LLM App Dev — AI Agents, Skills & Tools
Agents, skills, guides, tools, and commands for llm app dev — 45 curated resources for building with AI coding agents.
LLM Integration Engineer
Use this agent to add an LLM feature to an application and make it production-grade — typed/structured output, streaming, provider fallback and retries, caching, and cost/latency controls. Examples — "add an AI summary endpoint to our app", "our LLM calls return unparseable JSON and break, make them reliable", "add streaming and a fallback provider to our chat feature".
LLM Output Schema Generator
Turn an example of the data you want from an LLM into a precise, validated output schema (Pydantic / Zod / JSON Schema) and wire it into structured-output calls. Use when adding typed LLM output, replacing brittle JSON parsing, or designing an extraction shape.
Provider Fallback Wrapper
Wrap LLM calls so a provider outage, rate limit, or timeout degrades gracefully — with multi-provider fallback, bounded retries with backoff, and timeouts. Use when an app depends on a single model/provider and needs production resilience.
Model Router Designer
Design a model router that sends each LLM request to the cheapest model that can handle it and escalates only the hard cases to the strongest — cutting cost and latency without tanking quality, gated by an eval set so the savings don't come from silently worse answers. Use when one expensive model serves all traffic (most of it easy), when LLM cost or latency is too high, or when balancing quality against spend across a range of request difficulty.
Semantic Cache Designer
Design a semantic cache for LLM responses — serve a cached answer when a new query is similar enough to a past one — to cut cost and latency on repetitive traffic, with the similarity threshold calibrated on real query pairs and a cache key that prevents cross-user/model leaks. Use when an LLM app sees many near-duplicate prompts (FAQs, support, search), when token spend on repetitive queries is high, or when latency on common questions matters.
Token Usage Profiler
Measure and attribute LLM token usage and cost across an app — input vs output tokens by feature, route, model, and tenant — then rank the waste and the specific lever to cut it. Use when LLM spend is high or climbing with no clear cause, before scaling a feature that calls a model, or when you need per-feature or per-tenant cost attribution for billing or budgets.
LLM API Pricing in 2026: Every Major Model Compared
Per-million-token prices for Claude, GPT, Gemini, DeepSeek, Mistral, and Grok — plus caching and batch discounts — verified against vendor pricing pages.
LLM Context Windows Compared (2026)
Context windows and max output tokens across Claude, GPT, Gemini, DeepSeek, and Grok — the million-token era, what it costs, and what fits in practice.
LiteLLM vs OpenRouter: One API for Every Model (2026)
LiteLLM vs OpenRouter compared — self-hosted gateway library vs hosted model marketplace. Keys, billing, control, and which unified LLM layer fits.
Calling Any Model: Unified LLM Gateways & SDKs in 2026
Why teams put a unified layer in front of LLM providers — and how LiteLLM, OpenRouter, and the Vercel AI SDK compare for fallback and cost control.
Structured Output vs JSON Mode vs Function Calling: Which to Use in 2026
The reliable ways to get typed data out of an LLM — what JSON mode, function calling, and native structured outputs each guarantee, and when to use which.
Claude's Document Skills: Excel, PowerPoint, Word, and PDF
How Anthropic's pre-built document skills let Claude produce real .xlsx, .pptx, .docx, and PDF files — on claude.ai, the API, and in Claude Code.
Claude Skills on claude.ai and the API
How Agent Skills work beyond Claude Code: uploading to claude.ai, the /v1/skills API with code execution, Managed Agents, and the Agent SDK.
Add Image Understanding to Your App
A practical guide to sending images to a vision model and getting reliable, structured results: base64 vs URL, resolution, prompting, cost, and errors.
How to Build a Voice Agent: The STT → LLM → TTS Pipeline
How to build a real-time voice agent: the STT → LLM → TTS pipeline, the latency budget that makes or breaks it, and how to wire each stage.
Agno
A Python framework for building multi-agent systems with memory, knowledge, and tools — formerly Phidata, now with the AgentOS runtime.
BAML
A domain-specific language for type-safe LLM functions, with generated clients and schema-aligned parsing.
