AI Agent & Local GPU Automation: Deterministic Workflows + RTX 3060 Inference

A customer-support AI bot that answers questions and provisions free-trial accounts over Telegram and WhatsApp — TypeScript, grammY, a Cloudflare tunnel webhook, and a self-hosted LiteLLM gateway.

One of my scheduled jobs failed 29 times in a row because I put a model in a loop that only needed a string comparison. Here is the rule I use now.

Learn how to stage large video files inside a Dockerized Chrome container using the Docker Archive API, then attach them through CDP without sending the entire file over the browser WebSocket.

Chrome's "continue where you left off" never fires inside a Docker container. The three fixes that failed, the real root cause, and the 70-line keeper that works.

Why our newly deployed local TTS engine synthesized endless 'percent' repetitions instead of spoken Chinese, and how character normalization and n8n sandbox limits collided.

A debugging story: a Dockerized telegram monitor whose sendPhoto calls returned 400 from nginx/1.30.1 while getMe worked fine — an IPv6-only DNS answer, a wrong extra_hosts IP, and a multipart join that corrupted JPEG bytes.

A private, self-hosted memory layer for AI agents — mem0 API + LiteLLM + PostgreSQL with pgvector on a Synology NAS. Semantic memory under your control, not a third party's.

Why dumping source files into LLM prompts leads to token bankruptcy and hallucinated bugs, and how pre-indexed AST knowledge graphs slash context by 80%.

How I sync my Hermes agent's skills, config, and cron jobs between two PCs with a git-backed profile distribution — and why I sync manually instead of on a cron.

Why letting multiple AI agents write code causes race conditions and drift, and how a single-writer architecture with isolated reviewers fixes it.

Over 30 days, autonomous coding agents added 518,000 lines across 5 repos, yet production kept 235,000. Here is why verification gates matter more than generation.

Why swarms of autonomous coding agents step on each other, play the telephone game, and make implicit conflicting decisions that break repositories.

AI music tools give you audio and nothing else — no line timings, no karaoke. Here is the pipeline I use to produce LRC and SRT subtitles for 18 songs, why plain transcription fails, and the two bugs that made the lyrics box scroll to the bottom.

A reading app needed TTS. Cloud free tiers expire tokens in 10 minutes and 1 hour. Here's the sidecar pattern that kept Azure and Google voices working for a year with no secrets in any workflow.

I run a self-hosted speech-to-text API on a single GPU PC. Dictation works from Windows, iPhone, iPad and Android — private, unlimited, and over 3x faster than typing.

How I migrated our production automation workflows from cloud speech APIs to a self-hosted CosyVoice 2 pipeline on a 12GB RTX 3060, integrated with Synology N8N.

Claude Opus and GPT are stronger than anything I can run locally. Here is the cost, control, and uptime argument for owning a GPU anyway — with real numbers.

A complete production breakdown of building a 4-minute 1080p anime OP music video (Crescent Bay): AI music generation, Gemini storyboard prompting, iterative image-to-video rerolls, and Filmora VFX editing.

AI music tools cut off complex tracks mid-sentence. Here is how I solved the 240s duration wall using YuE2 BF16, 295s headroom budgeting, and a 60-song pipeline.

Explore an automated music video workflow using Remotion, Whisper, Docker and Chrome DevTools Protocol, from lyric alignment and rendering to YouTube publishing and multilingual subtitles.

Measured on an RTX 3060: Wan 2.2 TI2V-5B generation, SeedVR2 upscaling, the 1080p resolution trap, and the one command that fixed five failed runs.

Twelve Mandarin songs came out exactly 240.000 seconds long with the outros missing. The cause wasn't the lyrics — it was a hard cap, a VRAM ceiling, and a planner that ignores BPM.