Show HN: I've been building autonomous AI agents for 2 years – before OpenClaw
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.
Our agents get their own identity: dedicated phone numbers, email addresses, comms channels. They operate 24/7 as persistent entities rather than ephemeral chat sessions. They handle inbound and outbound communications, manage workflows across tools, and maintain context over long-running interactions.
The thing nobody tells you about "autonomous" agents is that the hard part isn't getting them to work. It's getting them to work reliably at 3am on a Saturday when nobody's watching. We've spent the majority of our time on failure handling, security hardening, and making sure an agent with real credentials can't do something catastrophic when it encounters an edge case it's never seen before.
The event-driven approach you're describing with the Event Hub is interesting. Silence detection especially. We've found that knowing when something didn't happen is often more valuable than reacting to what did.
We recently wrote up a detailed architectural comparison between Gobii and OpenClaw that covers a lot of these patterns: always-on runtime design, event triggers, memory, browser execution, security posture. https://gobii.ai/blog/gobii-vs-openclaw/ Relevant here because the overlap between what you're building and what both of these projects are doing is pretty clear. The space is converging fast.
Curious how you're thinking about identity and trust boundaries for agents that have access to 10,000+ services. That's been one of our biggest areas of focus: scoping permissions so agents have exactly what they need and nothing more.
On identity and trust boundaries: each agent in Splox runs with isolated credentials scoped to the tools the user explicitly connects. Agents can't discover or access services beyond what's been granted. The MCP protocol helps here — tool access is defined per-connection, so permissions are inherently scoped rather than bolted on after the fact.
For the "3am on Saturday" problem — that's exactly why we built the Event Hub with silence detection. If an agent stops hearing from a service it's monitoring, it reacts to that. Subscriptions state persists across restarts.
The Event Hub is what makes the decision-based ones viable. Agents subscribe to real-time events and react based on triggers — you can use structured filters or even natural language conditions ("fire when the user seems frustrated"). So the agent isn't just on a cron loop, it's genuinely reacting to context.
On failure states: agents have built-in timeouts on subscriptions, automatic retries with exponential backoff, and silence detection (they can react to the absence of events, not just their presence). If something breaks, the subscription expires and the agent can re-evaluate. Long- running agents also persist their state across restarts so they pick up where they left off.
There's also a workflow builder where you connect multiple agents together in non-linear graphs — agents run async and pass results between each other. So you can have one agent monitoring, another analyzing, another executing — all coordinating without a linear chain
Once they hit limits or want more control, they move to the workflow builder and design custom graphs. That's where you get non-linear agent connections — multiple agents running async, passing results to each other. One monitors, one analyzes, one executes.
Abstraction is definitely the challenge as graphs grow. Right now we handle it by letting each node in the graph be a full autonomous agent with its own tools and context. So you're composing agents, not steps. Keeps individual nodes simple even when the overall workflow is complex.