Open source video editors that launched on a fresh machine
Editors and cutters for video, ordered by whether each one installed and came up when Argusic tried it fresh, desktop apps on a virtual display, with the recorded session one click away.
Tested between and . Each row shows its own test date; a project can change after that day.
66 of 72 tested projects run. 2 more waiting for a test.
In short: 44 of the 72 tested projects started as-is on a fresh machine: lossless-cut, rea-video, ffmpeg-skill, openfilm, FunClip, auto-editor, vidcutter, and capcut-cli, and 36 more. 22 more started once a stand-in replaced a service they expect, such as a database: AI-Youtube-Shorts-Generator, open-genjutsu, Adobe_Premiere_Pro_MCP, MotionClone, ghost-editor, chatgpt-video-editing-skills, premiere-pro-mcp, and opensource-clipping, and 14 more. 6 could not be verified: ai-video-editor, clip-js, fabric-video-editor, Kiwi-Edit, Light-A-Video, and Kiri; the log shows where each one stopped.
Measured by Argusic on a fresh machine every time. Every number links to its evidence.
| # | project | verdict | Argusic Score | language | stars | tested on |
|---|---|---|---|---|---|---|
| 1 | lossless-cut | Runs | 100 / 100 | TypeScript | 46,323 | |
The swiss army knife of lossless video/audio editing What the test found: All 93 vitest tests pass (11 test files), the Electron app launches via xvfb and logs version 3.69.0, initializes config, and stays running under Xvfb. 20 minutes. | ||||||
| 2 | rea-video | Runs | 100 / 100 | Python | 12,138 | |
Reverse-engineer any video, shot by shot: filmed, AI-generated or coded, and how to remake it. Breakdowns in the open VIDEO.md format. 逆向一切视频,逐个镜头看是拍的、AI... What the test found: rea-video 0.1.0 is installed, all 88 unit tests pass, decompose produces full breakdown.json/report.html/report.md, summary prints per-shot verdicts, probe shows metadata, tiles extracts frames, capability matrix validates, and install_skill.sh links skill to agent directories. 25 minutes. | ||||||
| 3 | ffmpeg-skill | Runs | 100 / 100 | Python | 9,611 | |
Local video editor for coding agents: 42 FFmpeg tools with a machine-readable contract and an MCP server, for Claude Code, Cursor and Codex. Cut, captions... What the test found: The repo installs via npx ffmpeg-skill, doctor reports 0 required capabilities missing, the MCP server answers initialize with ffmpeg-skill 2.10.3 and tools/list with 12 tools, both full test suites pass on clean output directories (907 + 169 tests, all OK with only skips), and cut/fit/caption/loudness produced files... 72 minutes. | ||||||
| 4 | openfilm | Runs | 100 / 100 | TypeScript | 8,974 | |
The open source AI video agent: turns any coding agent into a video agent, with editors to change anything it makes. What the test found: All three workspace packages install, build, and pass their full test suites (104+18+104 tests); the openfilm CLI renders films to valid MP4 frames using Playwright with a headless Chromium browser. 6 minutes. | ||||||
| 5 | FunClip | Runs | 100 / 100 | Python | 6,622 | |
FunASR-powered video transcription, subtitle generation, and LLM-assisted clipping tool with a local Gradio UI. What the test found: FunClip v2.2.1 is fully installed in a Python 3.12 venv with all dependencies, all 90 tests pass, the CLI recognition+clipping pipeline processes a real video with Paraformer-Large ASR and produces valid clipped MP4 output, and the Gradio web interface launches and serves HTTP 200 on localhost. 49 minutes. | ||||||
| 6 | auto-editor | Runs | 100 / 100 | Nim | 6,052 | |
Effort free video editing! What the test found: auto-editor builds and runs: processes MP4 files with audio-level-based silence detection and h264+aac re-encoding, producing valid output with zero decode errors. 40 minutes. | ||||||
| 7 | vidcutter | Runs | 100 / 100 | Python | 2,002 | |
A modern yet simple multi-platform video cutter and joiner. What the test found: VidCutter 6.0.5.2 GUI launches under offscreen Qt platform, connects to real libmpv 0.37.0 with FFmpeg 6.1.1, shows version and help output, and logs runtime configuration from the playback engine. 12 minutes. | ||||||
| 8 | capcut-cli | Runs | 100 / 100 | TypeScript | 1,250 | |
Independent, unofficial CLI to edit CapCut and JianYing (剪映) projects, subtitles, timing, speed, volume, templates, cut long-form to shorts. No API needed... What the test found: capcut-cli v0.25.0 installs, builds, and passes all 981 tests on Node 18.19.1 x86-64 Linux with ffmpeg and ffprobe available. 4 minutes. | ||||||
