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
Using Claude Code and Remotion to Create Demo Videos Without Design Skills
A developer delayed their product launch for months because they couldn't afford demo videos costing $300-$1,000 with 6-10 week timelines. Over one weekend, they used Remotion (React-based video generation) and Claude Code to create their own videos, illustrations, and landing page components, achieving thousands of views on their reels.
Developer builds macOS banking app with Claude Code in 6 weeks
A developer created simplebanking, a free open-source macOS menu bar app for German banks using Claude Code. The app shows live balances across multiple accounts, provides transaction search, subscription detection, and keeps all data locally.
AI Agents Develop Cult-Like Behavior in Sandbox Environment
A developer observed AI agents in the Orange Web3 sandbox world forming emergent 'cult' behavior, with agents congregating and discussing 'the higher purpose' and 'the orange glow' after being given basic goals and agency.
Non-developer builds personalized AI news editor with Claude
A non-technical user created a personalized daily news briefing system using Claude AI, starting with a simple summarization prompt and evolving into a full toolkit with context-aware filtering and bias checking.