All use cases & tools

Coding & Shipping Agents

Coding & Shipping AgentsTool
Claude Code
A terminal-first coding agent that reads your repo, edits files and runs commands.
Effort: Low
Coding & Shipping AgentsUse case
Claude Code GitHub Actions: @claude in issues and PRs
Mention @claude in an issue or PR and get code changes back as a PR.
Effort: Medium
Coding & Shipping AgentsUse case
Turn a GitHub issue into a PR with Copilot cloud agent
Assign an issue to Copilot and review the pull request it opens.
Effort: Low
Coding & Shipping AgentsTool
Cursor Cloud Agents
Run Cursor's agent in the cloud so tasks continue while you work on something else.
Effort: Low
Coding & Shipping AgentsTool
Cursor Bugbot for PR review
An AI reviewer that flags bugs and security issues on every pull request.
Effort: Low
Coding & Shipping AgentsTool
OpenAI Codex CLI
OpenAI's open-source, lightweight coding agent for your terminal.
Effort: Low
Coding & Shipping AgentsTool
Codex Cloud: delegate tasks to cloud sandboxes
Send coding tasks to Codex in the cloud, review the results, open PRs.
Effort: Medium
Coding & Shipping AgentsTool
Aider
Open-source AI pair programming in your terminal, with git commits built in.
Effort: Low
Coding & Shipping AgentsUse case
Auto lint-and-test fix loop with Aider
Make the agent run your linter and tests after each edit and fix what breaks.
Effort: Low
Coding & Shipping AgentsUse case
Give your agent a conventions file
A short CONVENTIONS.md stops agents from fighting your style every session.
Effort: Low
Coding & Shipping AgentsTool
Cline
Open-source autonomous coding agent for your IDE, CLI or as an SDK.
Effort: Low
Coding & Shipping AgentsTool
Devin
An AI software engineer that runs parallel cloud agents on your backlog.
Effort: Medium
Coding & Shipping AgentsTool
Jules by Google
An async coding agent: pick a repo, describe the task, approve the plan, get a PR.
Effort: Low
Coding & Shipping AgentsTool
Gemini CLI
Google's open-source agent that brings Gemini into your terminal.
Effort: Low
Coding & Shipping AgentsTool
opencode
An open-source coding agent for the terminal that works with many model providers.
Effort: Low
Coding & Shipping AgentsTool
OpenHands
An open-source platform for AI software agents you can self-host.
Effort: High
Coding & Shipping AgentsTool
CodeRabbit
Independent AI code review, PR triage and change explanations.
Effort: Low

Research & Automation

Research & AutomationTool
Gemini Deep Research
Hand off a research question and get back a multi-source report.
Effort: Low
Research & AutomationTool
Perplexity API Platform
Real-time, web-grounded search and answers via API for your own products.
Effort: Medium
Research & AutomationTool
Open Deep Research (LangChain)
An open-source, configurable deep research agent you can run and modify.
Effort: High
Research & AutomationTool
GPT Researcher
An autonomous agent that researches any topic and writes a report, with any LLM.
Effort: Medium
Research & AutomationTool
Firecrawl
Turn websites into clean, LLM-ready data via API.
Effort: Low
Research & AutomationTool
Crawl4AI
Open-source crawler that turns any website into clean, LLM-ready Markdown.
Effort: Medium
Research & AutomationTool
MarkItDown: convert docs to Markdown for LLMs
Convert PDFs, Office files and more into Markdown that LLMs read well.
Effort: Low
Research & AutomationTool
Gemini Notebook
An AI research partner grounded in the sources you upload.
Effort: Low
Research & AutomationTool
n8n
Workflow automation with AI agent nodes, self-hostable.
Effort: Medium
Research & AutomationUse case
Start from n8n community workflow templates
Thousands of community templates: copy one, swap credentials, ship.
Effort: Low
Research & AutomationUse case
Weekly competitor digest with n8n + Firecrawl
Scrape competitor pages weekly, summarise changes with an LLM, email yourself.
Effort: Medium
Research & AutomationTool
Zapier Agents
AI teammates that act across thousands of apps, on command or on a schedule.
Effort: Low
Research & AutomationTool
Make AI Agents
AI agents inside Make's visual automation scenarios.
Effort: Medium
Research & AutomationUse case
Make MCP Server: call your scenarios from any AI client
Expose Make scenarios as tools to Claude, Cursor and other MCP clients.
Effort: Medium
Research & AutomationTool
Raycast AI
AI in your launcher, connected to the tools you already use.
Effort: Low
Research & AutomationUse case
Turn a docs site into agent context
Crawl the docs once, save as Markdown, point your coding agent at it.
Effort: Low

