Idun Agent Platform

https://docs.idunplatform.com
Admin
An open-source, self-hosted control plane for deploying AI agents to production with guardrails,...
Tokens:82,962
Snippets:753
Trust Score:7.5
Update:5 months ago
Show doc for...
Tokens:
Raw
### Start Development Stack with Docker Compose (Alternative)

Source: https://docs.idunplatform.com/deployment/overview

This command clones the repository and sets up the development environment by copying the example environment file and starting the services. It's an alternative way to initiate the development setup.

```bash
git clone https://github.com/Idun-Group/idun-agent-platform.git
cd idun-agent-platform
cp .env.example .env
docker compose up
```

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

### Install Dependencies and Configure Environment

Source: https://docs.idunplatform.com/templates

Install project dependencies using pip and copy the example environment file. You will need to edit the .env file with your specific API keys.

```bash
pip install -r requirements.txt
cp .env.example .env
```

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

### Start Idun Agent Server with Config File

Source: https://docs.idunplatform.com/guides/langgraph-production-deployment

Set the Gemini API key and start the Idun agent server using the provided configuration file. This command initiates the agent's operation.

```bash
export GEMINI_API_KEY="your-gemini-api-key"
idun agent serve --source file --path config.yaml
```

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

### Run Idun Agent with Manager UI Integration

Source: https://docs.idunplatform.com/guides/langgraph-production-deployment

Install dependencies, set environment variables for API keys and manager host, and start the Idun agent server pointing to the manager. This connects the agent to the Idun platform for management.

```bash
pip install idun-agent-engine langchain-google-genai
export GEMINI_API_KEY="your-gemini-api-key"
export IDUN_MANAGER_HOST="http://localhost:8000"
export IDUN_AGENT_API_KEY="<your-api-key>"
idun agent serve --source manager
```

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

### Install and Serve ADK Agent (Manager UI)

Source: https://docs.idunplatform.com/frameworks/adk

Install necessary packages and serve your ADK agent using the Manager UI. Ensure environment variables for host and API key are set.

```bash
pip install idun-agent-engine google-adk
export IDUN_MANAGER_HOST=http://localhost:8000
export IDUN_AGENT_API_KEY=<your-api-key>
idun agent serve --source manager
```

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

### Start Idun Agent Platform (Production)

Source: https://docs.idunplatform.com/quickstart

Use this command to start the full platform including PostgreSQL, FastAPI backend, and React admin UI using pre-built Docker images. Ensure the Docker daemon is running.

```bash
docker compose up -d
```

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

### Complete Engine Configuration Example

Source: https://docs.idunplatform.com/configuration

This example demonstrates a comprehensive EngineConfig YAML file, showcasing various sections like server, agent, observability, guardrails, MCP servers, prompts, SSO, and integrations. It illustrates the use of environment variables for sensitive configuration values.

```yaml
server:
  api:
    port: 8001

agent:
  type: "LANGGRAPH"
  config:
    name: "Support Agent"
    graph_definition: "./agent.py:graph"
    checkpointer:
      type: "sqlite"
      db_url: "sqlite:///checkpoints.db"

observability:
  - provider: "LANGFUSE"
    enabled: true
    config:
      host: "https://cloud.langfuse.com"
      public_key: "${LANGFUSE_PUBLIC_KEY}"
      secret_key: "${LANGFUSE_SECRET_KEY}"

guardrails:
  input:
    - config_id: "DETECT_PII"
      on_fail: "reject"
      reject_message: "Request contains personal information."
  output:
    - config_id: "TOXIC_LANGUAGE"
      on_fail: "reject"

mcp_servers:
  - name: "time"
    transport: "stdio"
    command: "docker"
    args: ["run", "-i", "--rm", "mcp/time"]

prompts:
  - prompt_id: "system-prompt"
    version: 1
    content: "You are a support agent for {{ company_name }}"
    tags: ["latest"]

sso:
  enabled: true
  issuer: "https://accounts.google.com"
  client_id: "123456789.apps.googleusercontent.com"
  allowed_domains: ["yourcompany.com"]

integrations:
  - provider: "WHATSAPP"
    enabled: true
    config:
      access_token: "${WHATSAPP_ACCESS_TOKEN}"
      phone_number_id: "${WHATSAPP_PHONE_ID}"
      verify_token: "${WHATSAPP_VERIFY_TOKEN}"
```

