Frenchie
OCR, transcription, and image generation for AI agents via MCP.
Ask AI about Frenchie
Powered by Claude Β· Grounded in docs
I know everything about Frenchie. Ask me about installation, configuration, usage, or troubleshooting.
0/500
Reviews
Documentation
@lab94/frenchie
Frenchie β your agent's best friend.
Install Frenchie in your coding agent with one command. Frenchie Kit gives agents file and multimodal capabilities: read PDFs and images, transcribe audio and video, extract Office/CSV files to Markdown, and generate images from text prompts. Frenchie Method gives teams a structured workflow from requirement to release.
Upgrading from 0.1.x or 0.2.x? See MIGRATION.md for the breaking changes in 0.3.0 (stdio metadata-only responses, absolute-path MCP configs, new
mcp --help/--selftestflags).
This package ships:
- Frenchie Kit (
/ocr,/transcribe,/extract,/generate-image,/frenchie-statuscommands + HTTP/stdio MCP guidance) - Frenchie Method (
/frenchie-method,/requirement,/qa-analysis,/implement,/run-test,/pr-review,/release-check, and related workflow commands) - The Frenchie stdio MCP server (
lab94-frenchie mcp) bundled fornpx - An installer that wires skills and MCP config into your agent
Quick start
1. Install the skills
From the root of your project:
npx @lab94/frenchie install
This installs Frenchie Kit and Frenchie Method skills. Method is text-only and works without an API key.
Optional Method config:
npx @lab94/frenchie install --init-method
This creates .frenchie/method.config.json and .frenchie/.gitignore; it does not edit your root .gitignore.
2. Log in for Kit MCP tools when you need file or image capabilities
Create an account at getfrenchie.dev. You get 100 free credits on your first signup, once per email. No card required.
Then connect your local agent:
npx @lab94/frenchie login
The login command opens a browser device-code flow, then writes FRENCHIE_API_KEY into the MCP config the installer created. The full key is never printed.
Fallback if you already have a key from the dashboard:
npx @lab94/frenchie install --api-key fr_your_key_here
To target a specific agent:
npx @lab94/frenchie login --agent claude
npx @lab94/frenchie login --agent cursor
npx @lab94/frenchie login --agent codex
npx @lab94/frenchie login --agent vscode
npx @lab94/frenchie login --agent gemini
User-level installs (Antigravity, Windsurf, Zed, Claude Desktop) need the --global flag β auto-detect never writes under $HOME:
npx @lab94/frenchie login --agent antigravity --global
npx @lab94/frenchie login --agent windsurf --global
npx @lab94/frenchie login --agent zed --global
npx @lab94/frenchie login --agent claude-desktop --global
Fallback with an existing key:
npx @lab94/frenchie install --agent claude --api-key fr_β¦
npx @lab94/frenchie install --agent codex --api-key fr_β¦
npx @lab94/frenchie install --agent antigravity --global --api-key fr_β¦
npx @lab94/frenchie install --agent claude-desktop --global --api-key fr_β¦
After login, your agent can call ocr_to_markdown, transcribe_to_markdown, extract_to_markdown, or generate_image. OCR/transcription/extraction results are saved to .frenchie/<name>/result.md automatically; generated images are saved to .frenchie/<slug>/generated.<ext>.
Upgrading later
When a new Frenchie version ships, the pinned package spec inside each MCP config (@lab94/frenchie@0.5.0) needs to point at the new version so npx stops serving a cached older bundle. Two upgrade commands cover everything:
# Project-scoped configs in this directory (.mcp.json, .cursor/mcp.json, .codex/config.toml, etc.)
npx @lab94/frenchie@latest install
# Every $HOME config that already has a frenchie entry β Antigravity, Claude Desktop, Windsurf, Zed,
# and any global Claude Code / Cursor / Codex / Gemini configs you set up. cwd doesn't matter.
npx @lab94/frenchie@latest install --global
install --global is upgrade-mode: it only rewrites frenchie entries that already exist. It will not surprise-install anything new under $HOME. First-time global installs still go through install --agent <name> --global.
3. Restart your agent
The installer prints the restart hint for your agent. After that, ask:
OCR ./report.pdf with Frenchie
β¦and Frenchie takes it from there.
For workflow orchestration, ask:
/frenchie-method
/frenchie remains the Kit entrypoint in agents that use a single Frenchie command. It is not an alias for Method.