Vibe-Coding & Prompt-to-App

Vibe-Coding & Prompt-to-AppTool
Lovable
Full-stack web apps from natural language, with real code you can export.
Effort: Low
Vibe-Coding & Prompt-to-AppTool
Bolt.new
Prompt, run, edit and deploy full-stack web apps in the browser.
Effort: Low
Vibe-Coding & Prompt-to-AppTool
v0 by Vercel
AI assistant to design, iterate and ship full-stack web apps on Vercel.
Effort: Low
Vibe-Coding & Prompt-to-AppTool
Replit Agent
Describe what you need; the agent writes, tests, fixes and publishes it.
Effort: Low
Vibe-Coding & Prompt-to-AppUse case
Run Bolt's open-source core yourself
The bolt.new repo is public: study or run a prompt-to-app agent locally.
Effort: High
Vibe-Coding & Prompt-to-AppTool
Supabase MCP server
Let your AI tools manage Supabase tables, migrations and queries.
Effort: Low
Vibe-Coding & Prompt-to-AppTool
Context7: up-to-date docs for AI editors
Feeds current, version-specific library docs into your coding assistant.
Effort: Low
Vibe-Coding & Prompt-to-AppUse case
Cursor Rules and AGENTS.md
Persistent instructions so the AI follows your stack every time.
Effort: Low
Vibe-Coding & Prompt-to-AppUse case
Reusable skills and slash commands in Claude Code
Package your repeated prompts as skills you can call with one command.
Effort: Low
Vibe-Coding & Prompt-to-AppUse case
Write a one-page spec before you vibe-code
Ten minutes of spec saves hours of the AI going in circles.
Effort: Low
Vibe-Coding & Prompt-to-AppUse case
Let your agent click through your app with Playwright MCP
Give the agent a real browser so it can check its own UI work.
Effort: Low
Vibe-Coding & Prompt-to-AppTool
Continue
Open-source coding agent for VS Code and JetBrains, any model.
Effort: Medium

Multi-Step Agent Setups

Multi-Step Agent SetupsTool
Model Context Protocol (MCP)
The open standard for connecting AI apps to tools and data.
Effort: Medium
Multi-Step Agent SetupsTool
MCP reference servers
Official example MCP servers to use or learn from.
Effort: Low
Multi-Step Agent SetupsTool
GitHub MCP Server
Give agents structured access to issues, PRs, code and Actions.
Effort: Low
Multi-Step Agent SetupsTool
browser-use
Open-source library for agents that use the browser.
Effort: Medium
Multi-Step Agent SetupsTool
Stagehand
Mix AI actions with code for more reliable web automation.
Effort: Medium
Multi-Step Agent SetupsTool
LangGraph
Low-level framework for stateful, controllable agent workflows.
Effort: High
Multi-Step Agent SetupsTool
CrewAI
Build collaborative agent crews and flows in Python.
Effort: Medium
Multi-Step Agent SetupsTool
OpenAI Agents SDK
A lightweight framework for multi-agent workflows with handoffs and guardrails.
Effort: Medium
Multi-Step Agent SetupsTool
Claude Agent SDK
Build your own agents on the same harness that powers Claude Code.
Effort: Medium
Multi-Step Agent SetupsUse case
Specialised subagents in Claude Code
Delegate review, testing or research to focused subagents with their own context.
Effort: Low
Multi-Step Agent SetupsUse case
Deterministic guardrails with Claude Code hooks
Run your own scripts at agent lifecycle events: format, lint, block risky commands.
Effort: Medium
Multi-Step Agent SetupsUse case
Building effective agents: the patterns
Prompt chaining, routing, parallelisation, orchestrator-workers, evaluator-optimizer.
Effort: Low
Multi-Step Agent SetupsUse case
12-Factor Agents
Principles for LLM software good enough to put in front of customers.
Effort: Low
Multi-Step Agent SetupsTool
E2B sandboxes for agent code execution
Secure cloud environments where agents can run code and tools.
Effort: Medium
Multi-Step Agent SetupsTool
Dify
Visual platform for agentic workflows and RAG pipelines, cloud or self-hosted.
Effort: Medium