I also set this up with my cameras and Frigate, which is linked to Home Assistant, using Object Classification. Everything runs local, I'm running it on an old Dell micro form factor pc with an 8th gen i5 cpu.

https://docs.frigate.video/configuration/custom_classificati...

€1500 can already get you 16.1kWh.

The investment point still stands, though you could argue both come with risk/reward, energy prices aren't guaranteed to be stable.

Alternative systems are closer to 5 years payback if you have access to off peak energy. 3-4%/year degradation is very high, battery packs available in the UK from Fogstar are rated at 8,000 cycles with a 95% depth of discharge.

FWIW my high voltage battery pack has almost 365 cycles and is still at 100% state of health.

FWIW i was just going off that fact that the warranty on the battery mentioned in the article only guaranteed >=60% after 10 years...

Interesting - how are you interacting and orchestrating this?

Not the parent, but:

https://omp.sh/

You define roles for different agents like this:

  modelRoles: 
    task: fireworks/kimi-k3-fast:high
    plan: fireworks/kimi-k3-fast:max
    slow: fireworks/kimi-k3-fast:max
    smol: fireworks/deepseek-v4-flash-0731:low
    tiny: fireworks/gpt-oss-20b
    vision: fireworks/qwen3.7-plus:high
    designer: fireworks/qwen3.7-plus:high
    advisor: openai-codex/gpt-5.6-sol:high
    main_worker: fireworks/kimi-k3-fast:high
    fast_worker: fireworks/deepseek-v4-flash-0731:low
    vision_worker: fireworks/qwen3.7-plus:high
    research_worker: fireworks/glm-5.2:medium
    code_worker: fireworks/kimi-k2.7-code-fast:high
    review_worker: anthropic/claude-fable-5:high
    security_review_worker: fireworks/kimi-k3-fast:max
    minimal_worker: fireworks/gpt-oss-20b
    default: fireworks/kimi-k3-fast
  task: 
    agentModelOverrides: 
      task: "@main_worker"
      sonic: "@fast_worker"
      scout: "@fast_worker"
      designer: "@vision_worker"
      librarian: "@research_worker"
      reviewer: "@review_worker"
      security-reviewer: "@security_review_worker"

Then you first say /plan and use some big model like K3. Finally the harness shows you a markdown you approve, and in approval you switch to a smaller model and reset the context. The smaller model gets the full plan and starts working on it. When done, you say /review and it spawns N review agents and returns the change suggestions. And you iterate on that.