YoloCut

YoloCut

Enables AI agents and MCP clients to programmatically edit video projects on a local desktop editor, with 119 tools for multitrack editing, effects, captions, audio, and batch auto-editing, producing reviewable and reversible real timeline edits.

Category
访问服务器

README

<p align="center"> <img src="assets/favicon.svg" width="96" alt="YoloCut logo" /> </p>

<h1 align="center">YoloCut</h1>

<p align="center"> <strong>Edit by hand. Delegate to agents. Keep the timeline under your control.</strong> </p>

<p align="center"> Open-source desktop video editing · Detachable Agent workspace · External MCP access · Hardware-aware 4K workflows </p>

<p align="center"> <a href="README_ZH.md">简体中文</a> · <strong>English</strong> </p>

<p align="center"> <a href="https://github.com/Hhz0823/YoloCut/releases/tag/v0.0.2"><img alt="Release v0.0.2" src="https://img.shields.io/badge/release-v0.0.2-0A84FF?style=flat-square" /></a> <img alt="Desktop platforms" src="https://img.shields.io/badge/desktop-Windows%20%7C%20macOS%20%7C%20Linux-3A3A3C?style=flat-square" /> <img alt="Agent tools 119" src="https://img.shields.io/badge/Agent_tools-119-30D158?style=flat-square" /> <a href="LICENSE"><img alt="AGPL-3.0-or-later" src="https://img.shields.io/badge/license-AGPL--3.0--or--later-FF9F0A?style=flat-square" /></a> </p>

<p align="center"> <a href="https://github.com/Hhz0823/YoloCut/releases/tag/v0.0.2"><strong>Download v0.0.2</strong></a> · <a href="#connect-an-external-agent">Connect an Agent</a> · <a href="#run-from-source">Run from source</a> · <a href="https://github.com/Hhz0823/YoloCut/issues">Report an issue</a> </p>

<p align="center"> <img src="assets/readme-pic/02-yolocut-editor.jpg" alt="YoloCut v0.0.2 desktop editor with multitrack timeline and Agent workspace" /> </p>

A new kind of video editor

YoloCut is a local-first desktop editor where a human and an Agent work on the same real project. Trim and arrange clips on the timeline, or ask the built-in Agent, Codex, Claude Code, Gemini CLI, Cursor, or another MCP client to use the same editing commands.

This is not a one-shot video generator that returns an opaque result. Agent work becomes normal media, tracks, clips, captions, transitions, effects, keyframes, and export jobs. You can preview it, review the proposed changes, apply or reject them, undo them, and continue editing by hand.

Media + script + editing goal
        ↓
Agent creates a reviewable edit session
        ↓
Real timeline changes → preview → refine → export

Why YoloCut

One editing core Agent-native workspace Built for real desktop hardware
Manual UI and Agent tools converge on the same EditorCore command layer. Dock the Agent left or right, detach it into a wide window, or connect an external MCP client. Proxy editing, decoder fallbacks, workload admission, and GPU-aware export keep long high-resolution projects usable.

Product tour

<table> <tr> <td width="50%"> <img src="assets/readme-pic/01-yolocut-dashboard.jpg" alt="YoloCut v0.0.2 project dashboard" /> <br /><sub><b>Local project dashboard</b> — create, search, import, copy, export, and manage projects.</sub> </td> <td width="50%"> <img src="assets/readme-pic/03-yolocut-agent.jpg" alt="YoloCut Agent skill library and detachable Agent workspace" /> <br /><sub><b>Agent workspace</b> — reusable workflows beside the same multitrack project.</sub> </td> </tr> <tr> <td width="50%"> <img src="assets/readme-pic/04-yolocut-effects.jpg" alt="YoloCut effects library" /> <br /><sub><b>Effects library</b> — masks, keying, color tools, LUTs, shaders, transitions, and motion effects.</sub> </td> <td width="50%"> <img src="assets/readme-pic/05-yolocut-mcp.jpg" alt="YoloCut external Agent MCP connection center" /> <br /><sub><b>External Agent connection</b> — live endpoint, Bearer token, health checks, and the required edit-session flow.</sub> </td> </tr> </table>

All screenshots above were captured from the current YoloCut v0.0.2 desktop application.

