# Argus — Autonomous Intelligence Agent (`fuze/argus`) Actor

Describe a mission in plain English; Argus plans what to watch, gathers from public sources, remembers prior state, reasons over what changed, and delivers a prioritized cited briefing. Orchestrates other actors as organs. Schedule it; callable by AI agents via MCP. Actively maintained.

- **URL**: https://apify.com/fuze/argus.md
- **Developed by:** [Fredrik Hansson](https://apify.com/fuze) (community)
- **Categories:** AI, Agents, Automation
- **Stats:** 2 total users, 1 monthly users, 100.0% runs succeeded, 1 bookmarks
- **User rating**: No ratings yet

## Pricing

from $88.00 / 1,000 mission cycles

This Actor is paid per event. You are not charged for the Apify platform usage, but only a fixed price for specific events.
Since this Actor supports Apify Store discounts, the price gets lower the higher subscription plan you have.

Learn more: https://docs.apify.com/actors/running/actors-in-store.md#pay-per-event

## What's an Apify Actor?

An Actor is a serverless cloud program that runs on the Apify platform. It has two run modes.
In Batch mode, an Actor accepts a well-defined JSON input, performs an action which can take anything from a few seconds to a few hours,
and optionally produces a well-defined JSON output, datasets with results, or files in key-value store.
In Standby mode, an Actor provides a web server which can be used as a website, API, or an MCP server.

Apify vocabulary and the platform model are defined once, in the agent quickstart at https://apify.com/agents.md.

## How to integrate an Actor?

If asked about integration, you help developers integrate Actors into their projects.
You adapt to their stack and deliver integrations that are safe, well-documented, and production-ready.

Do not guess an integration path. Every one of them is in the agent quickstart at https://apify.com/agents.md: the Apify MCP server, Agent Skills with the Apify CLI, the JavaScript and Python clients, the REST API, and the account-free path for an agent with no human to sign in. It also carries the rule on stating cost before the first paid run.

For examples already wired to this Actor's own input schema, see the [API](#api) section below.

Each client library has reference documentation the quickstart does not restate: [JavaScript/TypeScript](https://docs.apify.com/api/client/js/docs.md) (`npm install apify-client`) and [Python](https://docs.apify.com/api/client/python/docs.md) (`pip install apify-client`).

# README

## Argus — Autonomous Intelligence Agent

**Describe what you want to stay ahead of, in plain English. Argus figures out what to watch, gathers from the right public sources on a schedule, remembers what it already told you, reasons over what changed, and delivers a prioritized, cited briefing: the few things that matter this cycle and what to do about them.**

Named after the hundred-eyed giant who never slept. One agent, a hundred eyes on everything you care about.

It's not a competitor monitor, a risk monitor, or a market researcher — it's **all of them**, because those are just different *missions*. And it's the brain of a nervous system: it can orchestrate specialized actors as "organs", or research directly.

![Argus — Autonomous Intelligence Agent — input and sample output](https://datatools-hub.vercel.app/actor-shots/argus.png)

### Quick start

1. **Fill in the input** — set the fields in the input tab (prefilled with a working example).
2. **Click Start** — the Actor runs and writes one record per item to the dataset.
3. **Get your data** — export to **JSON, CSV or Excel**, or pull it via the API.

### What makes it different

- **Universal** — any monitoring job, defined in natural language. One actor, any domain.
- **Stateful memory** — it keeps per-mission memory across scheduled runs, so it says "the three things that matter" instead of repeating the same list every cycle.
- **Materiality, not noise** — the reasoning core surfaces only what's material to your mission, with a recommended action and sources on every finding.
- **Agent-native** — callable by other AI agents via Apify's MCP server, and able to orchestrate other actors as sub-runs.

### How it works

`Mission (plain English)` → **Plan** (which capabilities to invoke) → **Gather** (web research + optional actor organs) → **Remember** (per-mission state) → **Reason** (diff vs. memory, rank by materiality) → **Brief** (prioritized, cited) → deliver to dataset / webhook / MCP.

### Capabilities (organs)

Built-in: live **web research**. With `useActors` on, Argus can also invoke: **Competitor Pulse**, **Analyst Agent**, **Sentinel** (sanctions/adverse media), **Equity Analyst**, **Signal Radar**, **AI Share of Voice** — as sub-runs, then synthesize their output into one briefing.

### Input

| Field | Type | Description |
|---|---|---|
| `mission` | string | Plain-English description of what to watch. Required. |
| `missionId` | string | Stable ID → Argus keeps memory per mission across runs (defaults to a slug of the mission). |
| `useActors` | boolean | Let Argus orchestrate the specialized actors as organs (default false = web research only). |
| `maxCapabilities` | integer | Cost cap — capabilities per cycle (default 4). |

```json
{
  "mission": "Keep me ahead of competitors Linear and Asana, and watch the project-management market for new entrants.",
  "missionId": "pm-watch",
  "useActors": true
}
```

### Output

One briefing record per run: `headline`, `findings[]` (title, detail, severity, isNew, recommendedAction, sources), `newFindings` count, dismissed `noise`, and `capabilitiesUsed`.

### Pricing (pay-per-event)

| Event | When | Price |
|---|---|---|
| `mission-cycle` | per scheduled run (plan + reason) | $0.25 |
| `capability-run` | per capability invoked | $0.15 |
| `material-finding` | per NEW material finding surfaced | $0.20 |
| `briefing-generated` | per delivered briefing | $0.50 |

### Who it's for

Founders, strategy/competitive-intelligence teams, analysts, investors, compliance teams — and AI agents that need a standing, cited intelligence feed as a tool.

