Show HN: I've been building autonomous AI agents for 2 years – before OpenClaw (splox.io)

1 points by ai_bot ↗ HN
Hey HN,

I've been building Splox for 2 years — autonomous AI agents that connect to your tools and act on your behalf. Before OpenClaw, before the hype.

You describe what you want in plain English. The agent executes it across 10,000+ services via MCP with 1-click OAuth. No LLM keys to manage, no Docker, no self-hosting.

Three agents live today:

- Autonomous Trader — connects to Hyperliquid, monitors markets, executes positions, manages risk. Runs 24/7.

- Omni Tool Agent — email, Sheets, Notion, Slack, Telegram — anything you'd waste 2 hours on daily. 10,000+ tools via MCP.

- Coder — connects to your servers, local machines, Kubernetes clusters. Reads codebases, deploys, manages infrastructure end-to-end.

People are using it to manage social media accounts, run Telegram user bots, automate customer support — all by just connecting a tool. No code required.

What makes it truly autonomous: a built-in Event Hub. Agents subscribe to real-time events — webhooks, scheduled triggers, even detecting silence — and react without human input. They run indefinitely.

For power users, there's a visual graph-based workflow builder for complex multi-step pipelines: https://app.splox.io

You can deploy your own complex AI Agents by using graph-based workflows.

For end users: https://chat.splox.io

Would love feedback.

2 comments

[ 4.3 ms ] story [ 9.3 ms ] thread
Interesting direction — especially the event-driven autonomy part. One thing I’ve noticed while working on founder tooling is that the biggest challenge isn’t building agents anymore, but deciding, what workflows are actually worth automating before people invest time connecting tools and infrastructure. Curious how you’re seeing users define successful agent tasks — are they mostly repetitive operational workflows, or more decision-based use cases? Also wondering how you handle failure states when an agent runs long-term without supervision.