What is available in v0.0.2

Area Current capabilities
Timeline Multitrack video and audio, move, trim, split, ripple trim, slip, rate stretch, snapping, markers, keyframes, undo, and redo
Preview and canvas 25%–400% zoom, pan mode, custom output sizes, safe areas, composition guides, and clip transforms
Text and captions Transcription jobs, transcript editing, silence cleanup, captions, translation, styling, and SRT export
Audio Voice-over recording, multitrack mixing, sound effects, music analysis, loudness tools, ducking, and voice isolation
Visual system Masks, chroma key, grading, scopes, LUTs, WebGL/GLSL effects, transitions, and motion-graphics templates
Agent Built-in chat Agent, reusable Skills, proposals, approval policy, progress, history, and the canonical 119-tool catalog
Batch editing Media folders, edit scripts, narration scripts, reference videos, durable queues, per-job projects, QA, and status readback
Local and cloud AI Local ASR/TTS/model packs plus configurable third-party LLM, image, video, music, and sound providers
Desktop runtime Immediate native startup shell, parallel embedded server startup, deferred heavy services, isolated smoke profiles, and stage-level startup tracing
Delivery MP4, audio, SRT, FCPXML, portable project packages, export history, and hardware-aware H.264 routing

Agent-native by design

The detachable Agent workspace is a control surface, not a decorative chat sidebar:

  • It shares project state and editing commands with the manual UI.
  • It can dock left or right, open as a separate wide desktop window, and return to the editor through corner docking.
  • Mutating work is staged in an edit session for review before it is considered applied.
  • The built-in Agent and external MCP clients use the same canonical 119-tool catalog.
  • When no project is open, YoloCut exposes only the smaller server-direct surface and reports the limitation honestly.

<p align="center"> <img src="assets/readme-pic/yolocut-runtime.en.svg" alt="YoloCut editor, Agent, MCP, media, and export architecture" /> </p>

Connect an external Agent

Install the YoloCut Agent Skill:

npx skills add Hhz0823/YoloCut --skill yolocut

Start YoloCut, open the target project, then open Agent Connection Center (MCP) and copy its live URL and Bearer token. The default endpoint is:

http://localhost:5199/api/external-mcp/mcp

The desktop application can choose another loopback port when 5199 is occupied, so clients should use the address displayed by the connection center rather than permanently hard-coding the default.

Required completion flow:

yolocut_status → get_connection_manifest → list_projects → target_project
→ load_skill / ToolSearch → begin_edit_session → editing tools
→ review_edit_session → get_edit_session (status=applied)

An Agent should report completion only when full editing is ready, capability coverage is complete, and the final edit session is applied. Configuration examples for Codex, Claude Code, Gemini CLI, Cursor, and generic Streamable HTTP clients are in YOLOCUT_AGENT_CONNECTION.md.

Batch auto-editing

Give YoloCut a media directory, edit script, narration script, and optional reference video. The durable queue accepts up to 10,000 jobs, with a separate project and lifecycle for every output instead of placing thousands of videos on one timeline.

  1. Scan an authorized local media directory.
  2. Attach the edit script, narration script, and optional reference cut.
  3. Analyze rhythm, shot structure, captions, transitions, and color intent.
  4. Let the Agent create reviewable edits with hardware-aware concurrency.
  5. Render, quality-check, and read back success, failure, or cancellation per job.

Optional local reference analysis uses the Apache-2.0 SmolVLM2-500M-Video-Instruct-GGUF package with llama.cpp. Missing models or runtimes fail visibly; YoloCut does not fabricate an analysis result.

