout
    true,   // enable conversation logs
    nil,    // skills service (optional)
)

// Create a new agent in the pool
agentConfig := &AgentConfig{
    Name: "my-agent",
    Model: "gpt-4",
    SystemPrompt: "You are a helpful assistant.",
    EnableKnowledgeBase: true,
    EnableReasoning: true,
    // Add more configuration options as needed
}

err = pool.CreateAgent("my-agent", agentConfig)

// Start all agents
err = pool.StartAll()

// Get agent status
status := pool.GetStatusHistory("my-agent")

// Stop an agent
pool.Stop("my-agent")

// Remove an agent
err = pool.Remove("my-agent")
```

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

### Example Agent Configuration Structure

Source: https://github.com/mudler/localagi/blob/main/README.md

This JSON object illustrates the structure of an agent's configuration, defining its name, model, capabilities, and operational parameters.

```json
{
  "name": "my-agent",
  "model": "gpt-4",
  "multimodal_model": "gpt-4-vision",
  "hud": true,
  "standalone_job": false,
  "random_identity": false,
  "initiate_conversations": true,
  "enable_planning": true,
  "identity_guidance": "You are a helpful assistant.",
  "periodic_runs": "0 * * * *",
  "permanent_goal": "Help users with their questions.",
  "enable_kb": true,
  "enable_reasoning": true,
  "kb_results": 5,
  "can_stop_itself": false,
  "system_prompt": "You are an AI assistant.",
  "long_term_memory": true,
  "summary_long_term_memory": false
}
```

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

### Run NVIDIA GPU Configuration

Source: https://github.com/mudler/localagi/blob/main/README.md

Use this command to run LocalAGI with NVIDIA GPU acceleration. Ensure you have NVIDIA drivers installed.

```bash
docker compose -f docker-compose.nvidia.yaml up
```

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

### Get agent configuration metadata

Source: https://github.com/mudler/localagi/blob/main/README.md

Retrieves metadata for agent configurations.

```APIDOC
## GET /api/meta/agent/config

### Description
Get agent configuration metadata.

### Method
GET

### Endpoint
/api/meta/agent/config
```

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

### Get agent configuration

Source: https://github.com/mudler/localagi/blob/main/README.md

Retrieves the configuration for a specific agent.

```APIDOC
## GET /api/agent/:name/config

### Description
Get agent configuration.

### Method
GET

### Endpoint
/api/agent/:name/config

### Parameters
#### Path Parameters
- **name** (string) - Required - The name of the agent.
```

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

### Start Agent

Source: https://github.com/mudler/localagi/blob/main/README.md

Resumes a paused agent, allowing it to continue its activities. This is the counterpart to the pause agent endpoint.

```bash
curl -X PUT "http://localhost:3000/api/agent/my-agent/start"
```

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

### Get Agent Configuration

Source: https://github.com/mudler/localagi/blob/main/README.md

Retrieves the current configuration settings for a specific agent. This is useful for auditing or understanding agent parameters.

```bash
curl -X GET "http://localhost:3000/api/agent/my-agent/config"
```

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

### Send message & get response

Source: https://github.com/mudler/localagi/blob/main/README.md

Sends a message to an agent and receives a response.

```APIDOC
## POST /api/chat/:name

### Description
Send message & get response.

### Method
POST

### Endpoint
/api/chat/:name

### Parameters
#### Path Parameters
- **name** (string) - Required - The name of the agent to chat with.

### Request Body
- **message** (string) - Required - The message to send to the agent.
```

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

### Send message & get response (v1)

Source: https://github.com/mudler/localagi/blob/main/README.md

Sends a message to an agent and receives a response, compatible with OpenAI's API format.

```APIDOC
## POST /v1/responses

### Description
Send message & get response. This endpoint is compatible with OpenAI's Responses API.

### Method
POST

### Endpoint
/v1/responses

### Documentation
See [OpenAI's Responses](https://platform.openai.com/docs/api-reference/responses/create) for request and response details.
```

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

### Get Agent Status

Source: https://github.com/mudler/localagi/blob/main/README.md

Fetches the status history for a specific agent. Useful for monitoring agent activity.

```bash
curl -X GET "http://localhost:3000/api/agent/my-agent/status"
```

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

### Build and Run LocalAGI from Source

Source: https://github.com/mudler/localagi/blob/main/README.md

Steps to clone the repository, build the project using Go and Bun, and run the application.