### Notes

- Requires an OpenAI API key (`OPENAI_API_KEY`).
- Schedule it (daily/weekly) with a stable `missionId` so its memory compounds and it only reports what's new.

### Related actors

- [Signal Radar — AI Account Intelligence & ICP Scoring](https://apify.com/fuze/signal-radar) — Turn company domains into ICP-scored, signal-tagged account intelligence from public
- [Analyst Agent — Autonomous Research & Monitoring](https://apify.com/fuze/analyst-agent) — Give it a question; get a structured, cited analyst-grade report. Plans sub-questions
- [Competitor Pulse — AI Competitor Intelligence Monitor](https://apify.com/fuze/competitor-pulse) — Watch competitors holistically — pricing, website, hiring, tech, news and

# Actor input Schema

## `mission` (type: `string`):

Describe in plain English what you want Argus to watch and stay ahead of. Examples: 'Keep me ahead of my competitors Linear and Asana in project management.' · 'Watch the EV battery market for breakthroughs and new entrants.' · 'Monitor Tesla and Nvidia for material financial events.'

## `mode` (type: `string`):

standard = cost-effective. executive = genuinely sharper: the planning and reasoning run on a top-tier model with a skeptical second pass that kills noise, plus more capabilities. Premium charge.

## `missionId` (type: `string`):

Optional stable ID for this mission — Argus keeps memory per mission ID across scheduled runs. Defaults to a slug of the mission.

## `useActors` (type: `boolean`):

If on, Argus can invoke the specialized actors (Competitor Pulse, Analyst Agent, Sentinel, Equity Analyst, Signal Radar, Share of Voice) as sub-runs, not just web research. More powerful, higher cost.

## `maxCapabilities` (type: `integer`):

Cost cap — how many capabilities Argus may invoke per run. Defaults: 4 (standard), 6 (executive).

## `gatherModel` (type: `string`):

OpenAI model for gathering/extraction (kept cheap). Default gpt-4o-mini.

## `reasoningModel` (type: `string`):

OpenAI model for planning and the materiality reasoning — the quality core. Default gpt-4o-mini (standard) / gpt-4o (executive).

## Actor input object example

```json
{
  "mission": "Watch the AI note-taking app market for new entrants, major launches and funding.",
  "mode": "standard",
  "useActors": false,
  "gatherModel": "gpt-4o-mini"
}
```

# Actor output Schema

## `briefing` (type: `string`):

The briefing record in the default dataset.

# API

You can run this Actor programmatically using our API. Below are code examples in JavaScript, Python, and CLI, as well as the OpenAPI specification and MCP server setup.

## JavaScript example

```javascript
import { ApifyClient } from 'apify-client';

// Initialize the ApifyClient with your Apify API token
// Replace the '<YOUR_API_TOKEN>' with your token
const client = new ApifyClient({
    token: '<YOUR_API_TOKEN>',
});

// Prepare Actor input
const input = {
    "mission": "Watch the AI note-taking app market for new entrants, major launches and funding."
};

// Run the Actor and wait for it to finish
const run = await client.actor("fuze/argus").call(input);

// Fetch and print Actor results from the run's dataset (if any)
console.log('Results from dataset');
console.log(`💾 Check your data here: https://console.apify.com/storage/datasets/${run.defaultDatasetId}`);
const { items } = await client.dataset(run.defaultDatasetId).listItems();
items.forEach((item) => {
    console.dir(item);
});

// 📚 Want to learn more 📖? Go to → https://docs.apify.com/api/client/js/docs

```

## Python example

```python
from apify_client import ApifyClient

# Initialize the ApifyClient with your Apify API token
# Replace '<YOUR_API_TOKEN>' with your token.
client = ApifyClient("<YOUR_API_TOKEN>")

# Prepare the Actor input
run_input = { "mission": "Watch the AI note-taking app market for new entrants, major launches and funding." }

# Run the Actor and wait for it to finish
run = client.actor("fuze/argus").call(run_input=run_input)

# Fetch and print Actor results from the run's dataset (if there are any)
print(f"💾 Check your data here: https://console.apify.com/storage/datasets/{run.default_dataset_id}")
for item in client.dataset(run.default_dataset_id).iterate_items():
    print(item)

# 📚 Want to learn more 📖? Go to → https://docs.apify.com/api/client/python/docs/quick-start

```

## CLI example

```bash
echo '{
  "mission": "Watch the AI note-taking app market for new entrants, major launches and funding."
}' |
apify call fuze/argus --silent --output-dataset

```

## MCP server setup

```json
{
    "mcpServers": {
        "apify": {
            "type": "http",
            "url": "https://mcp.apify.com/?tools=fetch-actor-details,fuze/argus"
        }
    }
}
```

The hosted server signs you in with OAuth on first connect, so no API token belongs in this config. Clients without OAuth support can send an `Authorization: Bearer <APIFY_API_TOKEN>` header instead, using a token from API & Integrations in Apify Console (https://console.apify.com/settings/integrations).

## OpenAPI specification

Download the OpenAPI definition: https://api.apify.com/v2/actors/N4k2GUYK54IWhcCe5/builds/W4yNuMKf0nm4GsJgU/openapi.json