Long 4K projects on modest machines

YoloCut separates the interactive proxy path from final-quality media. Analysis and preview can use smaller derivatives while final export reads the original files.

  • NVIDIA systems prefer NVDEC → scale_cuda → NVENC after live capability probes.
  • H.264 routing probes NVENC, Intel QSV, AMD AMF, and then software libx264.
  • AV1, VP9, and unsupported hardware paths can fall back to FFmpeg software decoders such as libaom-av1 and libvpx.
  • CPU, memory, VRAM, codec support, and active workload decide proxy size and queue concurrency.
  • Runtime results show the backend that was actually used and any fallback reason; model or GPU names alone are never treated as proof.
Hardware tier Conservative editing policy Local narration recommendation
Unrecognized GPU / low-end PC 540p proxy, one analysis job, one render job Kokoro CPU fallback
RTX 2060 6 GB 540p proxy, NVDEC/NVENC when proven available Kokoro 82M ONNX, WebGPU preferred with CPU fallback
RTX 4060 8–9 GB 720p proxy, up to two analysis jobs, protected single render Fish Audio S2 Pro with s2.cpp + Q6_K (experimental)
RTX 5060+ 8–9 GB 1080p proxy, up to three analysis jobs, protected single render Fish Audio S2 Pro with s2.cpp + Q6_K (experimental)
RTX 40/50 series with at least 10 GB VRAM Higher-quality local inference while preserving render headroom Fish Audio S2 Pro with s2.cpp + Q8_0 (experimental)

Fish S2 model weights use the Fish Audio Research License. Commercial use requires separate written permission. Hardware tiers are conservative policy contracts, not performance guarantees for every driver and machine.

Faster desktop startup

YoloCut v0.0.2 now stages desktop startup instead of blocking the first window on the complete editing stack:

  • Electron displays a lightweight native startup shell before loading the embedded application server.
  • The server starts in parallel, while GPU discovery continues asynchronously after the editor becomes usable.
  • Models, thumbnails, updater checks, and the packaged render runtime are deferred until the relevant feature or post-startup window needs them.
  • Renderer surfaces and dashboard dialogs stay behind lazy boundaries so the full editor graph is not part of the initial dashboard load.
  • Desktop smoke tests use a unique temporary profile and data directory, preventing tests from touching a user's projects, credentials, media, or live YoloCut process.

On the Windows release-verification machine, the unpacked build displayed its native shell in about 85 ms, brought up the embedded server in about 0.72 s, and loaded the first renderer in about 2.79 s on a cold run; a warmed renderer loaded in about 0.51 s. These are diagnostic measurements from one machine, not cross-device guarantees. Set YOLOCUT_STARTUP_TRACE=1 when launching the desktop build to print stage timings for another system.

Download

Platform v0.0.2 package
Windows x64 YoloCut-v0.0.2-x64.exe
macOS Apple Silicon YoloCut-v0.0.2-arm64.dmg
macOS Intel YoloCut-v0.0.2-x64.dmg

GitHub Release assets intentionally contain only the directly installable Windows .exe and macOS .dmg files. Installer SHA-256 values are listed in the release notes rather than attached as another asset. Windows packages are currently unsigned; macOS packages are ad-hoc signed but not notarized.

Linux remains built and smoke-tested in CI but is not attached to GitHub Releases. Linux users can run YoloCut from source using the instructions below. Packaged builds use the in-app version check and open the GitHub Release page for manual installation when an update is available.

Run from source

Requires Node.js >=24 <25 and npm.

git clone https://github.com/Hhz0823/YoloCut.git
cd YoloCut
npm install
cp .env.example .env.local
npm run dev

Desktop development and Windows packaging:

npm run desktop:dev
npm run desktop:dist:win

Development profiles isolate projects, media, credentials, tasks, and settings per Git checkout/worktree. Configure only the AI or media providers you actually intend to use.

