GitHub

anth-rate-limits

The Claude API uses token-bucket rate limiting measured in three dimensions: requests per minute (RPM), input tokens per...

by jeremylongshore

github

anth-reference-architecture

Three validated architecture patterns for Claude API integrations: synchronous API gateway, async queue-based processing...

by jeremylongshore

github

anth-policy-guardrails

Implement application-level guardrails for Claude API: input validation, output filtering, topic restrictions, and cost ...

by jeremylongshore

github

anth-observability

Instrument Claude API calls with structured logging, Prometheus metrics, and cost tracking. Every API response includes ...

by jeremylongshore

github

anth-performance-tuning

Optimize Claude API latency and throughput via prompt caching, model selection, streaming, and request optimization. The...

by jeremylongshore

github

anth-multi-env-setup

Configure isolated Claude API environments with per-env API keys, model selection, and spend controls using Anthropic Wo...

by jeremylongshore

github

anth-local-dev-loop

Set up a fast local development cycle for Claude API projects with environment management, request logging, cost trackin...

by jeremylongshore

github

anth-migration-deep-dive

Migration strategies for switching to Claude from OpenAI, Google, or other LLM providers, including API mapping, prompt ...

by jeremylongshore

github

anth-load-scale

Capacity planning and load testing for Claude API integrations. Key constraint: your rate limits (RPM/ITPM/OTPM) are the...

by jeremylongshore

github

anth-install-auth

Set up the official Anthropic SDK for Python or TypeScript and configure API key authentication. The SDK wraps the Claud...

by jeremylongshore

github

anth-known-pitfalls

from anthropic import AnthropicClient # Does not exist import anthropic client = anthropic.Anthropic() // WRONG import ...

by jeremylongshore

github

anth-incident-runbook

| Severity | Condition | Response Time | |----------|-----------|---------------| | P1 | API returning 500/529 for all r...

by jeremylongshore

github

anth-enterprise-rbac

Anthropic provides organization-level access control through Workspaces, API key scoping, and member roles via the Conso...

by jeremylongshore

github

anth-hello-world

Three minimal examples covering the Claude Messages API core surfaces: basic text completion, vision (image analysis), a...

by jeremylongshore

github

anth-deploy-integration

Deploy Claude API integrations with proper secret management, health checks, and rollback procedures across Docker, GCP ...

by jeremylongshore

github

anth-cost-tuning

Optimize Claude API spend through model routing, prompt caching, the Message Batches API, and real-time cost tracking. T...

by jeremylongshore

github

anth-data-handling

Anthropic's data policies: API inputs/outputs are NOT used for model training (commercial API). Zero-day retention is av...

by jeremylongshore

github

anth-core-workflow-b

Two complementary patterns: real-time streaming for interactive UIs (SSE events via POST /v1/messages with stream: true)...

by jeremylongshore

github

anth-ci-integration

Set up CI/CD pipelines that validate Claude API integrations with mock-based unit tests (free, fast) and prompt regressi...

by jeremylongshore

github

anth-core-workflow-a

Implement Claude's tool use capability where the model can call functions you define. Claude returns tooluse content blo...

by jeremylongshore

github

anth-architecture-variants

Four validated architecture patterns for Claude API integrations at different scales and use cases. import anthropic imp...

by jeremylongshore

github

anth-advanced-troubleshooting

import anthropic client = anthropic.Anthropic() count = client.messages.counttokens( model="claude-sonnet-4-20250514", m...

by jeremylongshore

github

retellai-policy-guardrails

Implementation patterns for Retell AI policy guardrails — voice agent and telephony platform. Completed retellai-install...

by jeremylongshore

github

explaining-machine-learning-models

Interpret machine learning model predictions using SHAP, LIME, and feature importance analysis to explain model behavior...

by jeremylongshore

github