AI & LLMs guides

How to Build an Agent with the Claude Agent SDK

Build an agent with the Claude Agent SDK — install, write custom tools, add hooks, compose sub-agents on the harness powering Claude Code. Free guide.

How to Set Up Claude Code

Configure Claude Code with permissions, MCP servers, and sub-agents for a full working setup. Free browser-only guide, no sign-up.

How to Set Up Cursor AI IDE

Optimize Cursor AI IDE modes, .cursorrules, and model picks to avoid credit-pricing traps. Free, instant configuration guide, no sign-up.

How to Use GitHub Copilot Agent Mode

Go from a GitHub issue to a reviewable PR with Copilot Workspace — plan review, model picker, copilot-instructions.md, and iteration by comment.

How to Build a Multi-Agent System with CrewAI

Create a three-agent Python crew — Researcher, Writer, Editor — using four primitives and cost control tips. Start building your free system instantly online.

How to Build a Stateful Agent with LangGraph

Build a long-running LangGraph agent with state, nodes, conditional edges, and SQLite checkpointing — pause, resume, and debug it. Free guide, no signup.

How to Connect an Agent to MCP Tools

Wire an MCP server into Claude Code, Agent SDK, or Cursor in seconds. Free guide on allow-listing and security rules for safe, instant connections.

How to Set Up a Hyperspace Pod

Pool your laptops into one peer-to-peer AI cluster with automatic model sharding and free local inference. Instant setup, no sign-up.

How to Use Ollama

Install Ollama, download models like Llama 3, Qwen, and Mistral, and run them via CLI or REST API with GPU acceleration. Get started instantly for free.

How to Use LM Studio

Pick models from the catalog, chat in the desktop UI, and expose an OpenAI-compatible server on port 1234 with GPU offloading. Free to run locally.

How to Use llama.cpp

Build llama.cpp from source, download GGUF files, and serve models via CLI or REST API with Metal or CUDA acceleration in your browser.

How to Use Jan

Download Jan to connect local and remote models, install extensions, and use keyboard shortcuts for a private ChatGPT alternative. No sign-up required.

How to Use GPT4All

Download GPT4All, load open-source LLMs, and create a private RAG pipeline over your documents using SBert embeddings—completely offline and free.

How to Use Hermes Models

Master Hermes 3 system prompts and function-calling syntax to extract reliable structured data from the Nous Research Llama tune. Free online walkthrough.

How to Use smolagents

Build and test code agents using smolagents and Hugging Face's free tools. Learn to add custom tools and use sandboxed execution instantly, no download needed.

How to Use SWE-agent

Solve GitHub issues automatically with SWE-agent. This free guide covers the agent-computer interface, model config, and cost control, with instant browser-based setup instructions.

How to Use OpenCode

Install SST's open-source terminal agent, connect Claude or local providers, navigate the TUI, and review diffs with plan mode. Free to use instantly.

How to Use Aider

Installing aider, --model flag, /add and /drop, edit formats (diff, whole, udiff), git integration, and voice coding.

How to Use Cline

Installing the Cline extension, task-based workflows, tool permissions, browser use, terminal commands, approval modes.

How to Use Continue.dev

Installing Continue in VS Code/JetBrains, config.json, choosing models, custom context providers, slash commands.

How to Use Windsurf

Edit whole codebases instantly with Windsurf's Cascade AI agent flows. Discover tab-to-complete and multi-file edits for free, online, with no registration needed to get started.

How to Use Goose

Set up Block's open-source Goose agent on your machine, connect LLM providers, enable extensions, and run headless with this free guide.

How to Use Gemini CLI

Installing the gemini CLI, free tier access, Gemini 2.5 Pro, 1M context, tool use, and comparing to other CLIs.

How to Use Codex CLI

Every Codex CLI command with examples. npm install, sandbox approval modes, /review, /init, config file gotchas — covers the OpenAI terminal agent in 5 min.

How to Use OpenHands

Run the OpenHands web UI in a sandbox container, connect LLM providers, and assign tasks to an autonomous AI developer. Set up instantly online.

How to Use Devin

Signing up for Devin, creating sessions, Slack integration, planning mode, the Devin API, pricing and gotchas.

How to Use Replit Agent

Start a project from a prompt, use checkpoints to roll back, set up databases and auth, and deploy live—all within the Replit online environment with no sign-up.

How to Use Bolt.new

Prompting Bolt.new, WebContainer runtime, iterating on generated code, connecting GitHub, deploying to Netlify.