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

### Enroll LangGraph Agent via CLI

Source: https://docs.idunplatform.com/frameworks/langgraph

Install necessary packages and set environment variables to enroll your LangGraph agent. The agent connects to the Manager, fetches its configuration, and starts.

```bash
pip install idun-agent-engine langgraph langchain-openai
export IDUN_MANAGER_HOST=http://localhost:8000
export IDUN_AGENT_API_KEY=<your-api-key>
idun agent serve --source manager
```

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

### Install idun-agent-engine

Source: https://docs.idunplatform.com/cli/overview

Install the necessary package to use the Idun CLI. This command should be run in your project's environment.

```bash
pip install idun-agent-engine
```

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

### Start Docker Compose with Demo Profile

Source: https://docs.idunplatform.com/deployment/overview

To include the demo agent service when running your Docker Compose stack, use the `--profile demo` flag. This command starts the services defined in the default `docker-compose.yml` along with the demo agent.

```bash
docker compose --profile demo up
```

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

### Run LangGraph Agent from Config File

Source: https://docs.idunplatform.com/frameworks/langgraph

Install required packages and run the LangGraph agent using a configuration file. This method allows for programmatic agent setup.

```bash
pip install idun-agent-engine langgraph langchain-openai
idun agent serve --source file --path config.yaml
```

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

### Clone Idun Platform and Start Docker Compose

Source: https://docs.idunplatform.com/guides/langgraph-production-deployment

Clone the Idun agent platform repository and start the development environment using Docker Compose. This sets up PostgreSQL, the Manager API, and the web UI.

```bash
git clone https://github.com/Idun-Group/idun-agent-platform.git
cd idun-agent-platform
cp .env.example .env
docker compose -f docker-compose.dev.yml up --build
```

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

### Launch Interactive TUI

Source: https://docs.idunplatform.com/cli/overview

Start the interactive Terminal User Interface (TUI) for step-by-step agent configuration. The TUI guides you through setting up agent information, memory, observability, guardrails, and MCP servers.

```bash
idun init
```

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

### Serve the Agent

Source: https://docs.idunplatform.com/manager/tutorial

Start the agent using the Idun CLI. The --source flag indicates the location of your agent's code or configuration.

```bash
idun agent serve --source manager
```

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

### Install Idun Engine and Langchain Google GenAI SDK

Source: https://docs.idunplatform.com/guides/langgraph-production-deployment

Install the necessary Python packages for the Idun agent engine and the Google Generative AI integration. This is a prerequisite for running LangGraph agents with Idun.

```bash
pip install idun-agent-engine langchain-google-genai
```

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

### Serve Agent from Saved TUI Config

Source: https://docs.idunplatform.com/cli/overview

Start an agent using a configuration file previously saved by the interactive TUI. The default location is `~/.idun/<agent-name>.yaml`.

```bash
idun agent serve --source file --path ~/.idun/my-agent.yaml
```

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

### Integrate Prompt with LangChain

Source: https://docs.idunplatform.com/prompts

Convert an Idun prompt to a LangChain `PromptTemplate` using the `to_langchain()` method. This requires the `langchain-core` library to be installed.

```python
prompt = get_prompt("rag-query")
lc_prompt = prompt.to_langchain()

result = lc_prompt.format(context="AI is...", query="What is AI?")
```

