airesearchos

# AIresearchOS

Deep research API — submit queries, track progress, retrieve full reports with sources.

## Authentication Detection

Before any research operation, determine the auth method:

```bash
# Check API key first (preferred)
if [ -n "$AIRESEARCHOS_API_KEY" ]; then
  echo "api_key"
# Then check x402 wallet
elif [ -n "$AIRESEARCHOS_WALLET_KEY" ]; then
  echo "x402"
else
  echo "unconfigured"
fi
```

- **api_key** → Use `/api/v1/` endpoints with `Authorization: Bearer $AIRESEARCHOS_API_KEY`
- **x402** → Use `/api/x402/` endpoints via `{baseDir}/scripts/x402-request.mjs`
- **unconfigured** → Present setup options (see below)

### If Unconfigured

Present this to the user:

> To use AIresearchOS, you need to set up authentication.
>
> **Option 1: API Key** (recommended for regular use)
> - Sign up at https://airesearchos.com
> - Go to Dashboard → Settings → Generate API Key
> - Add to `~/.openclaw/openclaw.json`:
>   `skills.entries.airesearchos.apiKey = "aro_sk_..."`
> - Start a new OpenClaw session
>
> **Option 2: x402 Pay-Per-Request** (no account needed)
> - Pay with USDC stablecoins per request
> - Scan: $0.50 | Due Diligence: $1.50 | Mission Critical: $5.00
> - Run: `cat {baseDir}/SETUP.md` for full x402 setup guide
>
> Which would you prefer?

## Research Modes

| Mode | API Key Credits | x402 Cost | Depth/Breadth | Sources | Best For |
|------|----------------|-----------|---------------|---------|----------|
| `scan` | 10 credits | $0.50 USDC | 2/2 | 10-20 | Quick validation |
| `dueDiligence` | 25 credits | $1.50 USDC | 3/3 | 50-100 | Decision-grade analysis |
| `missionCritical` | 100 credits | $5.00 USDC | 5/5 | 150-300+ | Exhaustive coverage |

Report lengths: `concise`, `standard` (default), `extended`.

**Confirm with user before:** Mission Critical (100 credits / $5.00), any x402 payment.

## Workflows

### Submit Research (API Key)

```bash
curl -s -X POST "${AIRESEARCHOS_BASE_URL:-https://airesearchos.com}/api/v1/research" \
  -H "Authorizatio...

# AIresearchOS Deep Research Skill for OpenClaw

## The Problem with AI Research

ChatGPT checks 3-10 sources and gives you a summary. Perplexity gives you slightly better summaries. Neither produces research deep enough for your AI agent to make an informed decision on your behalf — and if the input is shallow, the output will be too. If your agent's research can't survive scrutiny, its recommendations are just guesses with formatting.

## What AIresearchOS Does Differently

[AIresearchOS](https://airesearchos.com) runs **iterative deep research** — not a single search pass, but multiple rounds of follow-up searches and source analysis across 100-300+ sources. The output is a structured, cited report: executive summary, competitive landscape, market sizing, pricing signals, risks, and a full source appendix. Every claim is traceable.

In independent blind evaluations by Grok, AIresearchOS scored **9.0/10** — beating ChatGPT (5.7), Gemini (7.5), and Perplexity (7.5) on the same prompts. Zero red flags vs. 3-4 for competitors. ([Verify the evaluation yourself](https://grok.com/share/c2hhcmQtMw_d1d5516c-2320-43cf-bb57-1501cc1a9856))

It runs on open-source AI models. No content policies, no invisible guardrails, no corporate filters shaping your results.

## Why This Matters for Your Agent

This skill turns your OpenClaw assistant into a research analyst. Instead of you going to a website, typing a query, and waiting — you just tell your assistant what you need in natural language, from any channel you're already using (WhatsApp, Telegram, Slack, Discord, or the TUI). It handles the submission, monitors progress in the background, and delivers the full report directly to your conversation when it's ready.

Your assistant can also answer clarifying questions the research engine asks to sharpen results, check your credit balance, and pull up past reports — all conversationally.

## What This Skill Does

- **Submit research** on any topic across three depth levels
- **Ba...