| 9 | agent-plugin | Runs | 100 / 100 | JavaScript | 1,080 | |
AI video editor for agents. ChatCut plugin and MCP server for Codex, ChatGPT, Claude Code, Cursor, Grok, Gemini CLI, WorkBuddy, Doubao Work and Qwen Work: edit... What the test found: All 110 tests pass across 9 test files including plugin metadata validation, symlink integrity, serve-local-media HTTP server (CORS, range, origin, TTL), store package building, and skill content checks. 2 minutes. | ||||||
| 10 | FableCut | Runs | 100 / 100 | JavaScript | 806 | |
Zero-dependency browser video editor that AI agents can drive, JSON timeline, MCP + REST, live-reloading UI What the test found: Zero-dependency browser video editor FableCut v1.7.0 boots on port 7777, serves the UI and REST API, passes all 37 unit/integration tests, the MCP server initializes correctly, and ffmpeg 6.1 is available for fast export. 1 minute. | ||||||
| 11 | vit | Runs | 100 / 100 | Python | 740 | |
Git for video editing. What the test found: 100/100 tests pass; vit CLI fully works with real git backend; AI merge degrades gracefully without GEMINI_API_KEY; Resolve panel scripts import cleanly (tkinter panel excluded due to missing tkinter in headless container). 3 minutes. | ||||||
| 12 | openclip | Runs | 100 / 100 | Python | 585 | |
OpenClip - AI-powered highlight extraction for long videos (AI 驱动的长视频精彩时刻提取工具) What the test found: OpenClip dependencies installed, all 156 tests pass, and the Streamlit web app starts and responds with HTTP 200. 5 minutes. | ||||||
| 13 | kk-mix | Runs | 100 / 100 | Python | 566 | |
Windows 批量视频混剪工具,15 项批处理功能 | A Windows batch video editing toolkit, 15 batch operations. What the test found: kk-mix v10.3.0 installed with Python 3.12 in uv virtualenv, GUI launches with offscreen/vnc platform, i18n check passes, 5 worker types (split/compress/rotate/volume/concat) produce valid FFmpeg output verified via decode. 6 minutes. | ||||||
| 14 | autoclip | Runs | 100 / 100 | Python | 523 | |
Open-source, local-first AI video clipper. Long video in, caption-burned speaker-tracked 9:16 clips out. Fully offline with Whisper + Ollama, or bring your own... What the test found: The AutoClip web app is installed and running: the pytest suite passes 294 tests, the frontend builds to backend/autoclip/static, and the live server answers HTTP 200 on /api/health, /, /docs, /api/caption-styles, and /api/system (all served from a Node-20 frontend build and Python 3.12 backend). 4 minutes. | ||||||
| 15 | ViralForge | Runs | 100 / 100 | TypeScript | 521 | |
Agent-native viral video studio: one-click replicate viral short videos, deconstruct video hooks and scripts into a Viral DNA report, and ship 10 costed... What the test found: npm install, npm run build, and all 4 test suites (readme, smoke/e2e, media, mcp) pass with 0 failures. The dev server and preview server serve the studio UI. The CLI, MCP server, Playwright E2E tests, and media analysis all function without external API keys. 4 minutes. | ||||||
| 16 | dramaxis | Runs | 100 / 100 | TypeScript | 466 | |
🎬 Dramaxis (剧枢), 电影级多智能体影视叙事与智能解说平台 (Tauri 2 + Rust + React 19)。6 大智能体协同导演、5 轨毫秒级对齐时间轴、四道质量闸门硬核质检、本地优先沙箱架构与剪映草稿深度互通。 What the test found: All 280 frontend tests pass, frontend production build succeeds (299 modules), 10 of 11 Rust workspace crates compile and all their tests pass (core=13, intake=17, export=18), VitePress docs build succeeds. Tauri desktop shell (root Cargo.toml + update crate) blocked by missing libwebkit2gtk-4.1-dev system packages... 11 minutes. | ||||||
| 17 | velocut | Runs | 100 / 100 | TypeScript | 452 | |
AI-native, local-first video editor by Ribbi, runs entirely in the browser. Rust/WASM engine, WebGPU compositing, WebCodecs export; humans and LLM agents edit... What the test found: Velocut is fully operational: the TypeScript reference engine runs under Vite with all 62 unit tests and both Playwright E2E journeys passing, the Rust golden-vector test suite passes, and the WASM canonical engine compiles and drops into the editor's public directory. 7 minutes. | ||||||
| 18 | qiaomu-cut-skill | Runs | 100 / 100 | JavaScript | 389 | |
乔木智能视频导演 Skill:素材治理、双语字幕、品牌包装与可复现渲染 | Agent-native video director with governed sourcing and verifiable rendering What the test found: qiaomu-cut v0.5.0 installs with zero npm dependencies, doctor confirms ffmpeg 6.1.1 with full capability (libass, drawtext, overlay, loudnorm, sidechaincompress, xfade, libx264), all smoke tests and release checks pass, file narration renders to verified h264/AAC video, plan/workflow/list commands produce correct... 2 minutes. | ||||||