```bash
git clone https://github.com/mudler/LocalAGI.git
cd LocalAGI

# Build it
cd webui/react-ui && bun i && bun run build
cd ../..
go build -o localagi

# Run it
./localagi
```

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

### Create Agent

Source: https://github.com/mudler/localagi/blob/main/README.md

Creates a new agent with specified configurations. Requires agent name, model, system prompt, and optional settings for knowledge base and reasoning.

```bash
curl -X POST "http://localhost:3000/api/agent/create" \
  -H "Content-Type: application/json" \
  -d '{
    "name": "my-agent",
    "model": "gpt-4",
    "system_prompt": "You are an AI assistant.",
    "enable_kb": true,
    "enable_reasoning": true
  }'
```

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

### Customize Intel GPU Models

Source: https://github.com/mudler/localagi/blob/main/README.md

Specify custom text, multimodal, and image models for Intel GPU acceleration using environment variables.

```bash
MODEL_NAME=gemma-3-12b-it \
MULTIMODAL_MODEL=moondream2-20250414 \
IMAGE_MODEL=sd-1.5-ggml \
docker compose -f docker-compose.intel.yaml up
```

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

### Go File System Operations

Source: https://github.com/mudler/localagi/blob/main/README.md

This Go code handles reading, writing, and listing files. It expects a configuration map with 'path', 'action', and optional 'content' fields.

```go
import (
    "encoding/json"
    "fmt"
    "os"
    "path/filepath"
)

type FileParams struct {
    Path    string `json:"path"`
    Action  string `json:"action"`
    Content string `json:"content,omitempty"`
}

func Run(config map[string]interface{}) (string, map[string]interface{}, error) {
    p := FileParams{}
    b, err := json.Marshal(config)
    if err != nil {
        return "", map[string]interface{}{}, err
    }
    if err := json.Unmarshal(b, &p); err != nil {
        return "", map[string]interface{}{}, err
    }

    switch p.Action {
    case "read":
        content, err := os.ReadFile(p.Path)
        if err != nil {
            return "", map[string]interface{}{}, err
        }
        return string(content), map[string]interface{}{}, nil
        
    case "write":
        err := os.WriteFile(p.Path, []byte(p.Content), 0644)
        if err != nil {
            return "", map[string]interface{}{}, err
        }
        return fmt.Sprintf("Successfully wrote to %s", p.Path), map[string]interface{}{}, nil
        
    case "list":
        files, err := os.ReadDir(p.Path)
        if err != nil {
            return "", map[string]interface{}{}, err
        }
        
        var fileList []string
        for _, file := range files {
            fileList = append(fileList, file.Name())
        }
        
        result, _ := json.Marshal(fileList)
        return string(result), map[string]interface{}{}, nil
        
default:
        return "", map[string]interface{}{}, fmt.Errorf("unknown action: %s", p.Action)
    }
}

func Definition() map[string][]string {
    return map[string][]string{
        "path": []string{
            "string",
            "The file or directory path",
        },
        "action": []string{
            "string",
            "The action to perform: read, write, or list",
        },
        "content": []string{
            "string",
            "Content to write (required for write action)",
        },
    }
}

func RequiredFields() []string {
    return []string{"path", "action"}
}

```

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

### Customize NVIDIA GPU Models

Source: https://github.com/mudler/localagi/blob/main/README.md

Specify custom text, multimodal, and image models for NVIDIA GPU acceleration using environment variables.

```bash
MODEL_NAME=gemma-3-12b-it \
MULTIMODAL_MODEL=moondream2-20250414 \
IMAGE_MODEL=flux.1-dev-ggml \
docker compose -f docker-compose.nvidia.yaml up
```

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

### Create a new agent

Source: https://github.com/mudler/localagi/blob/main/README.md

Creates a new agent with specified configurations.

```APIDOC
## POST /api/agent/create

### Description
Create a new agent.

### Method
POST

### Endpoint
/api/agent/create

### Request Body
- **name** (string) - Required - The name of the agent.
- **model** (string) - Required - The model to be used by the agent.
- **system_prompt** (string) - Required - The system prompt for the agent.
- **enable_kb** (boolean) - Optional - Whether to enable knowledge base.
- **enable_reasoning** (boolean) - Optional - Whether to enable reasoning.
```

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

### Run Intel GPU Configuration

Source: https://github.com/mudler/localagi/blob/main/README.md

Use this command to run LocalAGI with Intel GPU acceleration. This is suitable for Intel Arc and integrated GPUs.

