While I slept, my 5-year-old MacBook ran Gemma 4 locally and indexed a year of video — simbastack

I'm in the Maasai Mara about half the year, in three-month stretches. Animals out the front of the lodge, motorcycles, friends in the Maasai villages, kids who think a drone is the funniest thing they have ever seen. That's one half of my year. The other half is sixteen-hour days in front of a terminal, Silicon Valley hacker brain on Africa time. Both real, both consuming attention.

The first half is a constant flood of footage from the iPhone, the DJI Pocket, the drone, the Nikon Z8, and lately the Ray-Ban Metas too. There's always something being recorded. Every photographer or videographer I know is sitting on the same problem: an archive that grows faster than they can edit it. The second half is why mine never gets touched.

Airport security somewhere between Nairobi and Spain. Two trays of cameras, headphones, drone bits, batteries, SSDs, more cables than anyone needs. Most of it records something. Almost none of what they record gets touched again any time soon.

Three months ago the lodge's social channels went dark. Not for lack of content; the lodge has years of raw footage across multiple SSDs. The bottleneck was editing time, and my time disappeared. Claude Code with Opus 4.5 (and then 4.6) hit the point in February where you could leave agents running for hours and come back to merged PRs. KaribuKit was going live with its first paying property in the same window. I stopped sleeping properly, started running three or four agents in parallel in the background, and the months when I would have cut reels turned into months when I shipped software instead.

So one weekend I sat down to fix it. The first thing I tried was wrong.

The wrong layer

The initial pitch (to myself, after about an hour of research) was a SaaS stack: Eddie AI for iterative editing, Higgsfield MCP for generative B-roll, Submagic for captions, Buffer for cross-posting. About $140 a month, slick on paper.

Two problems showed up before I ran any of it.

First, generative AI video has no place on a real travel brand. Guests pay $300 a night and up to see the actual place, and mislabeled AI shots equals TripAdvisor crucifixion. Higgsfield out.

Second, 3-5 posts a week was aggressive for me, and the realistic floor was more like 2-3. The pitch was optimistic in a way that would have me failing by week two.

Then I remembered I already own DaVinci Resolve Studio, and Resolve 21 ships IntelliSearch (semantic clip search), Smart Bins (auto-organizing folders), and Voice to Subtitle that produces 90-95% accurate captions on the timeline. That's roughly 70% of what Eddie sells, so Eddie was out too.

What I was left with was Claude Code driving Resolve via the open-source DaVinci Resolve MCP, with ElevenLabs handling voiceover on informational clips where it earned its place, and the cost had dropped from $140 a month to $22.

But the deeper thing only landed once I tried to actually use any of this. Every AI video editor on the market assumes your footage is already labeled. Mine is IMG_*.mov and DJI_*.mp4 across folders with names like Mara june 2024 backup final FINAL. Eddie can search by transcript, but none of these tools can find "the elephant on the hill at golden hour" against an unlabeled archive.

The AI editor is solving the wrong problem. Or more precisely, it's solving the second problem; the first problem is the index.

The question

I asked it out loud: how does the agent know what's in each clip?

There's no answer for an unlabeled archive. You can throw transcripts at it, GPS coordinates, filenames, parent folders. None of that gives you "the wide shot at sunrise with the giraffe in the frame" unless something has actually looked at the pixels.

The leverage is upstream. Build the index first, make the archive queryable in English, and the editor on top becomes a thin layer doing what it was designed to do.

So I built the index, locally.

The build

This is the kind of AI-native build I do for clients at SimbaStack, except I was both the client and the engineer this time, which made the decision tree a lot shorter.

Four constraints set the shape:

Local-first. The Mara Hilltop archive is on physical SSDs, and most of the personal stuff is on my laptop. Cloud upload was a non-starter both for cost (thousands of files, many gigabytes per clip) and for not handing the entire visual record of my life to a third party.

Sidecars, not a central database. A .description.md per clip, living next to it, plain text and grep-able. Survives if my indexer breaks tomorrow, and travels with the data when files move between drives.

One vision call captures everything. The expensive operation is the vision pass over the extracted frames, so anything I might want to know about a clip later has to come out of that one call. The schema is exhaustive on day one: rating, technical quality, lighting, time of day, color palette, audio...