Hosted agents (Lovable, Manus, Claude.ai, ChatGPT.com, Le Chat)
These agents can't run local npm binaries. Use the hosted MCP endpoint instead:
URL: https://mcp.getfrenchie.dev
Header: Authorization: Bearer fr_your_key_here
The same @lab94/frenchie skill files work in HTTP mode β install them once with install --agent <name> and the included SKILL.md will tell the agent to upload files via upload_file before calling OCR/transcription/extraction. Image generation does not need an upload step in HTTP mode; it returns a short-lived imageUrl that the agent should download for the user.
What you get
Frenchie Kit
| Command | What it does |
|---|---|
/ocr <file> | Parse a PDF or image into Markdown |
/transcribe <file> | Parse audio or video into a Markdown transcript |
/extract <file> | Parse DOCX, XLSX, CSV, TSV, or PPTX into Markdown |
/generate-image <prompt> | Generate a single image from a text prompt |
/frenchie-status | Check credits and recent jobs |
Under the hood, Frenchie exposes these MCP tools:
ocr_to_markdowntranscribe_to_markdownextract_to_markdowngenerate_imageget_job_resultupload_file(HTTP mode only)fetch_result_file(HTTP mode only)
Frenchie Method
Slash notation is the canonical Method command name. Claude Code reads command
files directly. Codex Desktop gets the same entries through wrapper skills such
as requirement and qa-analysis; restart Codex after install before trying
/requirement. Hosts without slash support can use natural language such as
Frenchie Method requirement ....
| Command | What it does |
|---|---|
/frenchie-method | Route a task through Method from requirement to release |
/method-check | Validate Method config, artifacts, gates, and next action |
/requirement | Turn a request into scoped requirements |
/qa-analysis / /test-case | Design proof before implementation planning |
/sa-analysis / /implementation-plan | Analyze architecture and implementation approach |
/implement | Execute from Method artifacts using the current agent |
/run-test | Run repo-declared verification and write a test report |
/pr-review / /review-pr | Review the result, tests, security, and artifact drift |
/release-check | Read-only release readiness gate |
Method stores optional workflow artifacts under .frenchie/docs/feature/. install --init-method also writes a visible skillTriggers skeleton in .frenchie/method.config.json; command keys are empty slots teams can fill with installed agent skills, for example "requirement": ["brainstorming"]. Teams decide whether to commit or ignore Method config and artifacts.
Invocation β how to call Frenchie in each agent
Every agent handles MCP a little differently. /ocr is a Claude Code-only slash command; Method slash commands are host-dependent and use Codex wrapper skills outside Claude Code. Other agents use natural language, @-mention, or a server-name slash command. All facts below are dogfood-verified.
| Agent | Invoke | Full guide |
|---|---|---|
| Claude Code | /ocr TOR.pdf | docs |
| Cursor | Use Frenchie to OCR TOR.pdf | docs |
| Codex (Desktop / CLI / IDE) | Kit: /frenchie TOR.pdf Β· @frenchie ocr TOR.pdf; Method: /requirement after restart, or Frenchie Method requirement ... | docs |
| Antigravity | /frenchie TOR.pdf (invokes by server name) | docs |
| VS Code Copilot | /frenchie TOR.pdf | docs |
| Claude Desktop | Use Frenchie to OCR TOR.pdf | docs |
| Windsurf | OCR TOR.pdf via Frenchie | docs |
| Gemini CLI | OCR TOR.pdf with Frenchie | docs |
| Zed | OCR TOR.pdf via Frenchie | docs |
Something not working? See the symptom-first troubleshooting guide β every error we've hit in dogfood has a canonical entry.
Pricing
Simple numbers. No subscriptions.
File extraction pricing: DOCX 0.5 credits per page, XLSX 0.5 credits per sheet, CSV/TSV 0.5 credits per file, PPTX 1 credit per slide.
| Action | Cost |
|---|---|
| OCR | 1 credit per page |
| Transcription | 2 credits per minute |
| DOCX extraction | 0.5 credits per page |
| XLSX extraction | 0.5 credits per sheet |
| CSV/TSV extraction | 0.5 credits per file |
| PPTX extraction | 1 credit per slide |
| Image generation | 20 credits per image |
$1 = 100 credits. Credits don't expire.
Privacy
Files are processed and deleted. Results expire about 30 minutes after first delivery. If you need a durable copy, save the Markdown when it comes back.
Supported formats
OCR: PDF, PNG, JPG, JPEG, WebP
Transcription: MP3, M4A, WAV, MP4, MOV, WebM
File extraction: DOCX, XLSX, CSV, TSV, PPTX
Image generation: PNG, JPEG, WebP output from text prompts
