{"slug": "video-use-edit-videos-with-coding-agents", "title": "Video-use: Edit videos with coding agents", "summary": "Browser Use released video-use, an open-source tool that lets users edit videos by chatting with coding agents like Claude Code, dropping raw footage into a folder and receiving a final.mp4 without presets or menus. The tool cuts filler words, auto color grades, burns subtitles, generates animation overlays via HyperFrames or Remotion, and self-evaluates output at every cut boundary, persisting session memory in project.md.", "body_md": "Introducing **video-use** — edit videos with Claude Code. 100% open source.\n\nDrop raw footage in a folder, chat with Claude Code, get `final.mp4`\n\nback. Works for any content — talking heads, montages, tutorials, travel, interviews — without presets or menus.\n\nTry video-use in [Browser Use Cloud](https://cloud.browser-use.com/v4?utm_campaign=video-use-use-in-cloud&utm_source=github).\n\n**Cuts out filler words**(`umm`\n\n,`uh`\n\n, false starts) and dead space between takes**Auto color grades** every segment (warm cinematic, neutral punch, or any custom ffmpeg chain)**30ms audio fades** at every cut so you never hear a pop**Burns subtitles** in your style — 2-word UPPERCASE chunks by default, fully customizable**Generates animation overlays** via[HyperFrames](https://github.com/heygen-com/hyperframes),[Remotion](https://www.remotion.dev/),[Manim](https://www.manim.community/), or PIL — spawned in parallel sub-agents, one per animation**Self-evaluates the rendered output** at every cut boundary before showing you anything**Persists session memory** in`project.md`\n\nso next week's session picks up where you left off\n\nPaste into Claude Code, Codex, Hermes, Openclaw, or any agent with shell access:\n\n```\nSet up https://github.com/browser-use/video-use for me.\n\nRead install.md first to install this repo, wire up ffmpeg, register the skill with whichever agent you're running under, and set up the ElevenLabs API key — ask me to paste it when you need it. Then read SKILL.md for daily usage, and always read helpers/ because that's where the editing scripts live. After install, don't transcribe anything on your own — just tell me it's ready and wait for me to drop footage into a folder.\n```\n\nThe agent handles the clone, dependencies, skill registration, and prompts you once for your ElevenLabs API key (grab one at [elevenlabs.io/app/settings/api-keys](https://elevenlabs.io/app/settings/api-keys)).\n\nThen point your agent at a folder of raw takes:\n\n```\ncd /path/to/your/videos\nclaude    # or codex, hermes, etc.\n```\n\nFor always-on editing from your own VPS or Telegram, run the agent through [Browser Use Box](https://browser-use.com/bux). [Watch the 15-second demo](https://www.tiktok.com/@browser_use/video/7639824093721758989).\n\nAnd in the session:\n\nedit these into a launch video\n\nIt inventories the sources, proposes a strategy, waits for your OK, then produces `edit/final.mp4`\n\nnext to your sources. All outputs live in `<videos_dir>/edit/`\n\n— the skill directory stays clean.\n\nIf you'd rather do it by hand:\n\n```\n# 1. Clone and symlink into your agent's skills directory\ngit clone https://github.com/browser-use/video-use ~/Developer/video-use\nln -sfn ~/Developer/video-use ~/.claude/skills/video-use        # Claude Code\n# ln -sfn ~/Developer/video-use ~/.codex/skills/video-use       # Codex\n\n# 2. Install deps\ncd ~/Developer/video-use\nuv sync                         # or: pip install -e .\nbrew install ffmpeg             # required\nbrew install yt-dlp             # optional, for downloading online sources\n\n# 3. Add your ElevenLabs API key\ncp .env.example .env\n$EDITOR .env                    # ELEVENLABS_API_KEY=...\n```\n\nThe LLM never watches the video. It **reads** it — through two layers that together give it everything it needs to cut with word-boundary precision.\n\n**Layer 1 — Audio transcript (always loaded).** One ElevenLabs Scribe call per source gives word-level timestamps, speaker diarization, and audio events (`(laughter)`\n\n, `(applause)`\n\n, `(sigh)`\n\n). All takes pack into a single ~12KB `takes_packed.md`\n\n— the LLM's primary reading view.\n\n```\n## C0103  (duration: 43.0s, 8 phrases)\n  [002.52-005.36] S0 Ninety percent of what a web agent does is completely wasted.\n  [006.08-006.74] S0 We fixed this.\n```\n\n**Layer 2 — Visual composite (on demand).** `timeline_view`\n\nproduces a filmstrip + waveform + word labels PNG for any time range. Called only at decision points — ambiguous pauses, retake comparisons, cut-point sanity checks.\n\nNaive approach: 30,000 frames × 1,500 tokens =\n\n45M tokens of noise. Video Use:12KB text + a handful of PNGs.\n\nSame idea as browser-use giving an LLM a structured DOM instead of a screenshot — but for video.\n\n```\nTranscribe ──> Pack ──> LLM Reasons ──> EDL ──> Render ──> Self-Eval\n                                                              │\n                                                              └─ issue? fix + re-render (max 3)\n```\n\nThe self-eval loop runs `timeline_view`\n\non the *rendered output* at every cut boundary — catches visual jumps, audio pops, hidden subtitles. You see the preview only after it passes.\n\n**Text + on-demand visuals.** No frame-dumping. The transcript is the surface.**Audio is primary, visuals follow.** Cuts come from speech boundaries and silence gaps.**Ask → confirm → execute → self-eval → persist.** Never touch the cut without strategy approval.**Zero assumptions about content type.** Look, ask, then edit.**12 hard rules, artistic freedom elsewhere.** Production-correctness is non-negotiable. Taste isn't.\n\nSee [ SKILL.md](/browser-use/video-use/blob/main/SKILL.md) for the full production rules and editing craft.", "url": "https://wpnews.pro/news/video-use-edit-videos-with-coding-agents", "canonical_source": "https://github.com/browser-use/video-use", "published_at": "2026-07-21 03:56:57+00:00", "updated_at": "2026-07-21 04:24:15.462026+00:00", "lang": "en", "topics": ["developer-tools", "artificial-intelligence", "ai-tools", "generative-ai"], "entities": ["Browser Use", "Claude Code", "Codex", "Hermes", "Openclaw", "ElevenLabs", "HyperFrames", "Remotion"], "alternates": {"html": "https://wpnews.pro/news/video-use-edit-videos-with-coding-agents", "markdown": "https://wpnews.pro/news/video-use-edit-videos-with-coding-agents.md", "text": "https://wpnews.pro/news/video-use-edit-videos-with-coding-agents.txt", "jsonld": "https://wpnews.pro/news/video-use-edit-videos-with-coding-agents.jsonld"}}