-
Four agents, four lessons: how my local AI agent grew up
I built four AI agents on one home server in seven months. Each failed in a new way: code that was not running, reports that said all clear, tasks closed with no work, a deleted home folder. Each failure moved trust out of the model.
-
After the wipe: six habits that changed how I run my home lab
A test deleted my home folder in ten seconds. Recovery took two days; the habits it left took longer. Freeze before you fix, reboot on purpose, back up the boring files hourly, commit everything, and give agents their own user.
-
One machine, everything: what I would do differently, and what's next
One workstation runs my whole lab: Kubernetes, a 120,000-work library, honeypots, local AI. Seven months of records hold 253 mistakes. What one machine gave me, what it cost, what I would do from day one, and what comes next.
-
When my datasets started talking, the loudest link was my RSS feed
In May 2026 a linker joined my lab's separate security datasets into one graph. On 8 July its strongest cross-layer link turned out to be an RSS reader polling my own blog. 1,885 pairs became 6, and I learned to ask what chance would give.
-
One docker rm -f took down my whole k3s cluster
Freeing a busy port with docker rm -f by filter removed the external Postgres that holds my k3s cluster state: about 20 minutes of total outage. How k3s datastores work, why recovery was quick, and the guard rails I added.
-
The cleanup job that deleted 239,000 live search chunks
A nightly orphan-chunk sweep in my Elasticsearch library deleted 239k live chunks from 19.4k documents for four weeks. Why its liveness check was wrong, how I recovered, and the count-first circuit breaker that followed.
-
13 hours of question marks: a canary for LLMs that look healthy
After a llama.cpp router restart my main model answered every request with question marks for 13 hours while every health check stayed green. A known-answer canary now catches it within 10 minutes.
-
How small local models finish hour-long agent tasks
Left alone, my 9B agent closed tasks without doing them and invented a 10 KB report from an empty sub-agent result. Scaffolded task trees, evidence checks and deterministic gathering let it finish 66-minute projects.
-
A post-reboot check script for a one-machine home lab
A cold boot of my lab produced 37 failed jobs; three were real defects hidden for up to two weeks. Here is the read-only OK/FAIL script I now run after every reboot, and the failures it catches.
-
One GPU, many LLMs: the VRAM guards that stopped a driver deadlock
With 33.9 of 34.2 GB of VRAM in use, a desktop app triggered a 24.7 GB eviction and froze my GPU driver. Here is the VRAM budget and the two guards that now enforce it.
-
Swapping an 8 GB NVIDIA card for a 32 GB AMD GPU: what broke
I replaced an RTX 4060 Ti with a 32 GB Radeon AI PRO R9700 for local AI. Ten things broke, mostly silently; here they are with fixes, and the before-and-after throughput.
-
Hybrid search with bge-m3 and Elasticsearch: six lessons
What I learned building BM25 + kNN hybrid search with reciprocal rank fusion and bge-m3 on one shared GPU: an analyser mismatch (38 to 2,631 hits), RRF pitfalls, embedding timeouts and a highlighting limit.