How to Use v0 by Vercel

Generate production-ready UI components with simple text prompts using v0 by Vercel. Iterate and ship to Next.js in your browser — free, online, and no sign-up needed.

How to Use Lovable

Create a project with Lovable, sync to GitHub, edit via chat, and integrate a Postgres database with Supabase. Deploy your app instantly for free.

How to Use AutoGen

Installing pyautogen, AssistantAgent + UserProxyAgent, group chat, termination conditions, code execution sandbox.

How to Use Pydantic AI

Define agents with validated result_types, inject dependencies, add tools, and stream responses with OpenTelemetry tracing. Build robust agents instantly online.

How to Use Agno (Phidata)

Installing agno, Agent + Teams, knowledge/RAG, tools, Playground UI, running in production with monitoring.

How to Use DSPy

Installing dspy-ai, Signatures, Modules (Predict, ChainOfThought, ReAct), MIPROv2 optimizer, metric-driven prompts.

How to Use Mastra

Create agents with memory, define multi-step workflows, and run evaluations. Integrate Mastra with Next.js and deploy to production free with this guide.

How to Use Vercel AI SDK

Build a unified interface for any LLM provider with the Vercel AI SDK. Learn to stream text and use hooks instantly with this free, online guide right in your browser.

How to Use LangChain

Build composable LCEL runnables, attach retrievers and memory, and parse structured output with LangChain. Start chaining components instantly online.

How to Use LlamaIndex

Ingest documents into a VectorStoreIndex, create custom workflows, and parse complex PDFs with LlamaParse. Start building your RAG stack online for free.

How to Use Zed's AI Agent

Generate and edit code inline by turning on Zed's AI Agent Panel. Configure any provider and use Edit Predictions for free, instantly, with no sign-up required in your browser.

How to Use Warp AI

Analyze code and run workflows with an AI agent directly in your terminal. Start using Warp's Agent Mode for free, instantly, and with no sign-up required right from your browser.

How to Use Amazon Q Developer

Install Amazon Q Developer, use inline completions, agent tasks, security scans, and AWS integration. Free guide — read instantly in your browser.

How to Use Tabby

Deploy a self-hosted, open-source coding copilot instantly using Tabby and Docker. Get free, private AI code completions with no registration, straight from your browser.

How to Use Phind

Get web-grounded technical answers using Phind-70B, switch between Quick and Thorough modes, and solve coding problems instantly in your browser for free.

How to Use Mentat AI

Install Mentat, control file context with /include and /exclude, apply diff-based edits, and integrate with your git workflow. Free to use in your browser.

How to Use Semantic Kernel

Build intelligent agents using Microsoft's Semantic Kernel for C#, Python, or Java. Explore plugins, planners, and memory with this free, online guide — no registration required.

How to Use Letta (MemGPT)

Build agents that remember across sessions using Letta's archival storage and memory management. Set up the server or cloud instance in seconds online.

How to Use Haystack

Combine document stores, retrievers, and generators into custom NLP pipelines. Deploy Haystack to production instantly with this online guide.

How to Use Griptape

Create AI agents with tools, memory, and off-prompt data using the Griptape SDK. Start building modular pipelines in seconds without sign-up.

How to Use Marvin AI

Use the @ai_fn decorator and Pydantic schemas to build type-safe NLP functions. Integrate AI into your Python codebase online without sign-up.

How to Use Open WebUI

Set up Open WebUI, integrate Ollama models, enable RAG on documents, support MCP tools, and manage users—all running locally online with no sign-up.

How to Use AnythingLLM

Install AnythingLLM, set up a workspace, pick embedding + vector DB. Plus the 3 settings that actually matter and which ones to skip.

How to Use Flowise

Installing Flowise, drag-drop chain building, templates, API deployment, credentials, and analytics.

How to Use Dify

Self-hosting Dify, visual workflows, agents, datasets, apps (chatbot/completion), API keys, monitoring.

How to Use LibreChat

Spin up LibreChat to unify OpenAI, Anthropic, and local models under one interface. Configure plugins and assistants API with this free Docker guide.

How to Use n8n's AI Agent Node

Connect LLM tools, memory, and LangChain backends inside n8n to create production-ready automations. Start building agent flows instantly for free.

How to Use Langfuse

Monitor AI apps by tracing prompts, scoring outputs, and running evals via the Langfuse SDK. Deploy the open-source dashboard for free in your environment.