```bash
docker compose -f docker-compose.intel.yaml up
```

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

### Import Agent Configuration

Source: https://github.com/mudler/localagi/blob/main/README.md

Imports an agent configuration from a JSON file. This allows for restoring or setting up agents with predefined configurations.

```bash
curl -X POST "http://localhost:3000/settings/import" \
  -F "file=@/path/to/my-agent.json"
```

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

### List available actions

Source: https://github.com/mudler/localagi/blob/main/README.md

Retrieves a list of all available actions that can be executed.

```APIDOC
## GET /api/actions

### Description
List available actions.

### Method
GET

### Endpoint
/api/actions
```

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

### Customize CPU Model

Source: https://github.com/mudler/localagi/blob/main/README.md

Set the MODEL_NAME environment variable to specify a custom text model when running LocalAGI on CPU.

```bash
MODEL_NAME=gemma-3-12b-it docker compose up
```

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

### Local MCP GitHub Server Configuration

Source: https://github.com/mudler/localagi/blob/main/README.md

This JSON configures a local MCP server for GitHub using Docker. Ensure the GITHUB_PERSONAL_ACCESS_TOKEN environment variable is set.

```json
{
  "mcpServers": {
    "github": {
      "command": "docker",
      "args": [
        "run",
        "-i",
        "--rm",
        "-e",
        "GITHUB_PERSONAL_ACCESS_TOKEN",
        "ghcr.io/github/github-mcp-server"
      ],
      "env": {
        "GITHUB_PERSONAL_ACCESS_TOKEN": "<YOUR_TOKEN>"
      }
    }
  }
}

```

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

### Fetch Agent Configuration Metadata

Source: https://github.com/mudler/localagi/blob/main/README.md

Use this curl command to retrieve all available agent configuration fields, including their types and descriptions, from the metadata endpoint.

```bash
curl -X GET "http://localhost:3000/api/meta/agent/config"
```

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

### Configure Slack Connector

Source: https://github.com/mudler/localagi/blob/main/README.md

Configure Slack with your bot token and app token. Obtain these from your Slack app's OAuth & Permissions and Basic Information settings.

```json
{
  "botToken": "xoxb-your-bot-token",
  "appToken": "xapp-your-app-token"
}
```

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

### Execute an action

Source: https://github.com/mudler/localagi/blob/main/README.md

Executes a specified action.

```APIDOC
## POST /api/action/:name/run

### Description
Execute an action.

### Method
POST

### Endpoint
/api/action/:name/run

### Parameters
#### Path Parameters
- **name** (string) - Required - The name of the action to execute.
```

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

### Import agent config

Source: https://github.com/mudler/localagi/blob/main/README.md

Imports agent configuration from a file.

```APIDOC
## POST /settings/import

### Description
Import agent config.

### Method
POST

### Endpoint
/settings/import

### Request Body
- **file** (file) - Required - The agent configuration file to import.
```

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

### Configure GitHub Issues Connector

Source: https://github.com/mudler/localagi/blob/main/README.md

Provide your Personal Access Token, repository details, and bot username to monitor GitHub issues.

```json
{
  "token": "YOUR_PAT_TOKEN",
  "repository": "repo-to-monitor",
  "owner": "repo-owner",
  "botUserName": "bot-username"
}
```

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

### Customize Actions Directory

Source: https://github.com/mudler/localagi/blob/main/README.md

Use the LOCALAGI_CUSTOM_ACTIONS_DIR environment variable to point to a custom directory for actions when running LocalAGI.

```bash
LOCALAGI_CUSTOM_ACTIONS_DIR=/app/custom-actions docker compose up
```

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

### Agent SSE Stream

Source: https://github.com/mudler/localagi/blob/main/README.md

Establishes a Server-Sent Events (SSE) stream for real-time agent events. Requires a client that natively supports SSE for proper handling.

```bash
curl -N -X GET "http://localhost:3000/api/sse/my-agent"
```

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

### Configure IRC Connector

Source: https://github.com/mudler/localagi/blob/main/README.md

Connect to IRC networks by providing server details, nickname, and channel. The `alwaysReply` setting controls bot behavior.

