mirror of
https://github.com/NousResearch/hermes-agent.git
synced 2026-05-07 02:51:50 +00:00
Meta-pipeline that wraps any video request — narrative film, product / marketing, music video, explainer, ASCII, generative, comic, 3D, real-time/installation — in a Hermes Kanban pipeline. Performs adaptive discovery, designs an appropriate team for the requested style, generates the setup script that creates Hermes profiles + initial kanban task, and helps monitor execution. Routes scenes to whichever existing Hermes skill fits each beat (`ascii-video`, `manim-video`, `p5js`, `comfyui`, `touchdesigner-mcp`, `blender-mcp`, `pixel-art`, `baoyu-comic`, `claude-design`, `excalidraw`, `songsee`, `heartmula`, …) plus external APIs for TTS, image-gen, and image-to-video. Kanban orchestration uses the `kanban-orchestrator` and `kanban-worker` skills. The single-project workspace layout, profile-config patching pattern, SOUL.md-per-profile model, and `--workspace dir:<path>` discipline are adapted from alt-glitch's original kanban-video-pipeline at https://github.com/NousResearch/kanban-video-pipeline. This skill generalizes those patterns across video styles and replaces the original string-replacement config patcher with a PyYAML-based one that touches only `toolsets` and `skills.always_load` (preserving security-sensitive fields like `approvals.mode`). Includes: - SKILL.md — workflow + critical rules - references/ — intake, role archetypes, tool matrix, kanban setup, monitoring, six worked examples - assets/ — brief / setup.sh / soul.md templates - scripts/ — bootstrap_pipeline.py (plan.json -> setup.sh) and monitor.py (poll + issue detection) Co-authored-by: alt-glitch <balyan.sid@gmail.com> |
||
|---|---|---|
| .. | ||
| bootstrap_pipeline.py | ||
| monitor.py | ||