| 19 | WeftCut | Runs | 100 / 100 | TypeScript | 385 | |
Free, open-source AI video editor for macOS, Windows and Linux, drive the whole timeline from any MCP client. What the test found: WeftCut v0.4.0 builds successfully on Linux x64: both napi addons compiled (@weftcut/core exports 17 symbols, @weftcut/native-decode compiled with ffmpeg-lgpl), ffmpeg and ffmpeg-lgpl resources staged, vitest suite runs 9284 of 9288 tests passing, all 20 Rust eval-crate tests pass, 99 of 100 script tests pass. 31 minutes. | ||||||
| 20 | Orkas-VideoStudio | Runs | 100 / 100 | TypeScript | 350 | |
Open-source alternative to Claude Motion and CapCut: your coding agent (Claude Code, Codex, Cursor) edits footage, designs motion graphics, adds narration and... What the test found: The repository installs, builds, typechecks, benchmarks, and passes all 282 unit tests plus 47 E2E tests including a real three-scene video production pipeline that composes HTML motion graphics, renders via HyperFrames 0.7.60 with chrome-headless-shell, burns captions with ffmpeg, and passes the delivery... 12 minutes. | ||||||
| 21 | capsule-cinema | Runs | 100 / 100 | Python | 328 | |
把视频做成模版,一次配方无限视频 · Turn videos into templates. One recipe, unlimited videos. What the test found: Capsule Cinema is installed as a Codex skill at /home/runner/.codex/skills/capsule-cinema with 17 active video capsules, all Python dependencies installed in /tmp/venv, ffmpeg verified, npm test passes, the unit test passes, and the quickstart checklist confirms the system is ready for project introduction videos... 4 minutes. | ||||||
| 22 | FrameScript | Runs | 100 / 100 | Rust | 325 | |
Video editing software with TypeScript(tsx) What the test found: The FrameScript project is fully installed: npm dependencies installed, studio and render Vite dev servers serve HTTP 200, Rust backend serves 6 working endpoints (healthz, is_canceled, render_log, render_audio_plan, reset), Electron v43.0.0 binary is present and responds to --version, and all build artifacts (dist/... 10 minutes. | ||||||
| 23 | vegas-pro-23-desktop | Runs | 100 / 100 | C++ | 304 | |
VEGAS Pro 23 2026 desktop setup with timeline editing, color correction, keyframe animation and DVD/Blu-ray authoring tools for Windows 11 What the test found: The C++ binary iobit-util compiles and runs, answering --version with 0.3.1 and --help with usage instructions. The static docs page serves at HTTP 200. 2 minutes. | ||||||
| 24 | pycaps | Runs | 100 / 100 | Python | 235 | |
Create beautiful, animated video subtitles with Python and CSS. What the test found: Installed pycaps from the repo with all extras in a venv; pycaps CLI answers help; all 14 bundled tests pass; a real 4-second mp4 with SRT subtitles rendered end to end through the default CSS/Playwright renderer into a valid h264+aac mp4 with visible caption frames. 3 minutes. | ||||||
| 25 | Cliparr | Runs | 100 / 100 | TypeScript | 231 | |
Create clips from media on your personal media server What the test found: The project installs, builds, passes its workspace and browser tests, and its production server answered 200 on /api/health and / with a working SQLite database. 5 minutes. | ||||||
| 26 | cutcli-cookbook | Runs | 100 / 100 | JavaScript | 203 | |
Cookbook, JSON templates, AI prompts and docs for cutcli, the CapCut / Jianying (剪映) draft CLI. Generate editable video drafts from code, Cursor, Claude Code... What the test found: cutcli 1.3.13 installed, cookbook lint suite passes 4/4 checks, VitePress docs build generates the full site, and examples 01 and 03 produce working CapCut drafts with captions. Examples 02, 04, 05 fail only because their CDN-hosted demo assets return 404. 2 minutes. | ||||||
| 27 | get-brolls | Runs | 100 / 100 | - | 11 | |
GET BROLLS, proprietary software. Access through the Engenheiro de Vídeo community. What the test found: Get B-rolls 2.5.2 installed and verified: Python 3.12 venv with yt-dlp/yt-dlp-ejs, Node 22.11 with Playwright CLI, ffmpeg 6.1 with drawtext; CLI runs all subcommands; test suite passes ~1058 tests; Wikimedia Commons live search confirmed working; local file resolve works end-to-end. 34 minutes. | ||||||
| 28 | premierepro-video-editor-2026 | Runs | 100 / 100 | HTML | 2 | |
