Smart Stack
One workspace for your AI toolkit: track the tools you use, compare alternatives side by side, and start from verified agent foundations.
My stack
The AI tools you run, with costs, coverage, and an honest audit.
Compare
Side-by-side pricing, features and compliance for any tools in the directory.
Foundations
Complete, verified build sheets for running real AI agents. Every part links to its record in the directory, with the date it was last checked.
OpenClaw Starter
The minimum viable OpenClaw setup: one agent that lives on a small server, answers you in your chat app, and can actually look things up on the live web instead of guessing.
- Agent shell: OpenClaw — Open-source personal agent that runs 24/7 and talks to you through your messaging apps.
- Brain: Claude Opus 4.8 — Strong long-horizon reasoning — the difference between an agent and an autocomplete.
- Web search: Exa — A search API built for agents: clean, structured results a model can actually read.
- Calendar: Google Calendar — Lets the agent see and manage your schedule.
- Runs on: Hetzner — A small cloud server is enough to keep it running around the clock.
OpenClaw Power Build
The full-strength OpenClaw rig. The agent can run code safely in a sandbox, trigger multi-step workflows, and speak — useful when you want it managing things, not just chatting.
- Agent shell: OpenClaw — Same shell as the starter — this build deepens what it can do.
- Brain: Claude Opus 4.8 — Handles multi-step plans without losing the thread.
- Code sandbox: E2B — Isolated cloud sandboxes so the agent can run code without touching your machine.
- Workflows: n8n — Self-hostable automation — the agent triggers flows across hundreds of apps.
- Voice: ElevenLabs — Natural text-to-speech for spoken replies and briefings.
- Runs on: IDCloudHost — Affordable Southeast-Asia hosting with full root access.
Hermes Research Desk
Hermes handles long research runs: it searches the live web, pulls sources into a structured index, and writes findings into your workspace where you actually work.
- Agent shell: Hermes Agent — Autonomous research agent built for long unattended runs.
- Brain: DeepSeek V4 — Open-weights frontier model — strong reasoning at a fraction of the token price.
- Web search: Exa — Semantic search tuned for research queries, not ad-ranked links.
- Source index: LlamaIndex — Turns collected documents into a queryable knowledge base.
- Workspace: Notion — Findings land as structured pages your team can read.
Claude Code Ship Crew
Claude Code does the heavy lifting in the terminal, Cursor gives you the same brain inside the editor, and a review layer catches what either of you missed before it merges.
- Coding agent: Claude Code — Terminal-native agent that plans, edits across files, and runs your tests.
- Brain: Claude Opus 4.8 — Top-tier code reasoning shared by both the agent and the editor.
- Editor: Cursor — AI-first editor for the hands-on parts of the work.
- Code review: Qodo — Automated review and test generation on every pull request.
- Sandbox: E2B — Run untrusted generated code in isolation before it lands.
Browser Operator
For work that only exists behind a browser: form-filling, bookings, account chores, scraping into spreadsheets. The agent operates pages directly, and structured scraping feeds it clean data.
- Agent shell: MultiOn — Acts inside a real browser session — clicks, types, navigates.
- Brain: Gemini 3.5 Pro — Strong vision-and-layout understanding for reading live pages.
- Web scraping: Browse AI — Point-and-click robots that turn any site into a structured feed.
- Hand-offs: Zapier — Pipes results into the rest of your stack — sheets, CRM, chat.
- Spreadsheets: Google Sheets — Scraped and processed data lands somewhere your team can use it.
Outbound Sales Agency
A pipeline where the agent finds prospects, writes the first line itself from real signals, and keeps the CRM honest — while a human stays on every send button that matters.
- Agent shell: Lindy — No-code AI agents for recurring revenue workflows.
- Brain: GPT-5.5 — Fast, reliable drafting across hundreds of personalized messages.
- Prospect data: Seamless AI — Live-verified emails and numbers, so outreach doesn't bounce.
- CRM: HubSpot — The system of record the agent reads and writes.
- Inbox: Shortwave — AI-native email where replies get triaged and drafted.
Support Desk Agent
A front-line support agent grounded in your own docs. It answers what it actually knows, hands off cleanly when it doesn't, and every conversation lands in your help desk.
- Agent shell: Ada — Enterprise support automation with guardrails and analytics.