```json
{
  "server": "irc.example.com",
  "port": "6667",
  "nickname": "LocalAGIBot",
  "channel": "#yourchannel",
  "alwaysReply": "false"
}
```

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

### Set Custom Actions Directory Environment Variable

Source: https://github.com/mudler/localagi/blob/main/README.md

Configure the environment variable to specify the directory for custom Go action files. This allows LocalAGI to automatically load your custom actions.

```bash
export LOCALAGI_CUSTOM_ACTIONS_DIR="/path/to/custom/actions"
```

```yaml
environment:
  - LOCALAGI_CUSTOM_ACTIONS_DIR=/app/custom-actions
```

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

### List all available agents

Source: https://github.com/mudler/localagi/blob/main/README.md

Retrieves a list of all agents currently available in the system.

```APIDOC
## GET /api/agents

### Description
Lists all available agents.

### Method
GET

### Endpoint
/api/agents
```

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

### Login JavaScript Function

Source: https://github.com/mudler/localagi/blob/main/webui/public/views/login.html

Handles the login process by validating the access token and setting it as a cookie. Displays an error message if the token is empty. Focuses the input field and applies a shake animation on error.

```javascript
function login() {
  var token = document.getElementById('token');
  var errorMsg = document.getElementById('error-message');
  var tokenValue = token.value.trim();
  if (!tokenValue) {
    errorMsg.innerHTML = '<i class="fas fa-exclamation-circle"></i> Please enter a valid token';
    errorMsg.style.display = 'flex';
    errorMsg.style.animation = 'none';
    errorMsg.offsetHeight;
    errorMsg.style.animation = 'shake 0.4s ease-out';
    token.focus();
    return;
  }
  var date = new Date();
  date.setTime(date.getTime() + (24 * 60 * 60 * 1000));
  document.cookie = 'token=' +
```

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

### Configure Email Connector

Source: https://github.com/mudler/localagi/blob/main/README.md

Configure email integration with SMTP and IMAP server details, authentication credentials, and display name. Set `smtpInsecure` and `imapInsecure` to 'false' for TLS/SSL connections.

```json
{
  "smtpServer": "smtp.gmail.com:587",
  "imapServer": "imap.gmail.com:993",
  "smtpInsecure": "false",
  "imapInsecure": "false",
  "username": "user@gmail.com",
  "email": "user@gmail.com",
  "password": "correct-horse-battery-staple",
  "name": "LogalAGI Agent"
}
```

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

### Login Authentication JavaScript

Source: https://github.com/mudler/localagi/blob/main/webui/views/login.html

Handles user login by validating the access token, setting it as a cookie, and initiating a page reload upon successful authentication. It also provides visual feedback during the authentication process.

```javascript
function login() {
    var token = document.getElementById('token');
    var errorMsg = document.getElementById('error-message');
    var tokenValue = token.value.trim();

    if (!tokenValue) {
        errorMsg.innerHTML = '<i class="fas fa-exclamation-circle"></i> Please enter a valid token';
        errorMsg.style.display = 'flex';
        errorMsg.style.animation = 'none';
        errorMsg.offsetHeight; // Trigger reflow
        errorMsg.style.animation = 'shake 0.4s ease-out';
        token.focus();
        return;
    }

    var date = new Date();
    date.setTime(date.getTime() + (24 * 60 * 60 * 1000)); // Expires in 24 hours
    document.cookie = 'token=' + tokenValue + '; expires=' + date.toGMTString() + '; path=/';

    var button = document.querySelector('.login-button');
    button.disabled = true;
    button.innerHTML = '<i class="fas fa-spinner fa-spin"></i><span>Authenticating...</span>';
    button.style.opacity = '0.8';

    setTimeout(function() {
        window.location.reload();
    }, 800);
}
```

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

### Real-time agent event stream

Source: https://github.com/mudler/localagi/blob/main/README.md

Establishes a real-time stream of events from an agent.

```APIDOC
## GET /api/sse/:name

### Description
Real-time agent event stream. For proper SSE handling, you should use a client that supports SSE natively.

