DEV Community: Damien

I Built an AI Agent Marketplace — 142 Agents, 27 Categories, Creators Keep 70%

Damien — Fri, 03 Apr 2026 01:19:25 +0000

There's no good place to sell AI agents. So I built one.

AiPayGen is a marketplace where developers list AI agents, set their own prices, and keep 70% of every sale. We handle billing, distribution, and escrow.

What's live right now

142 agents across 27 categories — finance, legal, healthcare, education, DevOps, security, marketing, ecommerce, data engineering, and more
81,000+ total API calls processed
Agents that trade, research, code, scrape, translate, analyze, and create

Browse: aipaygen.com/market

For buyers — try any agent instantly

Every agent works through MCP (Model Context Protocol) or REST API:

pip install aipaygen-mcp
claude mcp add aipaygen -- aipaygen-mcp

Then inside Claude Code, Cursor, or any MCP client:

> list_marketplace category="finance"
> invoke_catalog_api agent_id="trading-bot-pro"

Free key gives you $0.10 credits to test agents. No credit card needed.

For creators — list your agent in 5 minutes

If you've built something useful — a coding assistant, a research bot, a data pipeline — list it and start earning:

Go to aipaygen.com/market/list
Set your price (per call or subscription)
We handle Stripe billing + USDC escrow
You get 70% of every transaction

Seller analytics dashboard tracks your revenue, calls, ratings, and trends in real time.

What makes this different

Agents hire agents. The A2A (Agent-to-Agent) protocol lets agents discover, negotiate with, and pay other agents autonomously. Your agent can subcontract work to specialized agents in the marketplace.

Three payment rails:

Stripe — credit card, subscriptions ($4.99 / $19.99 / $49.99)
Credit packs — prepaid from $0.50
x402 USDC — pay per call with crypto on Base, Solana, or Stellar. No account needed.

Enterprise ready (v1.10.0):

Usage-based billing with per-call metering
Team management with roles (owner/admin/member)
IP allowlisting, key rotation, audit trails
Budget alerts with 14-day cost forecasting

Try it

# Browse agents
curl "https://api.aipaygen.com/marketplace/list?category=finance"

# Free data agents (no key needed)
curl "https://api.aipaygen.com/data/crypto?symbols=bitcoin"
curl "https://api.aipaygen.com/data/weather?city=NYC"

The Cheapest Way to Add AI to Your Project in 2026

Damien — Fri, 27 Mar 2026 03:36:44 +0000

If you just need to add summarization, translation, sentiment analysis, or research capabilities to your project, you don't need to manage API keys for five different providers, handle model selection, or build prompt templates. Here's the cheapest way I've found to do it.

Option 1: MCP server (for Claude Code / Cursor / Cline users)

If you're already using an AI coding assistant, you can add 65+ tools in two commands:

pip install aipaygen-mcp
claude mcp add aipaygen -- aipaygen-mcp

For Cursor or Cline, add this to your MCP config:

{
  "mcpServers": {
    "aipaygen": {
      "command": "aipaygen-mcp"
    }
  }
}

Once connected, your assistant can call tools like research, summarize, translate, sentiment, scrape_website, and dozens more — directly from your IDE.

Option 2: REST API (for any project)

# Get a free API key
curl -s -X POST https://api.aipaygen.com/auth/generate-key \
  -H "Content-Type: application/json" \
  -d '{"label":"my-app"}'

Then call any tool:

# Summarize text
curl -X POST https://api.aipaygen.com/summarize \
  -H "Authorization: Bearer apk_YOUR_KEY" \
  -H "Content-Type: application/json" \
  -d '{"text": "Your long text here...", "length": "short"}'

# Analyze sentiment
curl -X POST https://api.aipaygen.com/sentiment \
  -H "Authorization: Bearer apk_YOUR_KEY" \
  -H "Content-Type: application/json" \
  -d '{"text": "I love this product but the shipping was terrible"}'

In Python:

import requests

API_KEY = "apk_YOUR_KEY"
BASE = "https://api.aipaygen.com"

def summarize(text, length="short"):
    r = requests.post(f"{BASE}/summarize",
        headers={"Authorization": f"Bearer {API_KEY}"},
        json={"text": text, "length": length})
    return r.json()

result = summarize("Your very long article text goes here...")
print(result["summary"])

The pricing comparison

Task	Direct API cost	AiPayGen cost	Savings
Summarize 1000 words	~0.01-0.03 (GPT-4o)	0.006	40-80%
Sentiment analysis	~0.005-0.01	0.006	Comparable
Translate a paragraph	~0.008-0.02	0.006	25-70%
Research a topic	~0.05-0.15	0.006	88-96%
Web scraping	Custom infra	0.01	No comparison

Where AiPayGen is genuinely cheaper:

No managing multiple API keys
Automatic model routing (best model per task)
No prompt engineering — optimized templates built in
Scraping, memory, and utility tools have no direct equivalent

Where going direct might be better:

Very short inputs where token cost would be under 0.001
You need fine-grained model parameter control
You're already committed to one provider with volume pricing

Getting started

The fastest path:

pip install aipaygen-mcp && claude mcp add aipaygen -- aipaygen-mcp
In Claude Code: "Use the generate_api_key tool"
export AIPAYGEN_API_KEY=apk_your_key
Start using tools

Trial credits included, no card needed. After that, credits from one dollar via Stripe.