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

### Minimal LangGraph Agent Setup

Source: https://docs.idunplatform.com/quickstart

This Python code defines a simple chatbot function and sets up a LangGraph StateGraph. It requires the OPENAI_API_KEY environment variable to be set.

```python
from langgraph.graph import StateGraph, MessagesState

def chatbot(state: MessagesState):
    from langchain_openai import ChatOpenAI
    model = ChatOpenAI(model="gpt-4o-mini")
    return {"messages": [model.invoke(state["messages")]}

graph = StateGraph(MessagesState)
graph.add_node("chatbot", chatbot)
graph.set_entry_point("chatbot")
graph.set_finish_point("chatbot")
```

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

### Run Agent Locally

Source: https://docs.idunplatform.com/templates

Start the agent locally without the Manager for testing purposes. This allows you to verify agent logic before connecting to the platform.

```bash
idun web --port 8010
```

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

### Configure Database Session Service

Source: https://docs.idunplatform.com/memory/adk

Example configuration for the database session service using YAML. Ensure the `db_url` is correctly formatted for your database connection.

```yaml
agent:
  type: "ADK"
  config:
    session_service:
      type: "database"
      db_url: "postgresql://user:pass@localhost:5432/dbname"
```

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

### Pull Fetch MCP Server Image

Source: https://docs.idunplatform.com/tool-governance/docker-toolkit

Use this command to download the Fetch MCP server Docker image. Ensure Docker Desktop is installed and running.

```bash
docker pull mcp/fetch
```

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

### Clone Agent Template Repository

Source: https://docs.idunplatform.com/templates

Clone the repository containing runnable agent templates. This is the first step to getting started with pre-built agent examples.

```bash
git clone https://github.com/Idun-Group/idun-agent-template.git
cd idun-agent-template
```

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

### Get Managed SSO Config by ID

Source: https://docs.idunplatform.com/api-reference/sso/get-managed-sso-config-by-id

Fetches a managed SSO configuration using its ID. This endpoint is useful for retrieving the full details of an existing SSO setup.

```APIDOC
## GET /api/v1/sso/{id}

### Description
Get a managed SSO configuration by ID.

### Method
GET

### Endpoint
/api/v1/sso/{id}

### Parameters
#### Path Parameters
- **id** (string) - Required - The unique identifier of the SSO configuration.

#### Header Parameters
- **x-workspace-id** (string) - Optional - The workspace ID.

#### Responses
#### Success Response (200)
- **id** (string) - The unique identifier of the SSO configuration.
- **name** (string) - The name of the SSO configuration.
- **sso** (object) - The SSO (OIDC) configuration details.
  - **enabled** (boolean) - Toggle SSO enforcement on protected routes. Defaults to true.
  - **issuer** (string) - OIDC issuer URL.
  - **clientId** (string) - OAuth 2.0 client ID.
  - **audience** (string | null) - Expected JWT 'aud' claim. Defaults to client_id if not set.
  - **allowedDomains** (array[string] | null) - Optional list of allowed email domains.
  - **allowedEmails** (array[string] | null) - Optional list of specific email addresses allowed access.
- **agent_count** (integer) - Number of agents using this SSO config. Defaults to 0.
- **created_at** (string) - Creation timestamp.
- **updated_at** (string) - Last update timestamp.

#### Error Response (422)
- **detail** (array[object]) - Validation error details.
```

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

### Clone and Configure Project

Source: https://docs.idunplatform.com/quickstart

Clone the Idun Agent Platform repository and set up the environment variables.

```bash
git clone https://github.com/Idun-Group/idun-agent-platform.git
cd idun-agent-platform
cp .env.example .env
```

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

### Get Agent Config using cURL

Source: https://docs.idunplatform.com/api-reference/agents/get-agent-config-by-api-key

Use this cURL command to make a GET request to retrieve agent configuration. Ensure you replace `<auth>` with your actual authentication token.

```curl
curl --request GET \
  --url https://api.example.com/api/v1/agents/config \
  --header 'auth: <auth>'
```

