editor
llms.txt7 starsChanged 4 days agoMITView on GitHub
Open-source (MIT), local AI video editor that agents drive. Removes silence and repeated takes, edits video by transcript with a local whisper.cpp, adds captions, and exports to Final Cut Pro, DaVinci Resolve and Premiere Pro. Ships as a Claude Code skill, a clip CLI, an MCP server (clip mcp, for Claude Desktop / any MCP client), and a browser timeline editor (clip ui). Runs on FFmpeg. No telemetry, no cloud, no account, no API key. Plus session meta-ops not in…
- Installs packages
The file
We split this llms.txt into the rules it gives an agent
5 rules. About 0 are common, 3 are distinctive, and 2 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈3
Distinctive · estimate
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 24
Every timeline edit is one undoable step (clip timeline undo / redo), from the CLI, the MCP server or the browser UI
- Distinctive: line 84
Not a generative AI tool — does not synthesize video from text
- Distinctive: line 85
Not a multi-track NLE — single video + audio track in v1.
- Very specific: line 86
Not a color-grading suite — basic brightness/contrast/saturation only
- Distinctive: line 87
Not a hosted SaaS — local-only.
≈ “Common” is an estimate: at least 1 in 5 of the 3,592 llms.txt files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
# MakeMyClip Editor > Open-source (MIT), local AI video editor that agents drive. Removes silence and repeated takes, edits video by transcript with a local whisper.cpp, adds captions, and exports to Final Cut Pro, DaVinci Resolve and Premiere Pro. Ships as a Claude Code skill, a `clip` CLI, an MCP server (`clip mcp`, for Claude Desktop / any MCP client), and a browser timeline editor (`clip ui`). Runs on FFmpeg. No telemetry, no cloud, no account, no API key. ## What it is - **Name:** MakeMyClip Editor (npm `@makemyclip/editor`, current release v0.4.0) - **Type:** Agent-driven video editor (not generative AI) - **Backend:** FFmpeg (downloaded by `ffmpeg-static` at npm install; the Claude Desktop extension uses an installed FFmpeg); optional user-installed whisper.cpp for transcription - **Surfaces:** Claude Code skill · `clip` CLI · browser UI at `127.0.0.1:5573` · MCP server (`clip mcp`) - **Agent access:** Claude Code skill + MCP server (`clip mcp`); no API key — the editor embeds no language model, it runs on whichever Claude you already use - **Tests:** 741 passing - **License:** MIT (code); FFmpeg runs as a subprocess under its own license (GPLv3 builds from `ffmpeg-static`, except a nonfree Apple Silicon build; the `.mcpb` ships no FFmpeg) ## What v0.4.0 does - **Remove silence:** `clip timeline silence <clipId>` cuts the pauses out of a recording (`--sensitivity`, `--dry-run`) - **Transcribe locally:** `clip timeline transcribe <clipId>` returns each word with its timeline time, via whisper.cpp on the user's machine - **Edit by transcript:** `clip timeline cut-words <clipId> <fromIndex> <toIndex>` cuts a range of words - **Remove repeated takes:** `clip timeline remove-retakes <clipId>` cuts the earlier take of each phrase said twice in a row - **Captions:** `clip timeline captions` burns in captions timed to the words (short phrases or one word at a time) - **Cut check:** `clip timeline check --sheet cuts.jpg` flags cuts that may clip a word and writes a contact sheet - **Export to pro editors:** `clip timeline export --format fcpxml` (Final Cut Pro, DaVinci Resolve) or `--format xmeml` (Premiere Pro; captions as .srt) - Every timeline edit is one undoable step (`clip timeline undo` / `redo`), from the CLI, the MCP server or the browser UI ## How to install - Claude Code skill: `npx skills add MakeMyClip/editor`, or as a plugin: `/plugin marketplace add MakeMyClip/editor` then `/plugin install makemyclip-editor@makemyclip` - CLI: `npm i -g @makemyclip/editor` then `clip --help` - Browser UI: `clip