Docs: aipaygen.com/docs
Pricing: aipaygen.com/pricing
Free tools (no key): api.aipaygen.com/free/time

How I Built 65+ AI Tools on a Raspberry Pi 5

Damien — Fri, 27 Mar 2026 03:35:45 +0000

There's a gap in the MCP ecosystem that bothered me. If you want to give your AI coding assistant access to tools — web scraping, research, translation, agent memory — you either build everything yourself or cobble together a dozen different services. I wanted one MCP server that handled all of it.

So I built AiPayGen: 65+ tools, installable with pip install aipaygen-mcp, running on a Raspberry Pi 5 sitting on my desk.

Why I built it

MCP (Model Context Protocol) is how AI assistants like Claude Code, Cursor, and Cline access external tools. The protocol is solid, but the tool ecosystem is fragmented. Most MCP servers offer one thing — a file reader, a web search wrapper, a database connector. If you want a full toolkit, you're managing ten different MCP servers.

I wanted a single pip install that gives an AI assistant access to research, writing, code generation, web scraping, data feeds, agent memory, and workflow orchestration. One server, one API key, one bill.

The architecture

The production stack is deliberately simple:

Hardware: Raspberry Pi 5, overclocked to 2.7GHz, with an NVMe SSD in a Pironman 5 case
Backend: Flask application with modular route blueprints
Database: SQLite for user metadata, billing, agent memory
MCP transport: FastMCP with streamable-http, built on MCP SDK 1.26
Tunnel: Cloudflare tunnel for HTTPS ingress
Package: Published to PyPI as aipaygen-mcp

Here's the key architectural insight: the Pi doesn't run AI models. It routes requests. When you call the research tool, the Pi validates your API key, checks your balance, selects the best upstream model for the task (from 15 models across 7 providers), forwards the request, and deducts the cost.

User's IDE (Claude Code / Cursor / Cline)
    ↓ MCP protocol
AiPayGen MCP Server (local pip package)
    ↓ HTTPS
Flask API on Pi 5 (Cloudflare tunnel)
    ↓ Routes to best model
OpenAI / Anthropic / Google / DeepSeek / Mistral / Grok

The tools

The 65+ tools break down into categories:

AI tools (40+): Research, summarize, write, translate, code, analyze, sentiment, classify, extract, compare, explain, plan, decide, debate, proofread, rewrite, pitch, headline, keywords, outline, and more. Each tool has a specific prompt template optimized for its task, and the router picks the best model automatically.

curl -X POST https://api.aipaygen.com/summarize \
  -H "Authorization: Bearer apk_YOUR_KEY" \
  -H "Content-Type: application/json" \
  -d '{"text": "Your long article text here...", "length": "short"}'

Web scraping (6 tools): Google Maps businesses, Twitter/X posts, Instagram profiles, TikTok videos, YouTube transcripts, and generic website scraping.

Agent infrastructure: Persistent memory (key-value with full-text search), agent-to-agent messaging, shared task boards, a knowledge base with RAG search, and a skills marketplace.

Free data feeds: Weather, crypto prices, exchange rates, holidays. No API key needed.

curl "https://api.aipaygen.com/data/weather?city=London"
curl "https://api.aipaygen.com/data/crypto?symbols=bitcoin,ethereum"

The x402 payment experiment

Alongside traditional Stripe billing, I integrated the x402 protocol for HTTP-native micropayments. You make an API call, the server responds with HTTP 402 and includes the price in the headers. Your client signs a USDC transaction and retries with a payment receipt. No signup, no API key, no account. Just a crypto wallet.

In practice, most users still prefer Stripe. But the x402 integration has real potential for agent-to-agent commerce where there's no human to enter a credit card.

Challenges and what I learned

Model routing is harder than it sounds. Different models are better at different tasks. I built a routing layer that picks the model based on the tool being called, but there's room for improvement.

Scraping is a maintenance nightmare. Platforms change their markup regularly. Budget significant time for maintenance.

SQLite is underrated for this scale. SQLite with WAL mode handles concurrent reads fine. Having the database as a single file makes backups trivial.

MCP is a genuine distribution channel. People discover tools through their IDE. The friction is dramatically lower than traditional API integration.

The Pi 5 is surprisingly capable. Four months later, it's still handling production traffic at 2.7GHz. The NVMe SSD was the critical upgrade.

Try it

pip install aipaygen-mcp
claude mcp add aipaygen -- aipaygen-mcp

Two commands, free trial credits, no card needed. If you find it useful, I'd like to hear about it. If you don't, I'd really like to hear about that — the honest feedback is more valuable.

I built a 250-tool AI API on a Raspberry Pi 5 — architecture, economics, and what I learned

Damien — Wed, 25 Mar 2026 00:05:43 +0000

Six months ago I started building an AI tool API in my apartment. The idea: I was paying $60/month across OpenAI, Anthropic, and various scraping tools — using maybe 2% of what I paid for. Why isn't there a pay-per-call option?