PremierePro-Video-Editor-2026: Professional Multi-Track Video Editing with Lumetri Color and 4K/8K E What the test found: The TypeScript module 'sharp-portal' installs, the greet() function runs producing 'hi world', and the example works, but the repository does not contain any video editing software as its README claims. 2 minutes. | ||||||
| 29 | AI-Powered-Video-Tutorial-Generator | Runs | 98 / 100 | Python | 322 | |
Create and edit AI video tutorials with illustrated lessons, expressive presenters, distinct voices, and a native timeline. Windows desktop app with local... What the test found: All 6 workspace packages build successfully. JS unit tests pass 156/156 (packages/contracts/scenes/themes). Renderer tests pass 100/117 (17 pre-existing version-mismatch failures). Python pipeline tests pass 942/956 (2 pre-existing failures: Linux path normalization vs Windows test, and stale manifest byte count). The... 22 minutes. | ||||||
| 30 | flowblade | Runs | 96 / 100 | Python | 3,109 | |
Video Editor for Linux What the test found: Flowblade Movie Editor 2.24 launches and runs its GTK3 GUI with MLT 7.22.0, initializing the player with HD 1080p 30fps profile. 30 minutes. | ||||||
| 31 | OpenWorldLib | Runs | 96 / 100 | Python | 894 | |
Unified Codebase for Advanced World Models. What the test found: OpenWorldLib installed in Python venv, all 39 pipeline packages import successfully, DepthAnything pipeline runs end-to-end on CPU producing real depth map output from a HuggingFace model. 11 minutes. | ||||||
| 32 | subvert | Runs | 96 / 100 | PHP | 868 | |
Generate subtitles, summaries, and chapters from videos in seconds What the test found: The project builds with all Composer and npm dependencies installed, the test suite passes 4 tests with 9 assertions covering the full processing pipeline and HTTP routes, and the Laravel development server starts and serves HTTP 200 on the root endpoint. 15 minutes. | ||||||
| 33 | claude-remotion-skill | Runs | 95 / 100 | TypeScript | 1,249 | |
Open-source Claude agent skill that teaches Claude Code, Claude Desktop & Claude AI to create and edit professional motion graphics videos with Remotion. AI... What the test found: The Remotion examples project installed, audio synthesized to deterministic WAVs, and three of four compositions (SelfFix, CodeEdit, HaidrrrryPromo) rendered to valid H.264 MP4s with no ffmpeg errors; node 18.19.1, npm 9.2.0, ffmpeg 6.1.1. 3 minutes. | ||||||
| 34 | OpenCut | Runs | 94.7 / 100 | TypeScript | 99,162 | |
The open-source CapCut alternative What the test found: Web app dev server starts on port 5173 and returns 200 on root. API server starts on port 8788 and returns 200 on /, /health, and POST /echo. Desktop binary builds and links at target/release/opencut-desktop but cannot launch (no GPU). Rust cargo check passes with warnings. Web production build succeeds (client + SSR). 27 minutes. | ||||||
| 35 | splicr | Runs | 93.3 / 100 | TypeScript | 466 | |
🎬 Dramaxis (剧枢), 电影级多智能体影视叙事与智能解说平台 (Tauri 2 + Rust + React 19)。6 大智能体协同导演、5 轨毫秒级对齐时间轴、四道质量闸门硬核质检、本地优先沙箱架构与剪映草稿深度互通。 What the test found: Frontend installs, type-checks, builds, and its full Vitest and Playwright suites pass (157 unit tests, 8 e2e tests), and all 12 non-GUI Rust crates build and pass 79 unit plus 2 doc tests; the Tauri desktop shell still cannot be compiled because its system GTK/WebKit dev libraries are absent from this container. 28 minutes. | ||||||
| 36 | showtime | Runs | 92 / 100 | Python | 344 | |
A local video studio for your coding agent. Describe a video in one sentence: your agent directs, your machine renders. Claude Code, Codex, Cursor, Devin and... What the test found: showtime 0.4.1 installed and working: creates and renders 1080p videos with audio, QA passes, MCP and preview servers respond, 80/82 test files pass. 58 minutes. | ||||||
| 37 | autoclip | Runs | 90.7 / 100 | Python | 13,312 | |
AutoClip|一个链接,一键出片。开源 AI 视频剪辑桌面工具,将播客、访谈、课程等长视频自动剪成短视频,生成字幕、封面和发布文案,适配抖音、小红书、TikTok、Reels 与 YouTube Shorts。Open-source AI video clipping & content repurposing. What the test found: The AutoClip FastAPI backend serves all API health endpoints and the test suite passes with 103/103 tests passing. The frontend builds to production with Vite. 4 minutes. | ||||||
| 38 | openshot-qt | Runs | 80.7 / 100 | Python | 6,826 | |
