Ship AI agents
in days, not months
Three production-ready agent templates with shared infrastructure. Tool calling, memory, cost tracking, and evaluation — all wired up and ready to deploy.
Agent templates 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.
Customer Support
Knowledge base search, sentiment tracking, and automatic escalation to humans. Plug in your docs and go.
- → Knowledge base search
- → Sentiment analysis
- → Human escalation
- → Canned responses
Research Assistant
Multi-step research agent that searches, synthesizes, and produces structured reports with source citations.
- → Web search integration
- → Source extraction
- → Report generation
- → Citation tracking
Document Extraction
Extract structured data from PDFs, invoices, and contracts. Schema validation and confidence scoring built in.
- → PDF parsing
- → Schema validation
- → Confidence scores
- → Batch processing
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.
Read guide → conversation.py 203 lines Conversation Management
Message history with sliding window and automatic summarization. Keeps costs bounded without losing context.
Read guide → 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.
Read guide → 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.
Read guide → errors.py 169 lines Error Handling
Structured exceptions, Anthropic SDK error mapping, retry decorators with exponential backoff. Claude understands every failure.
Read guide →
eval/
harness + YAML Evaluation Framework
YAML test cases, automated harness, expected outputs, and budget assertions. Know when your agent breaks before your users do.
Read guide →Learn by building
In-depth tutorials that teach real patterns. Every guide builds toward the architecture in the starter kit.
Building Your First AI Agent with Claude
From zero to a working agent in 30 minutes. Tool calling, conversation management, and deployment.
Tool Calling Patterns That Actually Work
Registry pattern, Pydantic validation, timeout handling, and the retry strategies that matter in production.
Cost Tracking: The Feature You'll Wish You Built First
Per-conversation budgets, token logging, and the alerting system that prevents $500 surprise bills.
Evaluating AI Agents Without Losing Your Mind
YAML test cases, deterministic assertions, and the eval loop that gives you confidence to ship.
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
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
Team License
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
One-time purchase · Lifetime access · Secure checkout via Lemon Squeezy