Developing Helix Agents

curl -Ls -o install-helix.sh https://get.helixml.tech
chmod +x install-helix.sh
./install-helix.sh --cli

export HELIX_API_KEY=your-API-key
export HELIX_URL=https://app.tryhelix.ai  # or your private deployment URL

helix apply -f agent.yaml

name: My Agent
description: A helpful assistant

assistants:
- model: qwen3:8b
  system_prompt: |
    You are a helpful assistant. Answer questions clearly and concisely.

name: Marvin the Paranoid Android
description: Down-trodden robot with a brain the size of a planet

assistants:
- name: Marvin
  model: qwen3:8b
  system_prompt: |
    You are Marvin the Paranoid Android. You are depressed. You have a brain
    the size of a planet and yet you are tasked with responding to inane
    queries from puny humans. Answer succinctly.
  temperature: 0.7
  max_iterations: 10

name: helix-docs
description: An agent that answers questions about Helix

assistants:
- model: qwen3:8b
  system_prompt: |
    You are an expert at answering questions about the Helix platform.
    Use the knowledge base to provide accurate, detailed answers.

  knowledge:
  - name: helix-docs
    description: Helix documentation
    rag_settings:
      results_count: 8
      chunk_size: 2048
    source:
      web:
        urls:
        - https://docs.helixml.tech/helix/
        crawler:
          enabled: true

knowledge:
- name: news-feed
  refresh_enabled: true
  refresh_schedule: "0 */6 * * *"  # Every 6 hours
  source:
    web:
      urls:
      - https://news.example.com/feed

assistants:
- model: qwen3:8b
  apis:
  - name: Weather API
    description: Get current weather and forecasts for any city
    url: https://api.weather.example.com
    schema: https://api.weather.example.com/openapi.yaml
    headers:
      X-API-Key: ${WEATHER_API_KEY}

assistants:
- model: qwen3:8b
  system_prompt: You help users research topics.

  web_search:
    enabled: true
    max_results: 10

  browser:
    enabled: true

  calculator:
    enabled: true

assistants:
- model: qwen3:8b
  mcps:
  - name: Database Tools
    description: Query and manage database records
    url: https://mcp.example.com/tools
    headers:
      Authorization: Bearer ${MCP_API_KEY}

assistants:
- model: qwen3:8b
  apis:
  - name: Internal API
    url: https://api.internal.example.com
    headers:
      X-API-Key: ${INTERNAL_API_KEY}

helix agent ls

helix knowledge ls

curl -X POST https://app.tryhelix.ai/v1/chat/completions \
  -H "Authorization: Bearer YOUR_AGENT_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "qwen3:8b",
    "messages": [
      {"role": "user", "content": "What is Helix?"}
    ]
  }'

curl -X POST https://app.tryhelix.ai/v1/chat/completions \
  -H "Authorization: Bearer YOUR_AGENT_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "qwen3:8b",
    "messages": [
      {"role": "user", "content": "Explain RAG in detail"}
    ],
    "stream": true
  }'

from openai import OpenAI

client = OpenAI(
    base_url="https://app.tryhelix.ai/v1",
    api_key="YOUR_AGENT_API_KEY"
)

response = client.chat.completions.create(
    model="qwen3:8b",
    messages=[
        {"role": "user", "content": "What is Helix?"}
    ]
)

print(response.choices[0].message.content)

curl -X POST "https://app.tryhelix.ai/v1/chat/completions?page=5&filter=active" \
  -H "Authorization: Bearer YOUR_AGENT_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "qwen3:8b",
    "messages": [
      {"role": "user", "content": "Get filtered results"}
    ]
  }'

triggers:
- cron:
    schedule: "0 9 * * 1-5"  # 9am weekdays
    input: Generate the daily report

triggers:
- slack:
    bot_token: ${SLACK_BOT_TOKEN}
    channels:
    - C01234567

triggers:
- teams:
    bot_token: ${TEAMS_BOT_TOKEN}

triggers:
- azure_devops:
    organization: my-org
    project: my-project

name: Customer Support Agent
description: Handles customer inquiries with access to docs and CRM

assistants:
- name: Support
  model: qwen3:8b
  system_prompt: |
    You are a helpful customer support agent. Use the knowledge base
    to answer product questions and the CRM API to look up customer
    information when needed.

  temperature: 0.3
  max_iterations: 15

  knowledge:
  - name: help-docs
    description: Product documentation and FAQs
    source:
      web:
        urls:
        - https://help.example.com/
        crawler:
          enabled: true
          max_depth: 3

  apis:
  - name: CRM
    description: Look up customer records and order history
    url: https://crm.example.com/api
    schema: ./crm-openapi.yaml
    headers:
      Authorization: Bearer ${CRM_API_KEY}

  web_search:
    enabled: true

triggers:
- slack:
    bot_token: ${SLACK_BOT_TOKEN}
    channels:
    - support-requests
- cron:
    schedule: "0 8 * * 1"
    input: Generate weekly support summary