A cockpit CLI running the whole Content Creation Chain as an agent-drivable pipeline: research → write → produce → distribute → measure → learn. First campaign: 45 videos driven end-to-end — JSON scripts rendered to 9:16 MP4s through headless chromium + ffmpeg, published via Instagram's official Content Publishing API, with real performance flowing back into a self-recalibrating playbook.
- Closed the loop — a 45-video campaign driven end-to-end: script → render → publish → measure → learn
- Structured creativity — every video a hook × cta × pain composition, with predictions banded and auto-verdicted against real performance
- A playbook that learns — daily debrief snapshots with actual numbers recompile the campaign playbook after every post
- Production rendering — headless chromium + ffmpeg pipeline turning JSON scripts into 9:16 MP4s
- Official API publishing — Instagram Content Publishing with per-post accounting in SQLite
typescriptagent-cliffmpeginstagram-api
Закрытый проект — медиа, подробности и демо по запросу.