OpenShot Video Editor is an award-winning free and open-source video editor for Linux, Mac, and Windows, and is dedicated to delivering high quality video... What the test found: OpenShot qt 4.0.0 test suite passes all 513 tests on Ubuntu noble with PyQt6 6.11.0, libopenshot 0.3.2, and FFmpeg 6.1; app initializes to window creation, needing a display server for GUI. 34 minutes. | ||||||
| 39 | olive | Runs | 66.7 / 100 | C++ | 9,164 | |
Free open-source non-linear video editor What the test found: Olive 0.2.0 builds and links fully; the editor binary (15 MiB) prints version and help; all 9 test cases across 3 test suites pass; running requires LD_LIBRARY_PATH to include the rootfs-extracted runtime debs. 30 minutes. | ||||||
| 40 | open-edit | Runs | 60 / 100 | TypeScript | 1,849 | |
Open-source, agent-driven editing pipeline: create subtitles, motion graphics, slides, edit and render videos. What the test found: CLI builds and runs (version 0.0.0-dev), 967/967 unit tests pass, help/version/command-parsing verified working on linux-x64; rendering requires macOS arm64 or Windows x64 which this platform does not provide. 7 minutes. | ||||||
| 41 | filmcraft | Runs | 45 / 100 | Rust | 18,832 | |
FilmCraft: An open-source, nonlinear video editor written from scratch in pure Rust What the test found: Rust toolchain 1.99.0 installed, ALSA headers configured via PKG_CONFIG_PATH/LIBRARY_PATH, all crates compile cleanly, 31 of 33 test suites pass with 2 pre-existing failures, CLI binary renders video to PNG, desktop binary starts on the virtual display. 65 minutes. | ||||||
| 42 | shotcut | Runs | 40 / 100 | C++ | 15,767 | |
cross-platform (Qt), open-source (GPLv3) video editor What the test found: Shotcut 26.9.6 builds and runs (--version reports correctly, --help works); the 112MB debug binary executes on Xvfb display :99. 44 minutes. | ||||||
| 43 | Clypra | Runs | 33.3 / 100 | TypeScript | 3,370 | |
A hardware-accelerated video editor built on Rust, Tauri v2, and React 19. Sub-10ms frame decoding, GPU-native rendering, and a frame-accurate timeline, all... What the test found: Frontend dependencies install, TypeScript type-checks pass, Vite production build succeeds, and 322/327 vitest test files pass (2712/2731 tests); the Rust clypra-native-core crate compiles and passes all 22 tests. 63 minutes. | ||||||
| 44 | freecut | Runs | 33.3 / 100 | TypeScript | 2,348 | |
FreeCut is a professional-grade video editor that runs entirely in your browser. Professional video editing, zero installation. Create stunning videos with... What the test found: The FreeCut project builds, all 4782 unit tests pass across 669 test files, 43 headless Node tests pass, headless Chrome render/edit/frame/layout tests pass, 19 edit operation contracts pass, lifecycle e2e passes, and media/audio integration passes. 40 minutes. | ||||||
| 45 | AI-Youtube-Shorts-Generator | Runs with mocks | 92 / 100 | Python | 6,466 | |
Open-source alternative to Opus Clip, Vidyo.ai, Klap & SubMagic. Turn long-form YouTube videos into viral 9:16 shorts using LLM highlight detection, Whisper... What the test found: Both API mode (with mock MuAPI server) and local mode (with mock LLM) complete end-to-end: download, whisper transcription, highlight selection, and vertical crop produce valid output files. api_ok=True local_ok=True clip_valid=True. 10 minutes. | ||||||
| 46 | open-genjutsu | Runs with mocks | 92 / 100 | Python | 1,173 | |
Local-first AI video recasting with draft review, explicit HD approval, and source-audio restoration. What the test found: Open Genjutsu installs, imports, and launches via uvicorn serving the full FastAPI app with all 5 local endpoints (/api/health, /api/upload, /api/recast, /api/predictions/{id}, /api/export, /api/download/{id}, /api/clear) returning correct responses, static front-end assets served at /, and FFmpeg audio muxing working... 6 minutes. | ||||||
| 47 | Adobe_Premiere_Pro_MCP | Runs with mocks | 92 / 100 | TypeScript | 924 | |
Adobe Premiere Pro MCP. Tools for AI-driven video editing via MCP, for Codex, Claude, and other MCP clients. What the test found: The project builds with tsc, all 653 tests pass, the MCP server starts and responds to tools/list over stdio, and the CLI reports version and help correctly. 23 minutes. | ||||||
| 48 | MotionClone | Runs with mocks | 92 / 100 | Python | 694 | |
Rebuild a reference video as an editable HyperFrames project, compare the match against the original, and export an MP4. What the test found: Python dependencies install cleanly, all 120 unit tests pass, the FastAPI server boots and responds 200 on / and /api/status with ffmpeg and hyperframes enabled, and the Playwright-based light UI acceptance test verifies the UI renders correctly against the running server. 8 minutes. | ||||||