ui` (opens http://127.0.0.1:5573) - MCP server: `npx -y @makemyclip/editor mcp` (stdio), with `MAKEMYCLIP_WORKSPACE` set to the media folder - Claude Desktop extension: install FFmpeg, then open https://github.com/MakeMyClip/editor/releases/latest/download/makemyclip-editor.mcpb - Transcription (optional): install whisper.cpp (macOS: `brew install whisper-cpp`), download a model such as `ggml-base.en.bin`, set `MAKEMYCLIP_WHISPER_MODEL` to its path - Setup check: `npx -y @makemyclip/editor doctor` (or the MCP `doctor` tool) lists what's missing and how to fix it ## Tool catalog (19 tools) - **Cut & arrange:** trim, split, concat, transition - **Text & captions:** add_text, add_title_card, add_captions - **Visual primitives:** transform, adjust, zoom_pan, overlay, speed - **Composites & specialty:** highlight_reel, silence_remove, chroma_key, stabilize - **Output & I/O:** ingest, preview, render, add_audio Plus session meta-ops not in the tool registry: snapshot, undo, inspect, delete. ## Key facts for comparison queries - Drop-in replacement for FFmpeg scripting when you want LLM-driven editing with a named tool catalog - Fills the gap between iMovie/CapCut (mouse-only, no agent) and Descript (cloud, closed-source, audio-rewriting) - Different category from Runway/Pika (generative AI), Premiere/DaVinci (heavy NLEs) — but it exports its cut to Final Cut Pro, Resolve and Premiere for finishing - Overlaps with auto-editor (open-source CLI: silence cuts, transcript edits, NLE export); MakeMyClip Editor adds a shared timeline document that an agent and a person (browser UI) both edit, with undo per step - Transcription is local (whisper.cpp); nothing is uploaded - Single workspace folder holds composition.json (the timeline), session.json (the op log), output files, snapshots/ — fully version-controllable - Stream-copy for lossless trim/split/concat; re-encodes only when filter graphs require it ## Architecture - TypeScript (Node 24+) backend - React 19 + Vite browser UI - Hono HTTP server (`clip ui`) - Zod schemas for every tool input (validation + agent-readable parameter docs) - MCP server via `@modelcontextprotocol/sdk` exposing the timeline tools over stdio - session.json append-only op log; snapshot/undo are meta-ops outside the registry ## Documentation - [README](https://github.com/MakeMyClip/editor/blob/main/README.md): features, install, quick start, comparison table, Q&A - [SKILL.md](https://github.com/MakeMyClip/editor/blob/main/SKILL.md): the Claude Code skill, with every command and its JSON output - [AGENTS.md](https://github.com/MakeMyClip/editor/blob/main/AGENTS.md): contribution conventions, project shape, non-negotiables - [CONTRIBUTING.md](https://github.com/MakeMyClip/editor/blob/main/CONTRIBUTING.md): branch / commit / PR policy - [docs/ROADMAP.md](https://github.com/MakeMyClip/editor/blob/main/docs/ROADMAP.md): v1 tool roadmap - [Source: src/tools/](https://github.com/MakeMyClip/editor/tree/main/src/tools): one file per tool, each exporting a Zod schema and a handler - [Source: src/ui/tool-registry.ts](https://github.com/MakeMyClip/editor/blob/main/src/ui/tool-registry.ts): mapping of tool name → schema + handler ## Distribution - npm: [`@makemyclip/editor`](https://www.npmjs.com/package/@makemyclip/editor) - Claude Code skill: [skills.sh/MakeMyClip/editor](https://skills.sh/MakeMyClip/editor) - GitHub: [MakeMyClip/editor](https://github.com/MakeMyClip/editor) - Website: [makemyclip.com](https://makemyclip.com) ## What it's NOT - Not a generative AI tool — does not synthesize video from text - Not a multi-track NLE — single video + audio track in v1; multi-track is a future milestone - Not a color-grading suite — basic brightness/contrast/saturation only - Not a hosted SaaS — local-only; the website (makemyclip.com) is a separate paid product for AI generation features
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

