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
Local Fine-Tuning of Llama 3.2-1B for Secret Detection Surpasses Wiz's Model
A developer replicated and improved upon Wiz's secret detection model using purely local AI, achieving 88% precision and 84.4% recall with Llama 3.2-1B. The process involved dataset augmentation with procedural generation and local labeling using Qwen3-Coder-Next.
Local vs VPS OpenClaw deployment: practical differences for AI coding agents
Running OpenClaw locally provides real browser access with existing login sessions and local file access, while VPS deployment limits functionality to basic tasks and faces website restrictions.
Meet Claude: A Visual Novel Created Entirely by AI
A developer created a satirical visual novel called Meet Claude using Claude AI for writing, coding, art, music, and deployment. The game explores dependency on AI assistants and is available free on Steam with multiple endings.
Autonomous Claude Code Loop Runs Open-Source GymCoach 24/7 — Triages, Codes, Merges
Developer lets Claude Code run an open-source fitness app autonomously: triage issues, implement PRs, pass green-gate checks, merge, and document — all without human intervention.