EODHD Discovery & Calendars

Overview

The discovery counterpart to eodhd_market_data — instead of pulling data for a known ticker, it helps the agent find tickers and look up scheduled events. Use it to search for a company by name, screen the universe by market cap or sector, or get the next month of earnings releases, IPOs, analyst-rating shifts, and macro data prints.

How it works

Wraps the EODHD discovery and calendar endpoints (/search, /screener, /calendar/earnings, /calendar/ipos, /calendar/trends, /economic-events). Input grammar is '<operation>[:<arg1>[:<arg2>[:<arg3>]]]'. The screener supports EODHD's JSON-array filter syntax, and the parser preserves brackets so filter expressions stay intact. Date arguments default to today → +30 days for forward calendars when omitted, so 'ipos' alone returns the next month of IPOs.

Example

When a user asks:

Show me earnings releases scheduled in the next two weeks for the US market.

the agent calls the tool:

eodhd_discovery(input="earnings:2026-04-26:2026-05-10")

and gets back: a markdown table of scheduled earnings with date, ticker, estimate, and surprise columns, tagged [EODHD: calendar/earnings].

Configuration

Set these before calling the tool. Values marked required must be present or the tool call will fail.

Use it in a workflow

Wire this tool into a SwarmAI crew. Use the YAML DSL for declarative workflows, or the Java builder API when you want full programmatic control.

YAML DSL

# event-radar.yaml
name: event-radar-crew
process: SEQUENTIAL

agents:
  - id: scout
    role: Event Radar Scout
    goal: Surface upcoming earnings, IPOs, and macro prints worth watching
    tools:
      - eodhd_discovery

tasks:
  - id: event-radar-task
    agent: scout
    description: Compile the next 14 days of earnings releases and the next 30 days of IPOs.

Java

import ai.intelliswarm.swarmai.agent.Agent;
import ai.intelliswarm.swarmai.task.Task;
import ai.intelliswarm.swarmai.swarm.Swarm;
import ai.intelliswarm.swarmai.swarm.SwarmOutput;
import ai.intelliswarm.swarmai.process.ProcessType;
import ai.intelliswarm.swarmai.tool.common.EodhdDiscoveryTool;
import org.springframework.ai.chat.client.ChatClient;
import org.springframework.beans.factory.annotation.Autowired;

@Autowired ChatClient chatClient;
@Autowired EodhdDiscoveryTool eodhdDiscoveryTool;

Agent scout = Agent.builder()
    .role("Event Radar Scout")
    .goal("Surface upcoming earnings, IPOs, and macro prints")
    .chatClient(chatClient)
    .tool(eodhdDiscoveryTool)
    .build();

Task scoutTask = Task.builder()
    .description("Compile the next 14 days of earnings releases and the next 30 days of IPOs.")
    .agent(scout)
    .build();

SwarmOutput result = Swarm.builder()
    .agent(scout)
    .task(scoutTask)
    .process(ProcessType.SEQUENTIAL)
    .build()
    .kickoff();

What it's good for

Real scenarios where agents put this tool to work.

Source

Implementation lives at swarmai-tools/src/main/java/ai/intelliswarm/swarmai/tool/common/EodhdDiscoveryTool.java in the swarm-ai repository.

Open eodhd_discovery on GitHub →