### Method
GET

### Endpoint
/api/sse/:name

### Parameters
#### Path Parameters
- **name** (string) - Required - The name of the agent.
```

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

### Create a new agent group

Source: https://github.com/mudler/localagi/blob/main/README.md

Creates a new group of agents.

```APIDOC
## POST /api/agent/group/create

### Description
Create a new agent group.

### Method
POST

### Endpoint
/api/agent/group/create
```

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

### Export Agent Configuration

Source: https://github.com/mudler/localagi/blob/main/README.md

Exports the configuration of a specific agent to a JSON file. This is useful for backup or migration purposes.

```bash
curl -X GET "http://localhost:3000/settings/export/my-agent" --output my-agent.json
```

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

### Update Agent Configuration

Source: https://github.com/mudler/localagi/blob/main/README.md

Updates the configuration of an existing agent. Only specified fields like model or system prompt will be modified.

```bash
curl -X PUT "http://localhost:3000/api/agent/my-agent/config" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-4",
    "system_prompt": "You are an AI assistant."
  }'
```

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

### Configure Telegram Connector

Source: https://github.com/mudler/localagi/blob/main/README.md

Set up your Telegram bot token, and configure group mode, mention-only responses, and admin usernames. Ensure your bot can read messages in groups by disabling group privacy settings via BotFather.

```json
{
  "token": "your-bot-father-token",
  "group_mode": "true",
  "mention_only": "true",
  "admins": "username1,username2"
}
```

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

### Configure Discord Connector

Source: https://github.com/mudler/localagi/blob/main/README.md

Use your Discord bot token and optionally a default channel ID. Ensure 'Message Content Intent' is enabled in your bot's settings.

```json
{
  "token": "Bot YOUR_DISCORD_TOKEN",
  "defaultChannel": "OPTIONAL_CHANNEL_ID"
}
```

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

### Send Message to Agent

Source: https://github.com/mudler/localagi/blob/main/README.md

Sends a message to a specific agent and receives a response. This is the primary way to interact with agents for chat-like conversations.

```bash
curl -X POST "http://localhost:3000/api/chat/my-agent" \
  -H "Content-Type: application/json" \
  -d '{"message": "Hello, how are you today?"}'
```

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

### Export agent config

Source: https://github.com/mudler/localagi/blob/main/README.md

Exports the configuration of a specified agent to a file.

```APIDOC
## GET /settings/export/:name

### Description
Export agent config.

### Method
GET

### Endpoint
/settings/export/:name

### Parameters
#### Path Parameters
- **name** (string) - Required - The name of the agent to export.
```

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

### Generate group profiles

Source: https://github.com/mudler/localagi/blob/main/README.md

Generates profiles for an agent group.

```APIDOC
## POST /api/agent/group/generateProfiles

### Description
Generate group profiles.

### Method
POST

### Endpoint
/api/agent/group/generateProfiles
```

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

### Send notification to agent

Source: https://github.com/mudler/localagi/blob/main/README.md

Sends a notification to a specified agent.

```APIDOC
## POST /api/notify/:name

### Description
Send notification to agent.

### Method
POST

### Endpoint
/api/notify/:name

### Parameters
#### Path Parameters
- **name** (string) - Required - The name of the agent to notify.

### Request Body
- **message** (string) - Required - The notification message.
```

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

### Resume a paused agent

Source: https://github.com/mudler/localagi/blob/main/README.md

Resumes the activities of a paused agent.

```APIDOC
## PUT /api/agent/:name/start

### Description
Resume a paused agent.

### Method
PUT

### Endpoint
/api/agent/:name/start

### Parameters
#### Path Parameters
- **name** (string) - Required - The name of the agent to resume.
```

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

### Real-time Clock Update JavaScript

Source: https://github.com/mudler/localagi/blob/main/webui/views/login.html

Updates an HTML element with the current UTC time every second. Ensures the time display is accurate and dynamic.

```javascript
function updateCurrentTime() {
    var timeElement = document.getElementById('current-time');
    if (timeElement) {
        var now = new Date();
        var year = now.getUTCFullYear();
        var month = String(now.getUTCMonth() + 1).padStart(2, '0');
        var day = String(now.getUTCDate()).padStart(2, '0');
        var hours = String(now.getUTCHours()).padStart(2, '0');
        var minutes = String(now.getUTCMinutes()).padStart(2, '0');
        var seconds = String(now.getUTCSeconds()).padStart(2, '0');
        timeElement.textContent = year + '-' + month + '-' + day + ' ' + hours + ':' + minutes + ':' + seconds;
    }
}

updateCurrentTime();
setInterval(updateCurrentTime, 1000);
```

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

### Update agent configuration

Source: https://github.com/mudler/localagi/blob/main/README.md

Updates the configuration of a specific agent.