Data and security

  • Projects, chat, versions, indexes, and settings are local by default under ~/.yolocut.
  • Existing legacy data roots can be mounted by the migration layer so users do not lose earlier projects.
  • Provider keys stay on the service side and are not exposed through VITE_ browser variables.
  • MCP binds to loopback by default and requires a generated Bearer token.
  • Directory access uses opaque grants; absolute local paths do not cross the desktop IPC boundary into Agent tools.
  • AI traffic leaves the computer only for providers the user explicitly configures.
  • YoloCut targets a single-user desktop workflow, not an unisolated multi-tenant server deployment.

Architecture and verification

Layer Main responsibilities
src/editor/ Immutable timeline state and editing commands
src/agent/ Agent runtime, tools, Skills, proposals, approval, and progress
src/gl/ WebGL effects, transitions, and shader runtime
src/transcript/, src/captions/ ASR, transcript editing, captions, and translation
src/persist/ Projects, versions, media metadata, and batch jobs
server/ Local HTTP, MCP, models, media processing, jobs, and exports
desktop/ Staged Electron startup, windows, hardware probing, secure storage, and native IPC
remotion/ Headless rendering and deliverable exports
npm test                         # full regression suite
npm run build                    # type checking and production build
npm run lint                     # static analysis
npm run verify:architecture      # enforced dependency boundaries
npm run verify:mcp               # Agent/MCP contract checks
npm run verify:media-performance # codecs, proxies, acceleration, fallbacks
npm run verify:auto-edit         # batch auto-edit contracts
npm run desktop:smoke             # embedded server and desktop bridge
npm run desktop:smoke:render      # real packaged rendering path
npm run desktop:smoke:post-startup # deferred startup work
npm run desktop:smoke:agent-window

Current release boundaries

YoloCut 0.0.2 is an early public release. Core editing, Agent, MCP, batch, desktop packaging, and local model management are actively verified, but several surfaces remain experimental:

  • Fish S2, SmolVLM2, and some GPU paths depend on local runtimes and drivers.
  • The project format and Agent catalog will continue to evolve; back up important projects before upgrades.
  • Signing and notarization are not yet production-grade.
  • A configured provider or installed model is required for its corresponding AI feature; manual editing remains available without one.

See CHANGELOG.md for version history and GitHub Releases for published artifacts.

License, provenance, and contributing

YoloCut is independently maintained by hhz0823 and licensed under the GNU Affero General Public License v3.0 or later.

The codebase continues from the AGPL-licensed 0xsline/OpenChatCut project. This attribution preserves source and license provenance; upstream branding, contributors, community channels, and commercial relationships are not part of the YoloCut product or its public release history.

Third-party libraries, models, fonts, skills, and bundled binaries retain their own licenses. See THIRD_PARTY_NOTICES.md, src/agent/skills/NOTICE.md, and assets/fonts/LICENSES.md.

推荐服务器

Baidu Map

Baidu Map

百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。

官方
精选
JavaScript
Playwright MCP Server

Playwright MCP Server

一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。

官方
精选
TypeScript
Magic Component Platform (MCP)

Magic Component Platform (MCP)

一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。

官方
精选
本地
TypeScript
Audiense Insights MCP Server

Audiense Insights MCP Server

通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。

官方
精选
本地
TypeScript
VeyraX

VeyraX

一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。

官方
精选
本地
graphlit-mcp-server

graphlit-mcp-server

模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。

官方
精选
TypeScript
Kagi MCP Server

Kagi MCP Server

一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。

官方
精选
Python
e2b-mcp-server

e2b-mcp-server

使用 MCP 通过 e2b 运行代码。

官方
精选
Neon MCP Server

Neon MCP Server

用于与 Neon 管理 API 和数据库交互的 MCP 服务器

官方
精选
Exa MCP Server

Exa MCP Server

模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。

官方
精选