- Brain: Claude Sonnet 4.6 — Polite, precise, and cheap enough to run on every ticket.
- Knowledge: eesel — Trains the agent on your docs, past tickets, and internal wikis.
- Help desk: Zendesk — Escalations arrive as proper tickets with full conversation history.
- In-app chat: Intercom — The customer-facing surface where the agent meets users.
Voice Front Desk
Callers get a natural voice that understands them, checks the calendar, and books or routes — around the clock. Built from specialist layers rather than one black box.
- Voice agent: Retell AI — Orchestrates the live call: turn-taking, interruptions, latency.
- Brain: GPT-5.5 — Low-latency reasoning that keeps the conversation moving.
- Speech-to-text: Deepgram — Accurate live transcription, even on bad lines.
- Voice: ElevenLabs — A voice callers don't immediately clock as a robot.
- Phone lines: AgentPhone — Numbers, routing, and telephony plumbing for AI agents.
- Calendar: Google Calendar — Real availability, real bookings.
Content Studio
A production line for marketing content: long-form drafts grounded in your brand voice, visuals and video generated to match, and scheduling handled at the end.
- Brain: Claude Opus 4.7 — Long-form drafting that holds tone across thousands of words.
- Writing: Jasper — Brand-voice controls and campaign workflows on top of the model.
- Images: Midjourney — Still the bar for editorial-quality generated imagery.
- Video: HeyGen — Talking-head and localized video without a studio.
- Polish: Grammarly — A second pass that catches what generation misses.
- Scheduling: Hootsuite — Everything queued and posted across channels.
Meeting Ops
Every call gets recorded, summarized, and turned into action items in your workspace; the calendar reshuffles itself around the work. Quietly one of the highest-ROI stacks.
- Meeting notes: Fireflies — Joins calls, transcribes, and extracts decisions and actions.
- Brain: Claude Sonnet 4.6 — Summaries that read like a sharp colleague wrote them.
- Scheduling: Motion — Auto-plans your day around meetings and deep work.
- Calendar: Google Calendar — The single source of truth everything syncs against.
- Workspace: Notion — Notes and action items land where the team already works.
Automation Backbone
Before agents can manage real work they need rails: triggers, queues, retries, and connections into the apps a business actually runs on. This is that layer.
- Workflow hub: n8n — Self-hostable, code-friendly automation — agents call it like an API.
- App connector: Make — Visual scenarios for the integrations n8n shouldn't own.
- Quick glue: Zapier — Fastest path for the simple one-trigger automations.
- Durable jobs: Temporal — Workflows that survive crashes — for the automations that must not fail.
- Data sink: Google Sheets — The universal interchange format for ops teams.
Knowledge & RAG Base
A retrieval layer your whole agent fleet shares: documents in, grounded answers out, with model routing so each query runs on the cheapest brain that can handle it.
- Orchestration: LangChain — The framework wiring retrieval, tools, and models together.
- Indexing: LlamaIndex — Best-in-class document ingestion and query pipelines.
- Model routing: OpenRouter — One API over every frontier model — route by cost and capability.
- Fast inference: DeepSeek V4 Flash — Cheap, fast model for the high-volume retrieval calls.
- Compute: Modal — Serverless GPU compute for embedding and processing jobs.
App Builder Line
The stack non-engineers ship real software with: describe the product, iterate on the generated app, drop to an AI editor when you outgrow the builder, and host it all in one place.
- App generator: Lovable — Full-stack apps from a conversation — the fastest zero-to-demo.
- UI generator: v0 — Production-grade React components from prompts.
- Brain: GPT-5.5 — The default brain both builders lean on.
- Editor: Windsurf — Agentic editor for when you need to touch the code yourself.
- Host & deploy: Replit — Code, database, and hosting in one workspace.
Short-Video Factory
Generate footage, cut it to platform-native shorts, voice it, and score it — a complete short-form video line driven from a single script document.
- Video gen: Runway — Controllable, production-quality generated footage.
- Alt footage: Kling — A second generator with a distinctly different look.
- Clipping: OpusClip — Turns long footage into ranked, captioned shorts.
- Voiceover: ElevenLabs — Narration in any voice, any language.
- Music: Suno — Original backing tracks without licensing headaches.
Not sure where to start? Run Smart Match and we rank the listings that fit what you are doing, or browse the full AI directory.