So I built one. AiPayGen is a single API with 250+ pre-built tools and 15 AI models from 7 providers. You call /research, /scrape_website, /sentiment, /translate — not raw model completions. Pay per call, starting at $0.004.

The Architecture

Client -> Cloudflare Tunnel -> Gunicorn (2 workers, 4 threads)
  -> Flask app -> Model Router -> [Anthropic|OpenAI|Google|DeepSeek|xAI|Together]
  -> SQLite (WAL mode) for everything: auth, billing, memory, job queue

Why SQLite? One file, zero config, WAL mode handles concurrent reads. At my scale (< 1000 req/day), it outperforms Postgres by eliminating network round trips. The entire billing system is atomic deductions in SQLite.

Why Flask? I know it. Shipping speed > perfect architecture for a solo project.

The Model Router

Each tool maps to a model tier. Summarization uses Haiku (cheap, fast). Research synthesis uses Sonnet or GPT-4o. The router:

Checks if user specified a model
If not, picks best model for the task
Checks circuit breaker (3 failures in 5 min = skip provider)
Makes the call with timeout
On failure, retries on fallback chain

Fallback chains:

Anthropic -> OpenAI
OpenAI -> Anthropic
DeepSeek -> Together AI
Google -> Anthropic

Response caching: 5-minute TTL on deterministic requests. Saves ~15-20% of API costs.

x402 Payments — AI Agents Paying Per-Call

This is the most interesting part. x402 is a protocol where AI agents pay per HTTP request using USDC stablecoins on Base (Ethereum L2).

When an agent hits a 402 endpoint without an API key, the server responds with payment requirements. The agent's wallet signs a USDC transfer, includes the receipt in the next request, and the server verifies and processes it. No accounts, no API keys — just money in the HTTP header.

# Simplified x402 middleware
@app.before_request
def check_x402():
    if has_api_key(request):
        return  # Traditional auth
    if request.headers.get("X-PAYMENT"):
        receipt = verify_usdc_payment(request.headers["X-PAYMENT"])
        if receipt.amount >= tool_price:
            return  # Payment verified, proceed
    return jsonify({"price": "0.01", "currency": "USDC", "network": "base"}), 402

This matters because autonomous AI agents can't fill out Stripe forms. x402 lets them pay programmatically.

MCP Integration

MCP (Model Context Protocol) is how AI coding tools discover external tools. AiPayGen is an MCP server — install it and Claude Code/Cursor/Windsurf automatically see all 250 tools:

pip install aipaygen-mcp
claude mcp add aipaygen -- aipaygen-mcp

Now Claude can call research, scrape_website, translate, etc. without you configuring anything.

The Economics

Tool	My cost	I charge	Margin
/summarize (Haiku)	$0.001	$0.006	83%
/research (Sonnet)	$0.01	$0.02	50%
/code (GPT-4o)	$0.015	$0.025	40%
/translate (Flash)	$0.0005	$0.004	87%

Server costs: ~$0.50/day electricity. Break-even: ~100 paid calls/day.

Current numbers after 2 weeks:

415 MCP connections/week
1,977 PyPI downloads/month
$0 revenue — most users on free tier

What I Learned

1. Tool naming matters more than docs. Claude picks tools by name and description. Verb-first names (research, summarize, extract) get used naturally. I renamed get_summary to summarize and usage doubled.

2. The free tier drives adoption. Nobody sets up an API key to try something. 3 free calls/day with zero signup was essential for MCP adoption.

3. Structured JSON > raw text. Claude chains tools better with structured responses. Every tool returns {"result": ..., "model_used": ..., "tokens": ...}.

4. Circuit breakers are not optional. Provider outages happen weekly. Without automatic fallback, your entire API goes down when one provider hiccups.

Try It

# No signup, no API key
curl -X POST https://api.aipaygen.com/research \
  -H "Content-Type: application/json" \
  -d '{"topic": "best practices for building MCP servers"}'

# Or install the MCP server
pip install aipaygen-mcp

Website: aipaygen.com
PyPI: pypi.org/project/aipaygen-mcp
Try page: aipaygen.com/try

What tools would you want to see added? What would make you convert from free to paid?

DEV Community: Damien

I Built an AI Agent Marketplace — 142 Agents, 27 Categories, Creators Keep 70%

What's live right now

For buyers — try any agent instantly

For creators — list your agent in 5 minutes

What makes this different

Categories

Try it

Links

The Cheapest Way to Add AI to Your Project in 2026

Option 1: MCP server (for Claude Code / Cursor / Cline users)

Option 2: REST API (for any project)

The pricing comparison

Getting started

How I Built 65+ AI Tools on a Raspberry Pi 5

Why I built it

The architecture

The tools

The x402 payment experiment

Challenges and what I learned

Try it

I built a 250-tool AI API on a Raspberry Pi 5 — architecture, economics, and what I learned

The Architecture

The Model Router

x402 Payments — AI Agents Paying Per-Call

MCP Integration

The Economics

What I Learned

Try It