Launchpad by Gigeey

Build Your Team... without hiring one

Productivity

Open Source

Artificial Intelligence

Visit WebsiteSee on Product Hunt

Hey Product Hunt 👋 I'm Axew, a maker of Launchpad Studio. The journey to building this was sparked by a frustration we couldn't shake - it seems like every other week, LLMs are trading the spot for best at a set of tasks or better still, an OS/OW model becomes significantly more capable. We however kept feeling like we were locked into one or two providers because their tools were just good enough to get us by and we'd become too comfortable using them to easily switch or try different models/products. So over a year ago we started building a provider and model agnostic surface. But we did not just want another window with a chat box. We wanted it to be something we enjoyed using, and hopefully you will see that in the product decisions big or small. And because we will be open sourcing this, we hope the community can help steer the product to the direction we will collectively find most useful. There's lots of features available and even more in the pipeline but here are a few notable mentions through the lens of the autonomy ladder: Hand over as little or as much as you trust an agent with. Each rung does more on its own than the last. 1 Agents & profiles: This is the smallest unit of Agency. A specialist you shape once and reuse — its own persona, curated skills and tools, memory, and model/provider — instead of one generalist you re-brief every time. 2 Address books & delegation: Agents hand work to each other through a curated address book. Mix and match model sizes and providers to extract the most out of your agents. Larger models can be used for the heavy thinking, and hand off grunt work to smaller, faster, and cheaper models. 3 Tasklists: Multi-step work gets broken into steps, each run by a fresh, focused agent instance — the structured replacement for a hand-rolled "keep looping until done" prompt - this replaced the Ralph loop for us 4 Projects: Hand over a whole goal. An agent interviews you to capture intent, drives itself through tasklists, and can only call it done once an independent verifier agrees. 5 Assignments: The top rung — agents that start themselves, on a cron schedule, a webhook, or when a connected data source changes. No one has to ask. Hand off work to your daily drivers so that your changing preferences are incorporated immediately without requiring you to update this elsewhere