User repository on GitHub
Agent Skill and Python CLI for local video remixing, Jev judgments, and originality reports.
- Forks
- 1
- Last pushed
- Updated Oct 2026
Repo stats from the GitHub API, cached Oct 2026.
Jev directory
CommunityJev Agents & MCP
Jev Remix Cutter
An independent agent skill and Python CLI for local video remixing: shot-aware slots for beats and original narration are filled under Jev judgments and constrained orchestration, then rendered into a reviewable cut with originality and asset-license reports.
- Stars
- 16
- Language
- Python
- License
- MIT
- Reading time
- 3 min
- Published by
- Community
- Author
- gnipbao
- Last verified
- Oct 2026
Highlights
- Agent skill plus Python CLI for local remixing: shot-aware slots, Jev judgments, constrained orchestration and a reviewable cut with originality reports.
- Version 0.1.0 pins jev-1.13.0 and bundles jevkit 1.0.0; it stays separate from jev-highlight-cutter and imports from it read-only via --from-highlight.
- Needs Python 3.11+ (3.12 verified) plus FFmpeg and ffprobe with libass and libx264; venv, media and run output stay outside the skill directory.
- Jev reads the user-global TYPESAFE_API_KEY and doctor only reports present or absent; --key-file is a fallback for when the global variable is missing.
- One authorized run made real Jev text calls; some responses failed the probability-distribution contract, and mock demos only validate the pipeline.
Quickstart
bash
mkdir -p "$HOME/.local/share/jev-skills"
git clone https://github.com/gnipbao/jev-remix-cutter.git "$HOME/.local/share/jev-skills/jev-remix-cutter"
SKILL="$HOME/.local/share/jev-skills/jev-remix-cutter"
python3.12 -m venv "$HOME/.local/share/jev-remix-cutter/venv"
PY="$HOME/.local/share/jev-remix-cutter/venv/bin/python"
"$PY" -m pip install -e "${SKILL}[core]"
"$PY" "$SKILL/scripts/remix.py" doctor --jsonWatch out
README reviewed 2026-10-17; the digest truncates mid-sentence in the first remix tutorial, so the full walkthrough was not captured. The README itself reports that one authorized run made real Jev text calls with some probability-distribution contract failures, image-provider calls never ran for real, and M7/M8 compositing, anonymization, face swap and E4 blind tests remain unfinished.
Questions about this entry
Short answers drawn from the linked project or page.
An independent agent skill and Python CLI from gnipbao for local video remixing, built by the author of jev-highlight-cutter: it fills shot-aware slots for beats and original narration, has Jev judge them, and renders a reviewable remix with originality and asset-license reports.
Jev judges the candidate slots: the README says the project pins jev-1.13.0 and bundles jevkit 1.0.0, and its own status notes report that a real authorized run returned some values that failed the probability-distribution contract and none passed the automatic cast hard threshold.
With Python 3.11+ (3.12 verified) and FFmpeg/ffprobe with libass and libx264, clone the repo under ~/.local/share/jev-skills, create a venv, pip install -e "${SKILL}[core]", then run scripts/remix.py doctor --json; media and results must live outside the skill directory.
Yes, both are gnipbao projects, but they are not merged: jev-remix-cutter is an independent skill and CLI that can import highlight-cutter output read-only through the --from-highlight flag instead of depending on it.
It is version 0.1.0, a CPU-first implementation; image-provider calls never ran for real, M7/M8 advanced compositing, anonymization, real face swap and E4 blind tests are unfinished, and mock demos only validate the pipeline.
Jev needs a user-global TYPESAFE_API_KEY, with --key-file only as a fallback when that variable is missing; the README reports core dependencies tested on CPU (NumPy, OpenCV 4.14, librosa and PySceneDetect), and the optional image provider uses JEV_REMIX_VLM_* environment variables.
Codex users run scripts/install_skill.py, which symlinks the repo under ~/.codex/skills and stores only the interpreter path in ~/.config/jev-remix/runtime.json; the project installs from GitHub source and the README says it is not published to PyPI yet.
More Jev resources like this
An agent skill plus Python CLI that turns long interviews and podcasts into evidence-based highlight reels: the agent reads the transcript, Jev scores the text evidence, and local FFmpeg cuts a rough cut that fits your taste and target duration.
Jev Agents & MCP#community#github#python
Communitygnipbao/jev-highlight-cutterPython
gnipbao/jev-highlight-cutterPythonA Claude skill and API from tomascupr that turns any video link into one typed JSON document: summary, chapters, scenes, cast, key moments, the emotional arc, brands, on-screen text, and the full transcript. Jev then judges those fields so your code can branch on probabilities.
Jev Agents & MCP#community#github#claude
Community
tomascupr/reelqlHTML
tomascupr/reelqlHTMLA zero-embedding approach to video intelligence from DeepAleph: jevreel lays a video out on labelled contact sheets, one frame per second and sixty frames to an image, and has Jev judge every sheet in parallel. Your coding agent gets moments, times and probabilities back over MCP.
Jev Agents & MCP#community#github#mcp
Community
deepaleph/jevreelPython
deepaleph/jevreelPythonLocal-first MCP memory server for IDEs: tree-sitter indexing into a local ChromaDB store, plus an optional Jev layer that screens retrieved passages for relevance, evidence, contradiction and prompt injection.
Jev Agents & MCP#community#github#python
Community
KikeVen/zerikai_memoryPython
KikeVen/zerikai_memoryPythonAn auto-clipper that turns long videos into short standalone clips: code enumerates every plausible cut point, Jev judges the clip each candidate edge would make, and you get ranked mp4s for Shorts, Reels and TikTok.
Jev Tools & CLIs#community#catalog-import#logicrw
Community
vbs2004/jevcutPython
vbs2004/jevcutPythonA local System One decision layer for AI coding agents, shipped as an MCP server and Agent Skill, that offloads high-volume classification, checks, scores and ranking from frontier LLMs to sub-50ms local models with calibrated output.
Jev Agents & MCP#community#github#mcp
Community
aktonay/snapdecPython
aktonay/snapdecPythonFrom the Jev guides
Original write-ups on what this entry is for.
From the Jev AI model community
Posts from builders shipping with Jev right now.