| 49 | ghost-editor | Runs with mocks | 92 / 100 | Python | 687 | |
Open-source AI video editor for Claude Code. Raw talking-head take in, finished reel out. 19 styles. What the test found: Install green: dependencies in ~/.venvs/media and Node 22, sfx/music/emoji-optional media restored, doctor reports 17 ok 0 missing against a local Gemini mock, hyperframes CLI answers 0.8.159, and the repo's test suite passes except for one pre-existing test-fixture assertion in test_cutout_fx.py that was deliberately... 30 minutes. | ||||||
| 50 | chatgpt-video-editing-skills | Runs with mocks | 92 / 100 | Shell | 635 | |
用 ChatGPT/Codex 安裝 AI 剪輯環境,並依八大步驟完成可驗證的短影音剪輯。 What the test found: Project installs, builds, and runs. Both skills installed. video-use cloned at ~/Developer/video-use with Python deps synced via uv. Source Han Sans TW Regular+Bold fonts present with valid OTTO magic bytes. video-use test suite passes 26/26. Render pipeline produces decodable preview.mp4 from a test EDL. Transcribe... 4 minutes. | ||||||
| 51 | premiere-pro-mcp | Runs with mocks | 92 / 100 | TypeScript | 571 | |
Adobe Premiere Pro MCP, independent, local-first server for supported workflows. Connect Claude, Codex, or Cursor through a local CEP bridge. What the test found: MCP server builds cleanly, all 3725 automated tests pass, full CI gate passes, and the server binary starts and responds to MCP initialize over stdio with 382 default-profile tools registered. 4 minutes. | ||||||
| 52 | opensource-clipping | Runs with mocks | 92 / 100 | Python | 515 | |
Open-source AI video clipper with Web Studio, CLI & Colab/Kaggle notebooks. Turn long videos and podcasts into shorts with face tracking, karaoke captions... What the test found: FastAPI web API serves all endpoints (health returns 200, job CRUD works, settings panel responds). Pipeline renders video clips with face tracking, transcription, FFmpeg encoding, successfully produced 2 valid MP4 files from synthetic input. All 22 Python dependencies installed and importable. 21 minutes. | ||||||
| 53 | claude-youtube-editor | Runs with mocks | 92 / 100 | TypeScript | 389 | |
Record the talking head, Claude Code does the rest: the cut, the visuals, the voice, the sound effects, the thumbnail, and the YouTube upload. Every screen... What the test found: The project installs and builds successfully: Python venv with all deps, Remotion with all packages at v4.0.486, 144 compositions registered. Remotion renders both stills and video locally without any API keys. Local RNNoise-based voice cleaning works. Transcription formatting tools work on existing project data. The... 6 minutes. | ||||||
| 54 | BeatDesign | Runs with mocks | 92 / 100 | TypeScript | 371 | |
Local-first AI canvas and timeline. Any MCP agent. Open-source alternative to Higgsfield. What the test found: pnpm install, db:push, dev server, production build and production server all succeed; 417 unit tests pass; the dev server at 127.0.0.1:3020 answers HTTP 200 on /api/ping with {"message":"pong"}; the production server at port 3000 returns the same. 6 minutes. | ||||||
| 55 | Clip-Anything | Runs with mocks | 92 / 100 | Python | 321 | |
Clip any moment from any video with prompts What the test found: Clip-Anything transcribes a video with OpenAI Whisper (tiny model), calls a configurable LLM API for segment selection, and outputs a valid H.264/AAC MP4 clip with fades. 8 minutes. | ||||||
| 56 | charles-skills | Runs with mocks | 92 / 100 | JavaScript | 245 | |
Skills for Claude Code and Codex: design craft, reel editing, quality-of-life helpers, and every skill from my reels What the test found: The repository passes all validation checks: 18 skills across 4 shelves pass check.mjs with 0 errors, the site builder produces 18 skill pages and 12 keyword redirects, all 33 images and 2 videos are valid media files, manual install and link-skills.sh both work, marketplace.json matches all shelves exactly, and... 2 minutes. | ||||||
| 57 | oh-my-cassette | Runs with mocks | 92 / 100 | Python | 219 | |
你的随身 AI 剪辑搭档 | Pocket AI co-editor for video montage, AI video editing plugin & MCP server for Claude Code, Codex, Hermes & OpenCode What the test found: The packaged oh-my-cassette 0.6.0 installs and runs: it answers --version and --help, starts as a stdio bridge that lists the reference service's tools, imports and uploads real ffmpeg transcodes that decode cleanly, downloads the declared export, and the test suite reports 184 passed and 2 skipped. 10 minutes. | ||||||
