Open-source product engineering / Video workflow tooling
Reelora.
A preservation-first automatic Reel director, FFmpeg renderer, MCP adapter, and installable ChatGPT Skill for turning raw or already-generated footage into structured vertical video edits.
Explore public source ↗01 / THE PROBLEM
Make the process visible.
Automated editing can easily become a pass-through resize, overuse effects, ignore uploaded sources, or alter the product story. Reelora makes source coverage, real edit changes, audio replacement, crop behavior, and product preservation explicit and verifiable.
02 / THE APPROACH
Turn requirements
into useful work.
The project analyzes source footage, plans shots, reframes landscape input for vertical output, applies deterministic FFmpeg editing, supports multi-source coverage, handles music and premium transitions, and emits audit metadata about the rendered result.
- Video workflow and product architecture
- FFmpeg rendering pipeline
- MCP and ChatGPT Skill adapters
- Quality validation and audit metadata
- Release automation and CI
03 / SCOPE & EVIDENCE
What you can inspect.
These notes describe an internal product-engineering project, not a client engagement. Scope and technical descriptions come from the existing WebTayo case study; no performance or commercial outcome is claimed.
Review the linked repository for current implementation details, release history, tests, and documented limitations.
Open source repository ↗