3 templates · 5 core modules · 1,180+ lines of production Python

The AI Agent
Starter Kit

Three complete agent templates, shared production infrastructure, and an evaluation framework. Built on the Anthropic SDK — no frameworks, no magic, just clean Python you actually own.

One-time purchase from €79 · 30-day money-back guarantee

WHAT'S INSIDE

Three agents that actually ship

Each template is a complete, tested agent with its own tools, config, and evaluation suite. Fork one and customize, or compose pieces from several.

Most popular
💬

Customer Support

Knowledge base search, sentiment tracking, and automatic escalation to humans. Plug in your docs and go.

  • Knowledge base search with semantic retrieval
  • Sentiment analysis per message
  • Automatic human escalation rules
  • Canned response templates
  • Conversation summarization on handoff
Complex workflows
🔍

Research Assistant

Multi-step research agent that searches, synthesizes, and produces structured reports with source citations.

  • Web search with multiple providers
  • Source extraction and deduplication
  • Structured report generation
  • Citation tracking with confidence scores
  • Iterative refinement loop
High demand
📄

Document Extraction

Extract structured data from PDFs, invoices, and contracts. Schema validation and confidence scoring built in.

  • PDF and image parsing pipeline
  • Pydantic schema validation
  • Per-field confidence scores
  • Batch processing with progress tracking
  • Custom extraction templates
SHARED INFRASTRUCTURE

The boring parts, done right

Every agent shares a core/ layer of production infrastructure. Thin wrappers over the Anthropic SDK — no framework bloat, no magic, just clean Python.

tools.py 337 lines

Tool Calling

Registry pattern with schema validation, retries, timeouts, and formatted results. Register tools with decorators or Pydantic models.

conversation.py 203 lines

Conversation Management

Message history with sliding window and automatic summarization. Keeps costs bounded without losing context.

cost_tracker.py 230 lines

Cost Tracking

Per-call and per-conversation budgets, automatic pricing lookup, CSV/JSON export. The #1 thing teams wish they'd built earlier.

memory.py 241 lines

Three-Tier Memory

Short-term, session, and long-term (SQLite) storage. Simple key-value API with TTL support and namespace scoping.

errors.py 169 lines

Error Handling

Structured exceptions, Anthropic SDK error mapping, retry decorators with exponential backoff. Claude understands every failure.

eval/ harness + YAML

Evaluation Framework

YAML test cases, automated harness, expected outputs, and budget assertions. Know when your agent breaks before your users do.

CODE PREVIEW

Clean code you actually understand

No decorator soup. No framework magic. Register a tool, pass it to an agent, track the cost. That's the whole API.

agents/customer_support.py
from core.tools import ToolRegistry
from core.cost_tracker import CostTracker

registry = ToolRegistry("support-agent")
tracker = CostTracker(budget_usd=1.00)

@registry.tool
def search_knowledge_base (query: str) -> list[dict]:
"""Search the knowledge base for relevant articles."""
return kb.search(query, top_k=5)

# That's it. Schema validation, retries, and
# formatted results are handled automatically.
response = await agent.run(
"How do I reset my password?",
tools=registry,
cost_tracker=tracker,
)

print(tracker.total_cost) # $0.0023
FAQ

Common questions

Everything you need to know before buying.

What Python version do I need? +

Python 3.11 or higher. The kit uses modern Python features like type hints, match statements, and async/await throughout. We recommend 3.12 for the best experience.

Do I need LangChain or any other framework? +

No. The kit is built directly on the Anthropic SDK with zero framework dependencies. That's the whole point — thin wrappers, no magic, no abstraction layers you'll need to fight later.

How do updates work? +

You get access to a private GitHub repository. Solo licenses include 6 months of updates, Team licenses include 12 months. After that, you keep everything you have — you just won't receive new commits.

Can I use this for commercial projects? +

Yes. Both licenses allow full commercial use. You can build products, internal tools, and client projects with the kit. The only restriction is you can't resell the kit itself as a template or boilerplate.

What if I want a refund? +

30-day money-back guarantee, no questions asked. If the kit isn't what you expected, email us and we'll refund you immediately.

Do I need an Anthropic API key? +

Yes. The kit is built for Claude via the Anthropic SDK. You'll need an API key from console.anthropic.com. The cost tracker module helps you keep API spend under control from day one.

PRICING

One purchase. No subscriptions.

Pay once, own it forever. Both plans include the full kit with all three agent templates and shared infrastructure.

Solo Developer

€79 one-time

Everything you need to build and ship AI agents on your own.

  • 3 agent templates (support, research, extraction)
  • Shared core infrastructure
  • Evaluation framework + test cases
  • FastAPI endpoints + Docker config
  • 6 months of updates via GitHub
  • Email support
Get Solo License
Best value

Team License

€149 one-time · up to 5 devs

For teams shipping agents together. Same kit, shared access.

  • Everything in Solo, plus:
  • Up to 5 developer seats
  • 12 months of updates via GitHub
  • Priority email support
  • Team onboarding call (30 min)
  • Private Discord channel
Get Team License

30-day money-back guarantee · No questions asked · Secure checkout via Lemon Squeezy

NEWSLETTER

Get agent-building tips every week

Practical patterns, production gotchas, and new guide announcements. No spam, no AI hype — just things that help you ship.

Join 0 developers · Unsubscribe anytime