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

### Create LangGraph Project Directory

Source: https://docs.idunplatform.com/guides/langgraph-production-deployment

Sets up the basic directory structure for a LangGraph project. This is the initial step before writing agent code.

```bash
mkdir langgraph-prod && cd langgraph-prod
mkdir agent && touch agent/__init__.py
```

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

### OpenAPI Specification for Get Current Session

Source: https://docs.idunplatform.com/api-reference/auth/get-current-session

This OpenAPI specification defines the GET endpoint for retrieving the current user session. It outlines the request method, path, and expected response structure.

```yaml
openapi: 3.1.0
info:
  title: Idun Agent Manager API
  description: Idun service for managing AI agents
  version: 0.5.4
servers: []
security: []
paths:
  /api/v1/auth/me:
    get:
      tags:
        - Auth
      summary: Get current session
      description: Returns the current user session with fresh workspace data from DB.
      operationId: me_api_v1_auth_me_get
      responses:
        '200': 
          description: Successful Response
          content:
            application/json:
              schema:
                additionalProperties: true
                type: object
                title: Response Me Api V1 Auth Me Get

```

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

### Configure Fetch MCP Server Args

Source: https://docs.idunplatform.com/tool-governance/docker-toolkit

The Args field must be a valid JSON array. This example shows the correct format for running the `mcp/fetch` Docker image.

```json
["run", "-i", "--rm", "mcp/fetch"]
```

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

### Deploy Production Stack with Docker Compose

Source: https://docs.idunplatform.com/deployment/overview

Use this command to clone the repository, navigate to the directory, and start the full Idun Agent Platform stack using pre-built Docker images. Ensure you edit the `docker-compose.yml` file to set a strong `AUTH__SECRET_KEY` before running.

```bash
git clone https://github.com/Idun-Group/idun-agent-platform.git
cd idun-agent-platform
# Edit docker-compose.yml: set AUTH__SECRET_KEY to a strong random value
docker compose up -d
```

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

### Serve Agent Connected to Platform

Source: https://docs.idunplatform.com/templates

Connect your agent to the Idun Manager for centralized management. This command fetches configuration from the platform and applies guardrails, observability, memory, and MCP tools.

```bash
export IDUN_MANAGER_HOST=http://localhost:8000
export IDUN_AGENT_API_KEY=<your-api-key>
idun agent serve --source manager
```

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

### Get prompt by ID

Source: https://docs.idunplatform.com/llms.txt

Retrieves a prompt by its unique identifier.

```APIDOC
## Get prompt by ID

### Description
Get a prompt by its UUID.

### Method
GET

### Endpoint
/api/v1/prompts/{id}

### Parameters
#### Path Parameters
- **id** (string) - Required - The UUID of the prompt to retrieve.
```

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

### Configure Filesystem MCP Server

Source: https://docs.idunplatform.com/tool-governance/docker-toolkit

Example configuration for an MCP server that provides filesystem access. It uses the 'stdio' transport and executes 'npx' with specific arguments to access files within allowed directories.

```json
{
  "Name": "filesystem",
  "Transport": "stdio",
  "Command": "npx",
  "Args": [
    "-y",
    "@modelcontextprotocol/server-filesystem",
    "/allowed/path"
  ]
}
```

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

### Configure Input and Output Guardrails

Source: https://docs.idunplatform.com/guardrails/reference

Example of configuring guardrails for both input and output positions in a YAML configuration file. This demonstrates setting up PII detection for input and toxic language filtering for output.

```yaml
guardrails:
  input:
    - config_id: detect_pii
      reject_message: "PII detected in your input"
      pii_entities: ["EMAIL_ADDRESS", "PHONE_NUMBER", "CREDIT_CARD"]
      on_fail: exception

  output:
    - config_id: toxic_language
      reject_message: "Response contains inappropriate language"
      threshold: 0.7
```

