FlyMy.AI Agents

Build and deploy autonomous AI agents on FlyMy.AI. Agents execute complex multi-step tasks in the cloud -- searching the web, processing files, calling APIs -- and deliver results without human intervention.

Two Ways to Use Agents

Build Agents for Yourself

Create agents that automate your workflows. Define a goal, equip the agent with tools, start a run, get results.

from flymyai import AgentClient

client = AgentClient(api_key="fly-***")

# Register tools first — each returns a Tool object with an integer .id
web_search = client.tools.create(mcp_tool="tavily")
browser = client.tools.create(mcp_tool="browser")

agent = client.agents.create(
    name="Competitor Monitor",
    goal="Track competitor pricing changes and alert me about significant shifts.",
    tools=[web_search.id, browser.id]
)

run = client.runs.create(agent_id=agent.id)

result = client.runs.wait(run.id)
print(result.output)

Planned Feature — Coming Soon

Publish Agents for Others

Build agents and publish them to the FlyMy.AI marketplace. Other users discover your agent, fill in an input form, and pay per run. You earn revenue from every execution.

Marketplace features -- including visibility, pricing, input_schema, output_schema, and client.agents.publish() -- are not yet available in the API. This section describes planned functionality.

# Planned API — not yet available
agent = client.agents.create(
    name="SEO Audit Agent",
    goal="""Perform a comprehensive SEO audit of {{ website_url }}.
    {{#if focus_areas}}Focus specifically on: {{#each focus_areas}}{{this}}, {{/each}}.{{/if}}
    Return structured findings with severity ratings and actionable recommendations.""",
    tools=[web_search.id, browser.id],
    input_schema={
        "type": "object",
        "properties": {
            "website_url": {
                "type": "string",
                "description": "Website URL to audit"
            },
            "focus_areas": {
                "type": "array",
                "items": {"type": "string"},
                "description": "Specific areas to focus on (e.g., performance, meta tags, mobile)"
            }
        },
        "required": ["website_url"]
    },
    output_schema={
        "type": "object",
        "properties": {
            "score": {"type": "number"},
            "issues": {
                "type": "array",
                "items": {
                    "type": "object",
                    "properties": {
                        "severity": {"type": "string", "enum": ["critical", "warning", "info"]},
                        "category": {"type": "string"},
                        "description": {"type": "string"},
                        "recommendation": {"type": "string"}
                    }
                }
            }
        }
    },
    visibility="public",
    pricing={"per_run": 0.50}
)

# Publish to marketplace
client.agents.publish(agent_id=agent.id)

When published, FlyMy.AI will automatically generate an input form at app.flymy.ai/agents/{your-agent} -- buyers fill it in, click "Run", and get results. No code required on their side.

Key Capabilities

Capability	Description
Autonomous Execution	Define a goal -- agent plans, executes, iterates until done
Handlebars Templating	Use {{ variable }} syntax in the goal for reusable, configurable agents
MCP Tools	Web search, news, browser, and more via client.tools.create(mcp_tool="...")
Real-Time Events	Stream every tool call and reasoning event via client.runs.stream_events()
Run Lifecycle	Runs progress through statuses: pending, running, completed, failed, cancelled

How It Works

┌─────────────────────────────────────────────────────────────┐
│                      FlyMy.AI Cloud                         │
│                                                             │
│  ┌───────────┐    ┌──────────┐    ┌────────────────────┐   │
│  │   Agent    │───>│  Runner  │───>│    MCP Tools       │   │
│  │  Config    │    │  Engine  │    │  tavily            │   │
│  │  (goal +   │    │          │    │  browser           │   │
│  │   tools)   │    │          │    │  github            │   │
│  └───────────┘    └──────────┘    │  slack, etc.       │   │
│       │                │          └────────────────────┘   │
│       │           ┌────v────┐                              │
│       │           │  Logs   │                              │
│       │           │ (Events)│                              │
│       │           └─────────┘                              │
│  ┌────v──────────────────────────────┐                     │
│  │        Execution Result           │                     │
│  │  status: completed / failed       │                     │
│  │  agent_result: { ... }            │                     │
│  └───────────────────────────────────┘                     │
└─────────────────────────────────────────────────────────────┘

Use Cases

Use Case	Personal	Marketplace
Research Assistant	Research topics for your team	Sell research-on-demand to anyone
SEO Auditor	Audit your own sites	Offer SEO audits as a service
Data Processor	Clean and transform your datasets	Provide data cleaning tools
Content Generator	Generate content for your brand	Sell content generation
Code Reviewer	Review your team's PRs	Offer code review as a service
Lead Profiler	Profile your sales leads	Sell lead intelligence

Next Steps

• Quickstart -- build and run your first agent in 5 minutes
• Tools & MCP -- add tools and external services