Skip to main content
AIDiveForge AIDiveForge

AI tools that actually work — verified, not guessed

Stop spending hours testing tools that don’t pan out. AIDiveForge gives you verified specs, workflow blueprints, and portable skills — so you can pick the right stack and start building today.

874Tools
869Verified
15Tool Packs
Verified against live websites

Every spec is pulled directly from each tool’s homepage. If we can’t confirm it, we don’t list it.

No pay-to-play, ever

Rankings come from data and community votes. No tool buys a better position — not now, not later.

Workflows ready to run

Workflow packs bundle the tools, prompts, and steps for a specific outcome. Grab one and start building.

Stack Builder

Build your AI stack in 3 steps

Save the tools you use together. Share them as a URL. Come back next week and see what changed.

Build your first stack

Portable Skills

Drop a skill file into Claude Code, Cursor, or Copilot and immediately gain a repeatable capability — with the rationale for why it works built in.

Browse the Skill Forge →

Browse by Category

Filter by category, price, and what the tool actually does

This Week on AIDiveForge

🔥 Trending
Runner logo Runner
🏆 Top Contributor
Be the first to contribute

Recently Added

All specs pulled from live websites — never AI-guessed

Konxios logo

Konxios

The core bet is that your agents — code reviewer, personal assistant, browser automator — live on your machine, talk to each other, and never push your data to a third-party server. Local models run through Ollama or LM Studio; cloud fallback goes through OpenAI, Anthropic, or OpenRouter when you need it. Docker isolation means each project gets its own sandboxed container, so a misfired agent cannot touch unrelated work. The platform is in public beta at v0.1.0, which means the agent skill marketplace, multi-agent collaboration depth, and edge-case reliability are still being shaped by early users — not by two years of production hardening. Teams that need proven uptime SLAs or audit trails for enterprise compliance will hit the beta ceiling fast.

Paid
BotPenguin logo

BotPenguin

The platform covers the full stack a small-to-mid-size team actually needs: AI chatbot flows, autonomous agents that run multi-step tasks on their own, voice bots, bulk messaging campaigns, and a unified inbox — all without writing code. The no-code builder works cleanly for linear support flows and lead capture sequences. The wall appears when your conversation logic branches more than two or three levels deep; the canvas starts fighting you, and teams handling complex routing end up stitching in Zapier or a custom integration to cover the gaps. Analytics and segmentation are present, but community reports suggest the reporting depth does not match dedicated analytics tools. Self-hosting is not available, so teams with strict data residency requirements are blocked at the door.

Paid
Runner logo

Runner

Runner connects to 50+ apps and executes tasks across them — pulling context from email, calendar, chat, and cloud files, then acting on what it finds rather than handing the work back to you. The built-in Chrome browser fires up in the background to unblock searches without interrupting what you're doing, and a permission layer lets you sign off on each action until you're comfortable letting it run faster. Memory accumulates across sessions, so the tool builds a model of how you work over time. The ceiling appears when you need custom conditional logic or integrations outside the supported app list — there's no API to extend it yourself, and no self-hosted option if your data governance policy requires it.

Paid
Qwen 3.7 Plus logo

Qwen 3.7 Plus

The offering is a per-token API for the Qwen model family, covering chat, question answering, and content generation workloads. The architecture is cloud-only — no self-hosted option exists, so your data leaves your infrastructure on every call. For teams already running on Alibaba Cloud, the integration surface is tight and latency to regional endpoints is measurably lower than US-origin providers. The primary production constraint is the proprietary-API model: you are dependent on Alibaba's availability, pricing schedule, and model deprecation decisions. Teams that need output guarantees or compliance controls that require on-premise inference hit that wall immediately.

Paid
Agent Island logo

Agent Island

Built by the Stanford Digital Economy Lab and described in arXiv paper 2605.04312, Agent Island puts language models into a shared environment and measures strategic behavior — not just task completion. The benchmark exposes gaps that standard evals miss: can a model read the room, shift alliances, and avoid being outmaneuvered by another agent? The interface exposes play and log views so researchers can inspect run-by-run behavior. Where it breaks: there is no API, no self-hosted option, and no published code repository, so teams cannot integrate Agent Island into a CI pipeline or adapt the environment to their own agent design.

Free
Team0 logo

Team0

Team0 reads your Gmail, calendar, and meeting history and acts on what it finds — drafting the overdue invoice follow-up, queuing ten social posts grounded in what actually happened that week, and dropping a morning brief into WhatsApp before you open your laptop. Nothing goes out without your sign-off: every draft waits in Gmail or your preferred chat app for a yes. The architecture is one agent that covers four of five core business functions; financial management (Stripe, QuickBooks) is listed as read-only and described as forthcoming. There is no self-host option and no API surface exposed to the user, so any team that needs to extend or integrate Team0 into a wider automation stack runs into a wall fast.

Paid

Stay in the Loop

Every Monday: 3 verified tools, one workflow pack worth grabbing, and the occasional skill. No filler.

No spam. Unsubscribe anytime.