iBoost/Portfolio/Forpost

AI agents·2025 — now

Forpost

Video becomes news without a human in the loop: the system watches YouTube and TikTok, transcribes on GPU, rewrites into an article and publishes to Telegram and WordPress.

Our role

Product, architecture, GPU orchestration, SaaS layer

Status

Running in production

Period

2025 — now

Platform

Web · Telegram · WordPress · GPU fleet

AI AGENTS Forpost 01YouTube /TikTokmonitoring02Download andGPUtranscription03Summarisationinto a story04Per-chatpersonalisation05Publishing toTelegram / WP FASTAPI · NEXT.JS · POSTGRESQL · TIMESCALEDB · PGVECTOR · FASTER-WHISPER · OLLAMA IBOOST.UA · 2025 — now

System map · internal perimeter, access under NDA

01

What it is

The idea is simple: a person follows a dozen creators so they do not miss anything important. Forpost does that instead. The system sees a new video, pulls the audio, transcribes it with Whisper large-v3 on GPU, compresses it into a news item with a local LLM, picks key frames — and delivers the finished text where it will be read: a Telegram channel or a website.

What started as one bot for internal use grew into a multi-tenant SaaS: every client has their own channels, their own tone and censorship settings, and data isolation enforced at the database level.

The system rents its own transcription GPUs — on Clore.ai with RunPod as fallback — because owning a card around the clock costs more than renting one by the hour under load.

02

capabilities

What it does

01

Channel monitoring

YouTube over RSS, TikTok over yt-dlp with bot-wall bypass. Polling every N seconds, a job queue and S3 checkpoints — an interrupted run does not start over.

02

GPU transcription

faster-whisper large-v3 on CUDA float16. Long videos are chunked and a four-hour per-run cap stops one stream from blocking the queue.

03

Transcript-based topic gate

A video lands in the right section based on what was actually said, not on the channel name. This removed most mis-filed publications.

04

Per-chat personalisation

Translation, tone, length and censorship configured per recipient. The same story reads differently for traders and for a general audience.

05

WordPress publishing

A dedicated publishing module with multilingual output and cover images. Crypto news ships daily in Ukrainian and English to the client’s blog.

06

GPU rented on demand

Our own orchestrator over Clore.ai: spin a node, warm the model, hand it work, shut it down. RunPod Serverless is the fallback path.

03

architecture

How it works

01

YouTube / TikTok monitoring

02

Download and GPU transcription

03

Summarisation into a story

04

Per-chat personalisation

05

Publishing to Telegram / WP

Under the hood

  • A FastAPI orchestrator on async SQLAlchemy with a Procrastinate queue living inside PostgreSQL — no separate broker.
  • PostgreSQL 16 with TimescaleDB and pgvector; tenant isolation through RLS and PgBouncer in transaction mode.
  • The worker ships as its own CUDA image with pre-baked models, so a node is productive the moment it boots.
  • MinIO for checkpoints and media, Caddy at the edge with automatic TLS.
  • A full observability stack: OpenTelemetry → Tempo, Prometheus, Loki, Grafana.
  • Whisper and the LLM run locally — client transcripts never leave for a third-party API.
FastAPINext.jsPostgreSQL · TimescaleDBpgvectorfaster-whisperOllamaDockerGrafana LGTM

04

scale

Numbers

large-v3

transcription model

4 h

cap per single run

2

GPU providers

17

containers in production