Baseten
Production inference platform for ML and LLM models — autoscaling GPU deployments, scale-to-zero, and packaging via the open-source Truss framework.
Dify
The visual platform for LLM apps and agentic workflows — canvas-built chatflows, RAG pipeline, agent nodes with 50+ tools, and LLMOps, self-hosted via Docker.
Fireworks AI
Fast production inference for open models — serverless and dedicated GPU deployments, fine-tuning, and an OpenAI-compatible API on the FireAttention engine.
Flowise
Open-source, low-code visual builder for LLM apps and AI agents — drag-and-drop to assemble chains, agents, and RAG; self-host or use Flowise Cloud.
Google ADK
Google's open-source, code-first framework to build, evaluate, and deploy AI agents. Python and Java, model-agnostic, deploys to Vertex AI Agent Engine.
Groq
GroqCloud runs open-weight LLMs on custom LPU hardware for very fast, low-latency inference through an OpenAI-compatible API.
Instructor
Get structured, validated output from LLMs using plain type definitions, with automatic retries on validation failure.
LiteLLM
Call 100+ LLM APIs with one OpenAI-format interface — as a Python library or a self-hosted gateway/proxy.
LlamaParse
Hosted document-parsing API from LlamaIndex that turns complex PDFs — tables, charts, figures, handwriting — into clean, LLM-ready Markdown for RAG.
Mastra
An open-source TypeScript framework for building AI agents, workflows, RAG, and tool-calling, with memory, model routing, and built-in observability.
OpenRouter
A hosted unified API to hundreds of models from many providers, with one key, one bill, and automatic fallbacks.
Replicate
Run and deploy any open ML model — LLMs, image, video, audio — through one API with pay-per-second billing, and package your own with open-source Cog.
Together AI
A cloud for running, fine-tuning, and deploying open-source models (Llama, DeepSeek, Qwen) via an OpenAI-compatible API plus dedicated GPU endpoints.
Vercel AI SDK
An open-source TypeScript toolkit for building AI apps — unified model API, streaming, structured output, tool calling, and UI hooks.
Add a Streaming LLM Endpoint
Scaffold a token-streaming LLM endpoint — server-side streaming plus the client handler — so responses render incrementally instead of after a long wait.
Scaffold RAG Pipeline
Scaffold a Retrieval-Augmented Generation pipeline — ingestion (load, chunk, embed, upsert) and retrieval (search, rerank, grounded prompt with citations) — fitted to the project's stack.
Batch Inference
Batch inference processes many LLM requests asynchronously instead of one-at-a-time interactively — typically at ~50% discount via provider batch APIs.
Context Window
The context window is the maximum text — measured in tokens — an LLM can consider at once: prompt, conversation, documents, and its own output combined.
Frontier Model
A frontier model is one of the most capable AI models available — the leading edge from labs like Anthropic, OpenAI, and Google, defining the state of the art.
Token (LLM)
A token is the unit LLMs read and write — a word fragment of roughly 3–4 characters in English. Models are priced, limited, and measured in tokens, not words.
Model Routing
Model routing sends each request to the cheapest model that can handle it, escalating only hard cases to a stronger model — cutting cost and latency.
Prompt Caching
Prompt caching reuses the computed state of a repeated prompt prefix across requests — dramatically cutting cost and time-to-first-token for stable context.
Reasoning Model
A reasoning model is an LLM trained to think before answering — generating internal reasoning tokens it can spend adaptively on hard problems.
Semantic Caching
Semantic caching reuses LLM responses keyed by meaning rather than exact text, matching queries by embedding similarity to cut cost and latency.
Structured Output
Structured output makes an LLM return data in a guaranteed shape — JSON matching your schema — so code can consume model responses without parsing prose.
Temperature
Temperature controls how random an LLM's token choices are: low values make output focused and repeatable, high values make it varied and creative.
Token Streaming
Token streaming delivers model output incrementally as it's generated — via SSE or websockets — so users see text immediately instead of waiting.
Top-p (Nucleus Sampling)
Top-p sampling restricts an LLM's next-token choices to the smallest set whose probabilities sum to p — cutting the long tail of unlikely tokens adaptively.