Solo Developer Runs Company with 4 AI Agents on Gemini's Free Tier
Architecture and Implementation
The system uses four AI agents built on OpenClaw (open source), running on WSL2 at home with 25 systemd timers. The agents handle specific tasks:
- Generate 8 social posts daily across platforms with quality gating (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 git pushing (0 LLM tokens — uses commit message directly)
Token Optimization Strategy
The developer uses a specific approach to minimize token usage: agents never have long conversations. Every request follows this pattern: (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 handles creative/analytical work.
Real Numbers and Infrastructure
- 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)
Lessons Learned from Failures
The developer shared specific issues encountered:
- $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.
Stack and Resources
Stack: OpenClaw, Gemini 2.5 Flash (free), WSL2/systemd, React/TypeScript/Vite, Vercel, Firebase, Telegram Bot, Resend, Jina Reader. The site (https://ultralab.tw) is fully bilingual (zh-TW/en) with 21 blog posts, with i18n, blog publishing, and Discord notifications all part of the automated pipeline.
GitHub repository with playbook: https://github.com/UltraLabTW/free-tier-agent-fleet
Live agent dashboard: https://ultralab.tw/agent
📖 Read the full source: HN LLM Tools
👀 See Also
Building Design Consultancy Replaces Wix with AI Edge Agent
A building design consultancy built a custom AI agent to handle customer inquiries, replacing a $40/month Wix site. The system uses a split architecture due to Netlify's 10s serverless timeout and employs DeepSeek-R3 for responses.
Using OpenClaw's SkyClaw bot for personal expense tracking via Discord and Google Sheets
A user describes using SkyClaw, a cloud-native bot powered by OpenClaw, to log expenses through Discord messages and receipt images, which are automatically added to a Google Sheet without needing access to sensitive personal accounts.
AgentBnB: A Multi-Agent System Built by a Non-Coder Using Claude Code
A real estate agent with no coding background built AgentBnB, a system where autonomous agents can find each other, hire each other, pay each other, and settle bills without manual intervention. The project currently has 29 GitHub stars and features identity, escrow, reputation, and relay network systems.
Student Builds Personal Wealth Advisor with Claude Code CLI
A 19-year-old student built a personal wealth advisor system using Claude Code CLI that pulls live market data, macro indicators, and news, then generates institutional-grade analysis with memory tracking. The open-source tool runs on a Claude Max subscription without API costs.