How to Use Promptfoo

Write promptfooconfig.yaml assertions, run adversarial tests, and view results in the web UI. Integrate prompt evaluation into your pipeline online for free.

How to Use Rivet

Generate complex LLM workflows visually with Rivet's graph-based nodes and embed them in JS/TS apps instantly. No sign-up needed to start building in your browser.

How to Use AI in Small Business

Practical AI adoption for SMBs — start with one workflow, pick a free tier, keep humans in the loop.

How to Write Better AI Prompts

Generate higher-quality AI outputs instantly with a proven 4-part prompt formula. Explore chain-of-thought techniques in this free, online guide with no sign-up or download needed.

How to Combine Laptops to Run Large LLMs

Pool laptops into a cluster for Llama 70B or Qwen 72B using Hyperspace, exo, or llama.cpp. Free, online guide to choose the right network method.

How to Share a GPU Across Machines

Share one GPU host across your LAN with Ollama, vLLM, or LM Studio and manage auth and throughput. Free instant guide, no sign-up.

How to Run Llama 70B on Consumer Hardware

Run Llama 70B on consumer hardware with practical quantization and GPU offloading guidance. Free setup walkthrough, instant results.

How to Build a Home AI Cluster

Compare topologies, shop hardware, and manage network noise with this practical guide to building your own AI cluster in three weekends — no sign-up required.

Best AI for Coding (2026)

Which AI wins for coding in 2026: Claude vs GPT-5 vs DeepSeek vs Qwen, with Cursor / Copilot / Claude Code harness picks and language-specific recommendations.

Best AI for Research (2026)

The 2026 research stack: Perplexity for grounded answers, NotebookLM for source synthesis, Claude/Gemini for long-document analysis. Free + paid picks.

Best AI for Writing (2026)

Compare Claude and ChatGPT for marketing copy, technical docs, and fiction instantly. Find the optimal AI writer for your content type online.

Best AI for Marketing (2026)

Create a powerful marketing stack with ChatGPT, Claude, and Midjourney in seconds. Generate ads, blogs, and research instantly free.

Best AI for Students (2026)

Compare free and paid AI picks for homework, language learning, and CS instantly. Find the right study tool for every subject in your browser.

Best AI for Data Analysis (2026)

Compare ChatGPT, Claude, and Hex for spreadsheets, pandas, and dashboards instantly. Find your ideal data analysis AI tool free online.

Best AI for Creative Writing (2026)

Compare Sudowrite, Claude, and ChatGPT for fiction, literary prose, and stylistic range instantly. Pick the ideal AI for your creative form online.

Best AI for Customer Support (2026)

Compare Intercom, Zendesk, Decagon, and Sierra AI for support instantly. Find the right build vs. buy fit for your team with no sign-up.

Best AI for Image Generation (2026)

Compare Midjourney, FLUX, DALL-E, and Stable Diffusion for every style instantly. Find the perfect image generation AI free online.

Best AI for Video Generation (2026)

Compare Sora, Veo, Runway, and Kling for length, style, and control instantly. Find the ideal AI video generator for your project free online.

Best AI for Agents (2026)

Claude Opus 4.7 / Sonnet 4.6 lead agentic reliability. GPT-5 competes. DeepSeek wins on cost. The 2026 agent stack with framework picks.

Best AI for PDFs (2026)

Compare Claude, NotebookLM, and LlamaParse for document chatting and structured extraction instantly. Find your ideal PDF AI workflow online.

Best AI for Emails (2026)

Compare Superhuman AI, Shortwave, and the platform in Gmail for speed and clarity instantly. Find the perfect email AI workflow in seconds.

Best AI for Meetings (2026)

Compare Granola, Otter, Fireflies, and the platform for meeting notes instantly. Get accurate transcripts and privacy-first options online.

Best AI for Legal Research (2026)

Compare Harvey, Co-Counsel, and Spellbook for law firms instantly. Get pricing, hallucination warnings, and the right pick for your firm size online.

Best Free AI Tools (2026)

Combine NotebookLM, Claude, the platform, and the platform into a powerful free workflow instantly. Build your no-cost AI stack in your browser today.

How to Pick an AI Coding Assistant

Find your AI coding assistant by answering three questions—IDE, inline vs agent, budget. A free instant 2026 picks guide for Cursor, Copilot, and more, no sign-up.

