Build logs, notes, and research from running my own AI infrastructure.https://yash-jain.xyz/https://yash-jain.xyz/archive/multi-agent-fleet/https://yash-jain.xyz/archive/multi-agent-fleet/I got ambitious and tried to run a fleet of AI agents at once. The thing that broke wasn't what I expected — and it taught me more than the setup did.https://yash-jain.xyz/archive/memory-bridge/https://yash-jain.xyz/archive/memory-bridge/Every AI tool I use starts each session with total amnesia. I got tired of being the only one who remembered anything, so I built them a shared notebook.https://yash-jain.xyz/archive/llm-gateway-choice/https://yash-jain.xyz/archive/llm-gateway-choice/A supply chain attack, a proxy that held entire responses hostage, and 4x the memory. What switching the boring middle layer taught me.https://yash-jain.xyz/archive/context-window-traps/https://yash-jain.xyz/archive/context-window-traps/My agents kept summarizing conversations at 102k tokens on models that could handle 262k. The cause was invisible defaults stacked on invisible defaults.https://yash-jain.xyz/archive/vps-hardening-traps/https://yash-jain.xyz/archive/vps-hardening-traps/Cloud-init files that silently re-enable password auth, an ssh.socket unit that overrides your config, and a heredoc that ate half an API key. Everything on my checklist is a mistake I made first.https://yash-jain.xyz/archive/verify-dont-trust/https://yash-jain.xyz/archive/verify-dont-trust/Three times I believed a tool's website. Three times the actual code said otherwise. I'm not an engineer, but I learned to check the source — and it changed how I evaluate everything.https://yash-jain.xyz/archive/two-rail-networking/https://yash-jain.xyz/archive/two-rail-networking/I split my setup into two lanes: a public lane for APIs, a private lane for everything that should never touch the internet. The rule exists because I almost broke it.https://yash-jain.xyz/archive/research-pipeline/https://yash-jain.xyz/archive/research-pipeline/People ask how I produce research fast. The honest answer is a two-step pipeline plus one rule I never skip.https://yash-jain.xyz/archive/agent-infrastructure-roi/https://yash-jain.xyz/archive/agent-infrastructure-roi/57% of organizations have AI agents running, but the thing holding them back isn't cost or model quality — it's the plumbing. For a small business, that changes what to spend on.https://yash-jain.xyz/archive/enterprise-ai-platforms/https://yash-jain.xyz/archive/enterprise-ai-platforms/Two weeks, a 28-point scorecard, 100+ references — and I'm not an engineer, so I went looking for what the marketing pages don't say. The headline numbers are mostly not real.https://yash-jain.xyz/archive/india-data-centers/https://yash-jain.xyz/archive/india-data-centers/Rack densities tripling, up to 42 permits to open a facility, and a country at 17% of North America's capacity. The bottlenecks are cooling, power, and paperwork — not ambition.