AI agents run my one-person company on Gemini's free tier – $0/month
I'm a solo dev in Taiwan. I built 4 AI agents that handle content, sales leads, security scanning, and ops for my tech agency — all on Gemini 2.5 Flash free tier (1,500 req/day). I use ~105. Monthly LLM cost: $0. Architecture: 4 agents on OpenClaw (open source), running on WSL2 at home with 25 systemd timers. What they do every day: - Generate 8 social posts across platforms (quality-gated: generate → self-review → rewrite if score < 7/10) - Engage with community posts and auto-reply to comments (context-aware, max 2 rounds) - Research via RSS + HN API + Jina Reader → feed…
In plain words
A solo developer in Taiwan built four AI agents that automate content creation, sales lead handling, security scanning, and operations for a tech agency, all running on Google's free Gemini tier with no monthly cost. The agents generate and quality-review social posts daily, engage with community discussions, research industry news from multiple sources, run security scans for lead generation, and monitor customer data. The system runs on a home machine using open-source OpenClaw with automated timers, optimizing token usage to stay within the free tier's limits.
written from the facts on this page · September 2026
From the sources
In the maker’s words, at launch
I'm a solo dev in Taiwan. I built 4 AI agents that handle content, sales leads, security scanning, and ops for my tech agency — all on Gemini 2.5 Flash free tier (1,500 req/day). I use ~105. Monthly LLM cost: $0. Architecture: 4 agents on OpenClaw (open source), running on WSL2 at home with 25 systemd timers. What they do every day: - Generate 8 social posts across platforms (quality-gated: generate → self-review → rewrite if score < 7/10) - Engage with community posts and auto-reply to comments (context-aware, max 2 rounds) - Research via RSS + HN API + Jina Reader → feed intelligence back into content - Run UltraProbe (AI security scanner) for lead generation - Monitor 7 endpoints, flag stale leads, sync customer data - Auto-post blog articles to Discord when I git push (0 LLM tokens — uses commit message directly) The token optimization trick: agents never have long conversations. Every request is (1) read pre-computed intelligence files (local markdown, 0 tokens), (2) one focused prompt with all context injected, (3) one response → parse → act → done. The research pipeline (RSS, HN, web scraping) costs 0 LLM tokens — it's pure HTTP + Jina Reader. The LLM only touches creative/analytical work. Real numbers: - 27 automated Threads accounts, 12K+ followers, 3.3M+ views - 25 systemd timers, 62 scripts, 19 intelligence files - RPD utilization: 7% (105/1,500) — 93% headroom left - Monthly cost: $0 LLM + ~$5 infra (Vercel hobby + Firebase free) What went wrong: - $127 Gemini bill in 7 days. Created an API key from a billing-enabled GCP project instead of AI Studio. Thinking tokens ($3.50/1M) with no rate cap. Lesson: always create keys from AI Studio directly. - Engagement loop bug: iterated ALL posts instead of top N. Burned 800 RPD in one day and starved everything else. - Telegram health check called getUpdates, conflicting with the gateway's long-polling. 18 duplicate messages in 3 minutes. The site (https://ultralab.tw) is fully bilingual (zh-TW/en) with 21 blog posts, and yes — the i18n, blog publishing, and Discord notifications are all part of the automated pipeline. Live agent dashboard: https://ultralab.tw/agent Stack: OpenClaw, Gemini 2.5 Flash (free), WSL2/systemd, React/TypeScript/Vite, Vercel, Firebase, Telegram Bot, Resend, Jina Reader. GitHub (playbook): https://github.com/UltraLabTW/free-tier-agent-fleet Happy to answer questions about the architecture, token budgeting, or what it's actually like running AI agents 24/7 as a one-person company.
Does the same job
all alternatives →- IPI put an AI agent on a $7/month VPS with IRC as its transport layerMar 2026 · georgelarson.me · ▲340
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…
OpenClaw BusinessJun 2026 · cloudacropolis.com · ▲12What would you hire 4 people to do? This does it for €129/mo
- IMI Made an AI Software Engineer with Google Gemini 1.5 Flash2024 · saas-quick.com · ▲6
Hey HN! Thank you for all the support and feedback on my original submission 2 months ago. I've been improving the backend using a MCTS/AlphaZero approach and it's currently producing much better results. My long term goal is to allow users to manage multiple projects, deployed autonomously, both from scratch and by making continual updates all prompted with natural language. The cost of each project has been lowered to $9 as performance with smaller models has improved (I migrated from Claude-3-Opus to gemini-1.5-flash). Thanks for checking it out!
- CBClink – Bring your own CLI Agents, Ship instantlyOct 2025 · clink.new · ▲22
Clink lets you use the coding agents you already pay for (Claude Code, Codex CLI, Gemini CLI, Z.ai GLM) to build → live-preview → ship apps in an isolated container. No token purchases, no extra cost for coding. Just link your existing Claude/OpenAI/Gemini account and start building and deploying instantly. Why we built this: Claude Code is our go-to for coding, but it lacked preview + deploy capabilities. We didn't want to pay Lovable again just for that. Different agents excel at different tasks - Claude Code for versatility, Codex for complex work, GLM for speed. We needed one…
More ai this month
the category →
I trained a 125M-parameter transformer to autocomplete piano performances in real time (~108 notes/sec on an iPhone 15). The idea is basically GitHub Copilot or Tabnine, except instead of prompting it with code, you prompt it by playing a few notes on a MIDI piano. The model then continues what you played, entirely on-device. The app is free if anyone wants to try it. Happy to answer questions about the model, training, Core ML, or the many things that didn't work.
AI · 17d ago · simedw.com
Astute▲585Automate your B2B brand going viral, with new media creators
AI · 18d ago · company-app.joinastute.com
Hey HN, Henry from Cactus here! We previously released Cactus Needle, a 14MB agentic LLM for tool call, device use, and structured extraction for phones, wearables, smart homes, small robots and microcontrollers. We got really great feedback here, and have now incorporated the suggestions to release Needle 2. The whole model is a single 14MB binary that runs a full session in 28MB of RAM; 45m parameters at 2bit compression. Needle hits 500 tokens/sec decode speed on a Raspberry Pi 5, sits between 400-1,500 tokens/sec on VR devices like Meta Quest 3S and Apple Vision Pro, and ranges…
AI · 27d ago · cactuscompute.com
Launched alongside, March 2026
the whole month →
Switch from ChatGPT to Claude with import memory feature
AI · Mar 2026 · claude.com