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

### OpenAPI Specification for Get Prompt by ID

Source: https://docs.idunplatform.com/api-reference/prompts/get-prompt-by-id

This OpenAPI specification defines the GET /api/v1/prompts/{id} endpoint, which allows you to retrieve a prompt by its UUID. It includes request parameters, response schemas for success and validation errors, and component schemas for prompt data and error details.

```yaml
openapi: 3.1.0
info:
  title: Idun Agent Manager API
  description: Idun service for managing AI agents
  version: 0.5.4
servers: []
security: []
paths:
  /api/v1/prompts/{id}:
    get:
      tags:
        - Prompts
      summary: Get prompt by ID
      description: Get a prompt by its UUID.
      operationId: get_prompt_api_v1_prompts__id__get
      parameters:
        - name: id
          in: path
          required: true
          schema:
            type: string
            title: Id
        - name: x-workspace-id
          in: header
          required: false
          schema:
            anyOf:
              - type: string
              - type: 'null'
            title: X-Workspace-Id
      responses:
        '200':
          description: Successful Response
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ManagedPromptRead'
        '422':
          description: Validation Error
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/HTTPValidationError'
components:
  schemas:
    ManagedPromptRead:
      properties:
        id:
          type: string
          format: uuid
          title: Id
        prompt_id:
          type: string
          title: Prompt Id
        version:
          type: integer
          title: Version
        content:
          type: string
          title: Content
        tags:
          items:
            type: string
          type: array
          title: Tags
        created_at:
          type: string
          format: date-time
          title: Created At
        updated_at:
          type: string
          format: date-time
          title: Updated At
      type: object
      required:
        - id
        - prompt_id
        - version
        - content
        - tags
        - created_at
        - updated_at
      title: ManagedPromptRead
      description: Response body for a prompt.
    HTTPValidationError:
      properties:
        detail:
          items:
            $ref: '#/components/schemas/ValidationError'
          type: array
          title: Detail
      type: object
      title: HTTPValidationError
    ValidationError:
      properties:
        loc:
          items:
            anyOf:
              - type: string
              - type: integer
          type: array
          title: Location
        msg:
          type: string
          title: Message
        type:
          type: string
          title: Error Type
      type: object
      required:
        - loc
        - msg
        - type
      title: ValidationError

```

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

### Example Agent Configuration File

Source: https://docs.idunplatform.com/cli/overview

This YAML structure represents a typical agent configuration file. It defines server settings, agent type and configuration, observability, guardrails, and MCP servers.

```yaml
server:
  api:
    port: 8008

agent:
  type: LANGGRAPH
  config:
    name: my-agent
    graph_definition: ./agent.py:app
    checkpointer:
      type: memory

observability:
  provider: OFF

guardrails: []

mcp_servers: []
```

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

### Version

Source: https://docs.idunplatform.com/llms.txt

Get application version and name from FastAPI app metadata.

```APIDOC
## Version

### Description
Get application version and name from FastAPI app metadata.

### Method
GET

### Endpoint
/version
```

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

### Enroll Agent with Environment Variables

Source: https://docs.idunplatform.com/manager/overview

Set environment variables for the API key and Manager host before starting the agent in managed mode. This allows the agent to connect to the Manager and fetch its configuration upon startup.

```bash
export IDUN_AGENT_API_KEY=<your-agent-api-key>
export IDUN_MANAGER_HOST=https://manager.example.com
idun agent serve --source manager
```

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

### Get Managed Agent by ID

Source: https://docs.idunplatform.com/api-reference/agents/get-managed-agent-by-id

Retrieves a specific managed agent by its UUID.

```APIDOC
## Get Managed Agent by ID

### Description
Retrieve a specific managed agent by its UUID with complete configuration details.

### Method
GET

### Endpoint
/agents/{agent_id}

### Parameters
#### Path Parameters
- **agent_id** (string) - Required - The unique identifier (UUID) of the agent to retrieve.
```

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

### Get Managed SSO Config by ID

Source: https://docs.idunplatform.com/api-reference/sso/get-managed-sso-config-by-id