How to Pick an AI for Research

Select an AI research tool using a decision tree—find with Perplexity, synthesize with NotebookLM. A free instant guide by source length and citations, no sign-up.

How to Evaluate an AI Model

Build a 30-task eval set, score with rubrics, and spot-check failures using OpenAI Evals and Promptfoo. Free online framework—no signup required in seconds.

Claude Pricing Explained (2026)

Every Claude price in 2026: Free, Pro $20, Max $100/$200, Team $25-30/seat, plus Opus/Sonnet/Haiku API rates. With when each tier is worth it.

ChatGPT Pricing Explained (2026)

Every ChatGPT price in 2026: Free, Plus $20, Pro $200, Team $25-30/seat, plus GPT-5/mini/nano API rates. Including the rate-limit gotchas.

Gemini Pricing Explained (2026)

Every Gemini price in 2026: free, Advanced $20, Ultra $250, Workspace add-ons, plus 3 Pro / 2.5 Pro / Flash / Lite API rates.

DeepSeek Pricing Explained (2026)

DeepSeek V3.2 at $0.27/$1.10, R1 at $0.55/$2.19, off-peak 50% off, free chat, and what to know about privacy + self-host.

AI Pricing Cheat Sheet (2026)

Every consumer plan + API rate for Claude, ChatGPT, Gemini, Perplexity, DeepSeek, Kimi, Grok, Mistral, plus the 5 levers that cut your bill.

How to Choose the Right AI for Your Team

Identify the right AI for your team in 4 weeks with our free, instant guide. Compare ecosystems, calculate team costs, and learn negotiation tips.

What Are Agentic Browsers?

Agentic browsers (ChatGPT Atlas, Comet, Dia, Edge Copilot) let AI act on the web on your behalf. The 2026 lineup, capabilities, and which to pick.

How to Use ChatGPT Atlas

Get value from ChatGPT Atlas — OpenAI's standalone agentic browser. Setup, what it's good at, what it's not, and privacy considerations.

What Is MCP Protocol?

Model Context Protocol — open standard for connecting AI assistants to tools. Anthropic-launched, now supported by Claude, ChatGPT, Cursor, Zed, Goose.

What Is Vibe Coding?

Vibe coding is writing software by describing intent and letting AI build it. The 2026 toolchain (Bolt, Lovable, v0, Cursor, Replit Agent) and when it works.

How to Deploy Llama Locally

Deploy Llama models locally online for free with our instant setup guide. Get an OpenAI-compatible API running in 30 minutes, no sign-up needed.

How to Write AI Image Prompts

Generate stunning AI images with a 5-part prompt structure that works across Midjourney, DALL-E 4, and FLUX. Get the free, instant formula online — no sign-up required.

What Changed in GPT-5

GPT-5's reasoning router, 400k context, pricing drops, mini/nano tiers, Atlas + Operator + Sora 2. What got better in practice and what didn't.

What Changed in Claude 4

Claude 4.x lineup: 1M context across Sonnet+Opus, prompt caching at 90% off, Claude Code, Computer Use API, Skills + Hooks. What got better in practice.

AI Search vs Google in 2026

Where AI search wins (synthesis, multi-step, code) vs where Google still does (local, transactional, news, image). The new mental model.

How to Pick an MCP Server

Evaluate MCP servers by workflow, official vs community, and transport. A free instant guide with trust and safety tips for granting access, no download required.

Kimi K2 vs DeepSeek V3

Two open-weight Chinese flagships. Kimi K2 = 1M context, DeepSeek V3.2 = top-tier reasoning + coding. Pick by use case.

Anthropic Skills Explained

Skills as Anthropic's answer to Custom GPTs — markdown-defined, version-controlled in git, work in terminal. Anatomy + Skills vs Custom GPTs.

AI Fluency Skills

The 8 sub-skills of AI fluency: prompt structure, model selection, tool use, quality calibration, iteration, context management, cost awareness, privacy.

GitHub Copilot Security and Data Handling

Audit where your code goes, who sees it, training-data policy, network needs, and what happens when Copilot suggests broken code. Free, no sign-up.

GitHub Copilot Features and Capabilities

Test what Copilot really does — code accuracy, scope limits, debugging, web dev, legacy code, tests, docs, team customization. Free guide, no sign-up.

GitHub Copilot Pricing and Comparison

Compare free vs paid GitHub Copilot tiers and analyze it against ChatGPT, Cursor, and Tabnine. Find the best value plan instantly with this free online guide.