| 58 | VideoCoF | Runs with mocks | 92 / 100 | Python | 211 | |
[CVPR 2026 Highlight] VideoCoF: Unified Video Editing with Temporal Reasoner What the test found: Gradio demo app with 74 UI components serves HTTP 200 on port 7860, all core Python modules import successfully, video-to-video CoT pipeline construction verified, grounding instruction extraction works for all 4 task types. 13 minutes. | ||||||
| 59 | after-effects-mcp | Runs with mocks | 86 / 100 | JavaScript | 917 | |
MCP Server for Adobe After Effects. Enables remote control (compositions, text, shapes, solids, properties) via the Model Context Protocol using ExtendScript. What the test found: npm install succeeds, esbuild build produces build/index.js (27.1KB), and the MCP stdio server starts and responds to all 13 registered tool calls and 3 prompts over JSON-RPC protocol. 2 minutes. | ||||||
| 60 | ID-V2V | Runs with mocks | 71 / 100 | Python | 296 | |
The official implementation of SIGGRAPH Asia 2026 paper "ID-V2V: Identity-preserving Video Restylization" What the test found: The repo installs and its preprocessing/save pipeline runs on CPU against the bundled sample media, with the SAM3 gated checkpoints and GPU needed for a real model run. 10 minutes. | ||||||
| 61 | SAMA | Runs with mocks | 71 / 100 | Python | 202 | |
Official inference code for SAMA: Factorized Semantic Anchoring and Motion Alignment for Instruction-Guided Video Editing. What the test found: SAMA inference pipeline and diffsynth library install successfully; video loading, frame processing, safetensors loading, video saving, argument parsing, and resolution matching all verified working in a CPU-only container without Wan2.1 model weights. 12 minutes. | ||||||
| 62 | yt-short-clipper | Runs with mocks | 56 / 100 | TypeScript | 1,106 | |
Windows desktop app that turns long-form YouTube videos into 9:16 short-form clips, AI highlight detection, face-tracking portrait reframe, and word-by-word... What the test found: YT Short Clipper v2 frontend builds with npm, Rust backend compiles, Python sidecar binary responds to ping commands, and the Tauri desktop app launches on the Xvfb virtual display and stays running. 26 minutes. | ||||||
| 63 | cli | Runs with mocks | 56 / 100 | TypeScript | 976 | |
一条命令,把口播毛片变成可二次精修的剪辑工程。 What the test found: gtrk CLI v1.3.0 builds from source, passes typecheck, reports version, enumerates all 37 tools, checks ffmpeg readiness, and connects to a configured API endpoint with valid auth, all verified inside the container. 8 minutes. | ||||||
| 64 | kiri | Runs with mocks | 56 / 100 | Rust | 577 | |
截图、录屏和文字识别工具,支持 macOS、Windows、Linux。Screenshots, screen recording, and OCR for macOS, Windows, and Linux. What the test found: All 153 JS tests pass and the frontend builds with pnpm build, but the Rust/Tauri backend cannot compile in this container due to missing system libraries (glib, webkit2gtk, etc.). 13 minutes. | ||||||
| 65 | kdenlive | Runs with mocks | 33.3 / 100 | C++ | 6,171 | |
Free and open source video editor, based on MLT Framework and KDE Frameworks What the test found: kdenlive_render binary successfully compiled and executes. CMake configures with all dependencies. Main kdenliveLib cannot compile due to missing KF6 headers (18+ frameworks not available on Ubuntu 24.04). 46 minutes. | ||||||
| 66 | FireRed-OpenStoryline | Runs with mocks | 30.7 / 100 | Python | 3,731 | |
FireRed-OpenStoryline is an AI video editing agent that transforms manual editing into intention-driven directing through natural language interaction... What the test found: MCP server starts on port 8001, web UI on port 8005, and the full agent pipeline builds successfully with a mock API endpoint; missing model weights and resource files were stubbed. 31 minutes. | ||||||
| 67 | ai-video-editor | Could not verify | 80 / 100 | JavaScript | 1,002 | |
Open-source, local-first video editor where creators and AI agents edit the same real timeline. What the test found: npm install, TypeScript typecheck, and Vite build all pass; the dev server starts and serves the application at localhost:5173; the headless timeline CLI command engine parses commands and returns structured JSON errors. 9 minutes. | ||||||
| 68 | clip-js | Could not verify | 80 / 100 | TypeScript | 776 | |
