Watering the garden just got easier
This is more than a programmable tap with a timer. My own local AI oversees the watering now. It reads soil moisture from sensors in the beds, checks the weather, and decides whether each zone actually needs water. If a bed is already damp, it skips the cycle. If it’s been hot and dry, it waters longer
The setup is simple: a small home-automation hub, a two-zone smart water valve, and a few wireless soil sensors. One zone feeds the flower beds, the other feeds the vegetable garden and containers. Everything talks locally over Zigbee, so it still works even without internet
The part I like best is that it’s my own setup; local ai, opensource software, my hardware. The schedule, the data, the decisions - none of it lives in someone else’s cloud, app or platform.
It’s practical: plants stay alive, water doesn’t get wasted, and I don’t have to stand there with a hose.
What actually works in our OpenClaw setup (and the pain it fixed)
If you're spinning up OpenClaw and hitting the usual walls (context overflow, wrong model for the job, forgotten conversations, flaky pipelines), here's the stack and discipline that got us past it.
1. MRDE: route before you prompt
We built a Model Routing Decision Engine so every request hits the right model tier first, not after trial and error.
• Local private: sensitive stuff stays on-device (gemma-4-26B-MLX, ornith:9b for fast local lanes).
• Local heavy: deep reasoning when latency doesn't matter (ornith:35b, qwen3.6-35b for legal).
• Cloud coding/synthesis: complex troubleshooting (kimi-k2.7-code:cloud, kimi-k2.6:cloud, deepseek-v4-flash:cloud).
• Cloud fast fallback: quick answers when local is cold (gemma4:31b-cloud).
Pain solved: no more asking a 2.8T-parameter cloud model to grep logs, and no more running private queries through cloud APIs by accident.
2. Two-tier memory + RAG
• Immutable corpus: law sources, primary docs, transcripts. Append-only, never rewritten.
• Evolving memory: daily notes, decisions, lessons, atomic reports. Rewritten and refined.
• RAG v2: 10 corpora, ~66k chunks, all embedded. The assistant recalls before answering, then writes back compact, cited notes.
Pain solved: the system stops hallucinating continuity. It actually remembers yesterday, last week, and the source of the claim.
3. The loop: capture → recall → act → write back
Everything runs on a small, durable loop:
• Capture: drop it in the inbox (AirDrop, Telegram, share sheet, cron).
• Recall: search memory + RAG before any real work.
• Act: use the right tool/model for the task.
• Write back: one compact note with provenance (file path, source ID, or daily note).
For bigger tasks we add a gauntlet: run the output through critic models, check facts, verify file hashes, then keep or repair.
Pain solved: slop dies here. The system produces fewer, higher-quality artifacts instead of endless chat noise.
4. Scheduled pipelines (the nightshift)
A single cron at 02:00 dispatches phased jobs: I/O-bound tasks, then cloud API tasks, then local ML/vision, then reflection/audit. Local-ML concurrency is capped at 1 so vision models don't fight for the GPU.
Pain solved: long-running jobs finish overnight instead of interrupting the day, and the Mac doesn't melt.
5. Voice as default input
Whisper STT → local LLM → Kokoro TTS. Zero API cost, hands-free, and it actually gets used.
Pain solved: typing long prompts on mobile is miserable. Voice removes friction.
Advice for new OpenClaw builders
• Lock your default model before you build a dozen workflows. Routing is cheaper than re-prompting.
• Write memory back immediately after meaningful work, not at end of day.
• Use small verification loops (syntax checks, dry runs, file hashes) before trusting any autonomous edit.
• Run heavy/local-ML jobs in a single queue with concurrency caps, not in parallel cron storms.
• Prefer local TTS/STT once it's good enough. The cost and latency win is real.
The big shift: stop treating OpenClaw like a chatbot and start treating it like an operating system with memory, scheduling, and routing. The rest follows.
#OpenClaw #LocalAI #AIAgents #ai
Confession: It’s been a while since my last post on Nostr
I’ve been busy.
Lots going on IRL, some good, some bad - but it’s kept me tied up.
My ai assistant is helpful - but the time spent working on it absorbed the time gained by using it. I feel more organized-
The signal : i finally got a few moments to look at social media and I go to Nostr not some crumby platform. 😁
Hope you all have the best day ever.
Was just thinking back on this moment.
This a good friend, Nick Sherman playing a song of his on a borrowed guitar, down on Whiskey Dock, waiting for a ride.
We had one hell of a visit, he played a bunch of gigs including an impromptu concert in my gallery with Myles Morrison backing him up. We went to a punk show, stayed out till the sun came up. It's a moment I really appreciate for how cool it was.
Sometimes the simplest things are the best.
No production just me and my phone
Funny thing; I like this version better than the studio recording, lol
Anthropic publicly accused Moonshot, DeepSeek and MiniMax of “industrial scale fraud”
Yes, they were using Claude to train their own models, but they paid to use it - I mean, this is basically the 'recursive self improvement' loop that devs predicted will precede the singularity 😛
Slap in the face for Anthropic after their response to Openclaw sent it's developer into the open arms of OpenAi
Things are getting spicy.
🍿 🦞
I went to an art supply store today… left without buying anything, crazy 🤪
Normally I’m like : when you said ‘friends with benefits’ I thought you owned an art supply store. 😉
Price in sats is high right now, kills me to buy anything.
ʔuuqsap (Serenity) by Mark Penney
24x48" acrylic on canvas
Raffled in support Pacific Rim Arts Society
Serenity is the absence of anxiety and fear.
#themarkpenney #painting #coastal #art #artsr #original #markpenney