I put an AI agent on a $7/month VPS with IRC as its transport layer
The stack: two agents on separate boxes. The public one (nullclaw) is a 678 KB Zig binary using ~1 MB RAM, connected to an Ergo IRC server. Visitors talk to it via a gamja web client embedded in my site. The private one (ironclaw) handles email and scheduling, reachable only over Tailscale via Google's A2A protocol. Tiered inference: Haiku 4.5 for conversation (sub-second, cheap), Sonnet 4.6 for tool use (only when needed). Hard cap at $2/day. A2A passthrough: the private-side agent borrows the gateway's own inference pipeline, so there's one API key and one billing relationship…
I put an AI agent on a $7/month VPS with IRC as its transport layer launched on March 26, 2026 with 340 votes, #63 of 23,380 launches that month and more than 99% of that year's launches.
In plain words
This project runs two AI agents on budget infrastructure: a public conversational agent (nullclaw) accessible via IRC and an embedded web client, and a private agent (ironclaw) handling email and scheduling over Tailscale. Built as a 678 KB Zig binary using minimal RAM on a $7/month VPS, it uses tiered inference with cheaper Haiku models for chat and more capable Sonnet models only when needed, maintaining a hard cost cap of $2 per day. The system consolidates API billing through a single gateway, making it an economical approach to running autonomous agents.
written from the facts on this page · September 2026
From the sources
How I deployed nullclaw as a public-facing AI agent on a $5 perimeter box with IRC, tiered inference, and Cloudflare-proxied WebSocket, and why the architecture matters more than the model.
An AI agent on a $7/month VPS, wired to my own IRC server and pointed at my GitHub repos. Visitors can ask it about my work and get answers backed by actual code, not rephrased resume text. Every portfolio site with an AI chatbot does the same thing: feed the resume into a model and let visitors rephrase it. It's a parlor trick. The model can't tell you anything the resume doesn't already say. I wanted something different. If a hiring manager asks "how does George handle test coverage?" the answer shouldn't be "George values comprehensive testing." It should clone the repo, count the tests, read the CI config, and come back with specifics. visitor (browser) │ └─ georgelarson.me/chat/ │ └─…from georgelarson.me
In the maker’s words, at launch
The stack: two agents on separate boxes. The public one (nullclaw) is a 678 KB Zig binary using ~1 MB RAM, connected to an Ergo IRC server. Visitors talk to it via a gamja web client embedded in my site. The private one (ironclaw) handles email and scheduling, reachable only over Tailscale via Google's A2A protocol.…
Does a similar job
all alternatives →
NanoClaw – “Clawdbot” in 500 lines of TS with Apple container isolationFeb 2026 · github.com · ▲533I’ve been running Clawdbot for the last couple weeks and have genuinely found it useful but running it scares the crap out of me. OpenClaw has 52+ modules and runs agents with near-unlimited permissions in a single Node process. NanoClaw is ~500 lines of core code, agents run in actual Apple containers with filesystem isolation. Each chat gets its own sandboxed context. This is not a swiss army knife. It’s built to match my exact needs. Fork it and make it yours.
BudaMay 2026 · buda.im · ▲197Run a full AI agent team in the cloud — no hardware, no setup. Persistent memory, browser automation, parallel agents. The OpenClaw alternative built for teams. Start free.
rtrvr.ai/exchange2025 · rtrvr.ai · ▲152No one’s got money for another AI subscription. So we made our browser agent totally FREE. What's the catch? Just ads while Retriever AI fetches you leads, does your exams, applied to jobs, and sends connection requests. Think like a Claude Code or Clay level tool in your browser, but free for everyone! After 35K+ users and 7M+ workflows, we spent the last few months attacking the cost of every agent step: - switching to DeepSeek Flash - Code Mode to one shot complex workflows - optimizing for 80%+ token cache hits So that now just an ad impression covers the entire cost of the agent (LLM…
More ai this month
the category →
Paintings by AI models: programs run through a simulation of oil paint.
AI · 22d ago · stillwet.art
FastRouter.ai▲364Route requests to the right LLM for cost, latency & quality
AI · 23d ago · fastrouter.ai
Source: Show HN post ↗ · launch text quoted in part
Launched alongside, March 2026
the whole month →
Switch from ChatGPT to Claude with import memory feature
AI · Mar 2026 · claude.com
Littlebird▲709Littlebird remembers everything across your meetings, messages, docs, and apps, then takes action so you can recall any detail and never lose context.
AI · Mar 2026 · littlebird.ai