online video editor built with nextjs, remotion and ffmpeg (web assembly port) for render. What the test found: npm install and build succeed, the Next.js dev server starts and serves all static and dynamic pages with correct HTTP status codes. 3 minutes. | ||||||
| 69 | fabric-video-editor | Could not verify | 80 / 100 | TypeScript | 574 | |
Video editor that runs in the browser: timeline, text, image, video and audio layers, animations, filters, export with sound. Fabric.js + React + Next.js. What the test found: npm install succeeds, next dev serves both pages with HTTP 200. next build fails due to insufficient memory for SSR pre-rendering phase. 26 minutes. | ||||||
| 70 | Kiwi-Edit | Could not verify | 42.5 / 100 | Python | 336 | |
A unified and fully open-source framework for instruction-guided and reference-guided video editing using natural language. What the test found: Package builds and installs, core data loading/saving functions verified with demo files, but model inference requires CUDA GPU unavailable in this container. 6 minutes. | ||||||
| 71 | Light-A-Video | Could not verify | 35 / 100 | Python | 532 | |
[ICCV 2025] Light-A-Video: Training-free Video Relighting via Progressive Light Fusion What the test found: could not be verified; the log shows where it stopped. 19 minutes. | ||||||
| 72 | Kiri | Could not verify | 20 / 100 | Rust | 577 | |
截图、录屏和文字识别工具,支持 macOS、Windows、Linux。Screenshots, screen recording, and OCR for macOS, Windows, and Linux. What the test found: could not be verified; the log shows where it stopped. 12 minutes. | ||||||
| - | kinocut | Not yet tested | - | Python | 278 | - |
| - | erduo-broll-loop-engineering | Not yet tested | - | TypeScript | 254 | - |
runs installed and started with its real dependencies. runs with mocks started after stand-ins replaced external services such as a database or a third-party API. could not verify neither the standard agent nor the stronger one got it running within the time limit; the log shows where it stopped.
How we tested
On this list as of the latest test: 44 projects ran as-is, 22 with mocks, 6 could not be verified, 2 still waiting. Languages tested: C++, HTML, JavaScript, Nim, PHP, Python, Rust, Shell, TypeScript. Every attempt used a clean single-use machine, the subject at a pinned version, and a 90-minute limit for standard projects; the complete procedure is on the methodology page.
Frequently asked questions (FAQs)
How is this list ranked?
By measurement, not opinion: projects Argusic installed and launched on a fresh machine come first, then those that ran with mocks in place of external services, then those it could not verify. Ties go to the Argusic Score, then how popular it is on its own source.
Why are some projects unranked?
2 projects are still waiting for a test or for a finished attempt. They are listed without a rank until Argusic has measured them.
Where is the evidence?
Every row links to the project's Argusic page, where each run has a full log and a terminal recording stored with a sha256 fingerprint. The same pages exist for every one of the tested projects, on this list or not.
More lists in this category
- speech tools (shares AI-Powered-Video-Tutorial-Generator, FunClip, agent-plugin, ai-video-editor, dramaxis, splicr with this list)
- MCP servers (shares Adobe_Premiere_Pro_MCP, after-effects-mcp, agent-plugin, ffmpeg-skill with this list)
- open source coding agents (shares Orkas-VideoStudio, ffmpeg-skill, openfilm with this list)
- self-hosted AI apps (shares FunClip, autoclip with this list)
- screen recorders (shares Kiri, kiri with this list)
- AI agent frameworks (shares autoclip with this list)
- API clients
- API gateways
- CI/CD tools
- CMS platforms
- LLM gateways
- VPN tools
- backup tools
- browser automation tools
- code editors
- Open source databases, installed and queried
- developer CLI tools
- e-commerce platforms
- ebook readers
- game engines
- open source games
- home automation tools
- low-code platforms
- map tools
- message queues
- Open source music servers, installed and played
- observability tools
- Open source office suites, installed and launched
- self-hosted password managers
- project management tools
- search engines
- self-hosted analytics
- static site generators
- uptime monitors
- vector databases
- video players
- web scraping tools
- whiteboard tools
- wikis
- workflow automation tools
- self-hosted Notion alternatives
- self-hosted dashboards
- self-hosted git servers