Fetches a managed SSO configuration by its ID.

```APIDOC
## Get managed SSO config by ID

### Description
Get a managed SSO configuration by ID.

### Method
GET

### Endpoint
`/sso/managed/{id}`

### Parameters
#### Path Parameters
- **id** (string) - Required - The unique identifier of the managed SSO configuration.
```

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

### Configure Docker Logging for MCP Server

Source: https://docs.idunplatform.com/tool-governance/docker-toolkit

Example of configuring Docker logging drivers and options for an MCP server. This improves observability by managing log size and format.

```json
["run", "-i", "--rm", "--log-driver=json-file", "--log-opt=max-size=10m", "mcp/fetch"]
```

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

### System Overview Diagram

Source: https://docs.idunplatform.com/architecture

Visual representation of how Idun Agent Platform components interact.

```mermaid
graph LR
    Schema["Schema\n(Pydantic models)"] --> Manager["Manager\n(Control plane API)"]
    Schema --> Engine["Engine\n(Agent runtime SDK)"]
    Manager --> Engine
    Web["Web UI\n(Admin dashboard)"] --> Manager
    Engine --> Agent["Your agent\n(Production API)"]
```

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

### Get Managed Memory Config by ID

Source: https://docs.idunplatform.com/api-reference/memory/get-managed-memory-config-by-id

Fetches a managed memory configuration by its ID.

```APIDOC
## Get managed memory config by ID

### Description
Get a managed memory configuration by ID.

### Method
GET

### Endpoint
`/managed-memory-configs/{id}`

### Parameters
#### Path Parameters
- **id** (string) - Required - The unique identifier of the managed memory configuration.
```

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

### Get Managed Observability Config by ID

Source: https://docs.idunplatform.com/api-reference/observability/get-managed-observability-config-by-id

Fetches a managed observability configuration by its ID.

```APIDOC
## Get managed observability config by ID

### Description
Get a managed observability configuration by ID.

### Method
GET

### Endpoint
`/observability/managed/{id}`

### Parameters
#### Path Parameters
- **id** (string) - Required - The unique identifier of the managed observability configuration.
```

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

### Get Managed Guardrail Configuration

Source: https://docs.idunplatform.com/api-reference/guardrails/get-managed-guardrail-config-by-id

This operation retrieves a managed guardrail configuration by its ID.

```APIDOC
## Get managed guardrail config by ID

### Description
Get a managed guardrail configuration by ID.

### Method
GET

### Endpoint
/guardrails/{id}

### Parameters
#### Path Parameters
- **id** (string) - Required - The unique identifier of the managed guardrail configuration.
```

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

### Get current session

Source: https://docs.idunplatform.com/llms.txt

Returns the current user session with fresh workspace data from DB.

```APIDOC
## Get current session

### Description
Returns the current user session with fresh workspace data from DB.

### Method
GET

### Endpoint
/auth/session
```

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

### Get Managed MCP Server by ID

Source: https://docs.idunplatform.com/api-reference/mcp-servers/get-managed-mcp-server-by-id

Fetches a managed MCP server configuration by its ID.

```APIDOC
## GET /api/v1/mcp-servers/{id}

### Description
Get a managed MCP server configuration by ID.

### Method
GET

### Endpoint
/api/v1/mcp-servers/{id}

### Parameters
#### Path Parameters
- **id** (string) - Required - The unique identifier of the MCP server.
#### Header Parameters
- **x-workspace-id** (string) - Optional - The workspace ID.

### Responses
#### Success Response (200)
- **id** (string) - The unique identifier of the managed MCP server.
- **name** (string) - The name of the managed MCP server.
- **mcp_server** (object) - The MCP server configuration.
- **agent_count** (integer) - The number of agents using this MCP server.
- **created_at** (string) - The creation timestamp.
- **updated_at** (string) - The last update timestamp.

#### Error Response (422)
- **detail** (array) - Validation error details.
```

