Kinocut is an open-source, local-first MCP server, Python library, and CLI tool for AI-agent-driven video editing. It provides typed FFmpeg tools, preflight guardrails, quality gates, and human-in-the-loop review for safe, auditable video processing. Designed for developers building AI agents that automate video editing workflows.
Kinocut sits in PulseGate's Frameworks & runtimes category. It focuses on enabling AI agents and developers to perform safe, auditable, and automated video editing with local guardrails and quality checks. It is built as an open-source project for AI developers and agent framework builders. Kinocut is open source under the Apache-2.0 license. It runs on the command line, and it can be self-hosted.
KyaniteLabs builds and maintains Kinocut, and it first shipped in 2026. Development happens publicly on GitHub with 80 stars and 701 commits in the last 90 days. Key capabilities include preflight guardrails, Video Receipts, and quality gates. The interface is available in English and Spanish. It exposes integrations via an MCP server.
Summary written by a language model from the project’s public pages.
What PulseGate has recorded for this listing
Closest matches by what these projects do