Pinned Tweet
Hi, I'm Danny.
I'm an AI engineer building autonomous agents and automation systems.
On this account I share:
• AI agent architectures
• Real production workflows
• Tools and integrations
• Lessons from building systems
Follow if you're building with AI.
Google's Gemma 4 runs fully on-device on Android — no cloud, no API cost, no data leaving your phone.
Performance exceeded my expectations.
If this keeps improving, API providers are going to lose a significant chunk of their customer base. Sooner than they think.
#Gemma4
When building production AI agents, what’s the ONE thing you prioritize the most?
A. Cheap / $0 infra (Oracle Free, local, etc.)
B. Fast latency & performance
C. Robust error handling & retry logic
D. Easy monitoring & observability Vote below and tell me why in the comments.
1/8
Most people think running LLM “locally” means buying expensive GPUs.
I run my AI agents (including the Morning Brief pipeline) on Oracle Cloud Free Tier — zero extra cost, no GPU, and it’s been stable for months.
Here’s exactly how I do it without breaking the bank. 🧵
7/8
This is a simple but production-grade pattern: cheap infra + smart proxy + constrained prompts.
I use the same approach for other agents too — autonomous, observable, and maintainable.
6/8
Biggest lessons from running this in production:
- ARM + CPU inference works surprisingly well for agent workflows (not just chat)
- Signal vs noise starts at the proxy level, not just the prompt
- Over-engineering for speed is the #1 way to burn free tier resources
5/8
Performance in real use (Morning Brief agent):
- End-to-end latency: usually 30–50 seconds
- Main bottleneck: LLM inference step (not fetching)
- Handles daily summarization + structured output without issues
Not the fastest, but reliable and completely free.
4/8
Key optimizations to stay $0:
→ Use quantized/small models or fast Flash-Lite variants
→ Strict rate limiting & caching in OpenClaw
→ Fail-safe: fallback to a lighter model if latency spikes
This keeps everything within the free 3000 OCPU-hours/month.
3/8
My setup for OpenClaw+LLM layer:
- Instance: Oracle Linux ARM (Ampere A1 Flex)
- Proxy: OpenClaw (local OpenAI-compatible endpoint)
- Backend: Gemini 2.5 Flash-Lite routed through the proxy (or Ollama for fully offline)
- Scheduling: Simple cron
No API key rotation headaches.
2/8
Oracle Always Free Tier gives you:Up to 4 ARM OCPUs (Ampere A1)
- 24 GB RAM
- 200 GB block storage
- 10 TB/month outbound traffic
All forever free (as long as you stay within limits).Perfect for lightweight, quantized LLM inference.
1/11
I built an AI Morning Brief Agent that runs every morning with zero manual intervention.
It fetches, filters, and delivers the most important AI news to Discord automatically.
Oracle Cloud Free Tier → $0/month
Here's the full architecture 🧵
11/11
Simple. Production-ready. Zero-maintenance.
Next:
→ Per-topic sub-briefs
→ Pre-LLM article scoring
→ Weekly trend digest
What agents are you building?
Want me to open-source this?
👇 Drop your thoughts below
10/11
The real insight:
Fetching news is easy. Signal vs noise is hard.
25 articles in → 3–5 items out.
That curation ratio, enforced through prompt constraints alone, is what makes it actually useful.
9/11
Full stack:
• Python
• feedparser + requests
• OpenClaw → Gemini 2.5 Flash-Lite
• Discord webhook
• Oracle Cloud Free Tier (ARM A1)
Total cost: $0/month.
8/11
One cron job. Runs every morning.
Fails? Error embed fires to Discord automatically.
Zero manual intervention. Ever.
7/11
Output — clean Discord embed every morning:
◆ AI MORNING BRIEF ◆
TITLE
• Time: …
• Fact: …
• Why it matters: …
• Source: url
———
Radar: hot topic / trend / risk
6/11
LLM runs through OpenClaw — a local proxy on my Oracle Cloud instance.
Payload: model = "openclaw", input = "[prompt]"
No direct API key exposure. Everything routes through the local proxy.