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

### Get Managed MCP Server by ID

Source: https://docs.idunplatform.com/api-reference/mcp-servers/get-managed-mcp-server-by-id

Fetches a managed MCP server configuration by its ID.

```APIDOC
## Get Managed MCP Server by ID

### Description
Get a managed MCP server configuration by ID.

### Method
GET

### Endpoint
`/servers/{id}`

### Parameters
#### Path Parameters
- **id** (string) - Required - The unique identifier of the managed MCP server.
```

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

### Basic Signup

Source: https://docs.idunplatform.com/api-reference/auth/basic-signup

Allows users to create a new account using their email and password.

```APIDOC
## POST /api/v1/auth/basic/signup

### Description
This endpoint allows for basic user signup using email and password.

### Method
POST

### Endpoint
/api/v1/auth/basic/signup

### Request Body
- **email** (string) - Required - User's email address.
- **password** (string) - Required - User's password (minimum 8 characters).
- **name** (string | null) - Optional - User's name.

### Request Example
```json
{
  "email": "user@example.com",
  "password": "securepassword123",
  "name": "John Doe"
}
```

### Response
#### Success Response (200)
- **additionalProperties** (object) - A flexible object for additional response data.

#### Response Example
```json
{
  "message": "User created successfully"
}
```

#### Error Response (422)
- **detail** (array) - Contains details about validation errors.
  - **loc** (array) - Location of the error (e.g., field name).
  - **msg** (string) - Error message.
  - **type** (string) - Type of error.
```

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

### Create Manual Agent Configuration

Source: https://docs.idunplatform.com/quickstart

Define the agent's configuration in a YAML file. This file specifies server settings and agent details, including the graph definition path.

```yaml
server:
  api:
    port: 8008

agent:
  type: "LANGGRAPH"
  config:
    name: "my-agent"
    graph_definition: "./agent.py:graph"
    checkpointer:
      type: "memory"
```

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

### Get Application Version

Source: https://docs.idunplatform.com/api-reference/health/version

This endpoint retrieves the application version and name from the FastAPI app metadata.

```APIDOC
## GET /api/v1/version

### Description
Get application version and name from FastAPI app metadata.

### Method
GET

### Endpoint
/api/v1/version

### Responses
#### Success Response (200)
- **additionalProperties** (string) - Description of additional properties

#### Response Example
```json
{
  "key": "value"
}
```
```

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

### Serve Agent in Managed Mode

Source: https://docs.idunplatform.com/architecture

Commands to configure environment variables for connecting to the manager API. The engine fetches configuration from the manager at startup.

```bash
export IDUN_AGENT_API_KEY=your-agent-api-key
export IDUN_MANAGER_HOST=https://manager.example.com
idun agent serve --source manager
```

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

### Get Prompt by ID

Source: https://docs.idunplatform.com/api-reference/prompts/get-prompt-by-id

Fetches a prompt by its UUID. This endpoint is useful for retrieving prompt details for further processing or display.

```APIDOC
## GET /api/v1/prompts/{id}

### Description
Get a prompt by its UUID.

### Method
GET

### Endpoint
/api/v1/prompts/{id}

### Parameters
#### Path Parameters
- **id** (string) - Required - The unique identifier (UUID) of the prompt to retrieve.

#### Header Parameters
- **x-workspace-id** (string) - Optional - The workspace ID to specify the context for the request.

### Responses
#### Success Response (200)
- **id** (string) - The unique identifier of the prompt.
- **prompt_id** (string) - The ID of the prompt.
- **version** (integer) - The version of the prompt.
- **content** (string) - The content of the prompt.
- **tags** (array of strings) - Tags associated with the prompt.
- **created_at** (string) - The timestamp when the prompt was created.
- **updated_at** (string) - The timestamp when the prompt was last updated.

#### Error Response (422)
- **detail** (array of objects) - Contains details about validation errors.
```
Tokens:
Raw