```APIDOC
## PUT /api/agent/:name/config

### Description
Update agent configuration.

### Method
PUT

### Endpoint
/api/agent/:name/config

### Parameters
#### Path Parameters
- **name** (string) - Required - The name of the agent.

### Request Body
- **model** (string) - Optional - The new model for the agent.
- **system_prompt** (string) - Optional - The new system prompt for the agent.
```

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

### Notify Agent

Source: https://github.com/mudler/localagi/blob/main/README.md

Sends a notification to a specific agent. This is useful for alerting agents to important events or information.

```bash
curl -X POST "http://localhost:3000/api/notify/my-agent" \
  -H "Content-Type: application/json" \
  -d '{"message": "Important notification"}'
```

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

### Disable Login Button and Show Spinner

Source: https://github.com/mudler/localagi/blob/main/webui/public/views/login.html

Disables the login button, displays a spinning icon and 'Authenticating...' text, and then reloads the page after a short delay. This is used to provide visual feedback during the authentication process.

```javascript
var button = document.querySelector('.login-button');
button.disabled = true;
button.innerHTML = '<i class="fas fa-spinner fa-spin"></i><span>Authenticating...</span>';
button.style.opacity = '0.8';
setTimeout(function() { window.location.reload(); }, 800);
```

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

### Pause Agent

Source: https://github.com/mudler/localagi/blob/main/README.md

Pauses the activities of a specific agent. The agent can be resumed later.

```bash
curl -X PUT "http://localhost:3000/api/agent/my-agent/pause"
```

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

### Update and Display Current UTC Time

Source: https://github.com/mudler/localagi/blob/main/webui/public/views/login.html

Fetches the current UTC date and time and formats it as 'YYYY-MM-DD HH:MM:SS'. The time is updated every second to keep it current. This function is called once on load and then set to repeat.

```javascript
function updateCurrentTime() {
  var timeElement = document.getElementById('current-time');
  if (timeElement) {
    var now = new Date();
    var year = now.getUTCFullYear();
    var month = String(now.getUTCMonth() + 1).padStart(2, '0');
    var day = String(now.getUTCDate()).padStart(2, '0');
    var hours = String(now.getUTCHours()).padStart(2, '0');
    var minutes = String(now.getUTCMinutes()).padStart(2, '0');
    var seconds = String(now.getUTCSeconds()).padStart(2, '0');
    timeElement.textContent = year + '-' + month + '-' + day + ' ' + hours + ':' + minutes + ':' + seconds;
  }
}
updateCurrentTime();
setInterval(updateCurrentTime, 1000);
```

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

### Pause agent activities

Source: https://github.com/mudler/localagi/blob/main/README.md

Pauses the activities of a specified agent.

```APIDOC
## PUT /api/agent/:name/pause

### Description
Pause agent activities.

### Method
PUT

### Endpoint
/api/agent/:name/pause

### Parameters
#### Path Parameters
- **name** (string) - Required - The name of the agent to pause.
```

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

### View agent status history

Source: https://github.com/mudler/localagi/blob/main/README.md

Retrieves the status history for a specific agent.

```APIDOC
## GET /api/agent/:name/status

### Description
View agent status history.

### Method
GET

### Endpoint
/api/agent/:name/status

### Parameters
#### Path Parameters
- **name** (string) - Required - The name of the agent.
```

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

### Delete Agent

Source: https://github.com/mudler/localagi/blob/main/README.md

Removes an agent from the system. Use with caution as this action is irreversible.

```bash
curl -X DELETE "http://localhost:3000/api/agent/my-agent"
```

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

### Remove an agent

Source: https://github.com/mudler/localagi/blob/main/README.md

Deletes an agent from the system.

```APIDOC
## DELETE /api/agent/:name

### Description
Remove an agent.

### Method
DELETE

### Endpoint
/api/agent/:name

### Parameters
#### Path Parameters
- **name** (string) - Required - The name of the agent to remove.
```

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