AI-IDE: Code & Markdown Editor
Not in any tracked top chart right now.
Updated 25 Oct 2026 · rankings refresh through the day
DeveloperChun Chen
CategoryDeveloper Tools
PriceFree
Released
Rating★ 0.0 (0)
Version1.18
Age rating4+
First seen by us
24 Oct 2026
Rating
0.0 ★
0 ratings
Measured
AI-IDE: Code & Markdown Editor on the App Store
App details
App ID
6774000001
Publisher
Chun Chen
On the store since
Jun 2026
Under a year
Minimum OS
iOS 17.0+
iPhone XS and later
Devices
iPhone · iPad
Universal purchase
Content rating
4+
Languages
3
EN ZH ZH
Size
22 MB
Also listed in
Utilities
Where it ranks now
Every top chart it appears in across 30 countries.
| Country | Charts | Rank |
|---|---|---|
| Not charting right now. | ||
Ratings
App Store, worldwide.
Rating
0.0 ★
0 ratings
Measured
Ratings
0
Measured
About AI-IDE: Code & Markdown Editor
AI-IDE is a lightweight editor for iPhone, iPad, and Mac. Edit Markdown, code, and config files inside iCloud Drive or any Files folder — and work with the LLM of your choice without leaving the document.
KEY FEATURES
• Mark up the preview, let AI edit — Tap a spot or select a passage and say what to change. Queue marks, send one batch, review one diff.
• Bring your own AI — Anthropic, Gemini, DeepSeek, OpenRouter, Groq, Mistral, any API-compatible endpoint, local Ollama, or an AISA key for 70+ models. 16 one-tap presets. No built-in account or key: nothing runs until you add one.
• You approve every change — Edits show a diff first; nothing is written until you tap Apply, and overwrites are snapshotted.
• Multi-tab editor — Syntax highlighting for 10 languages, line numbers, autosave, find & replace.
• Rich Markdown preview — Outline navigation, in-document search, reading progress with resume, code copy, task checkboxes, light/dark themes.
• Office files and PDFs, both ways — Export to PDF, Word, Excel, and PowerPoint on device; "AI Refine" turns a document into slides, using your own .pptx as the master and Brand Kits for colours, fonts, and logo. Open a .docx, .xlsx, .pptx, or PDF to edit in place, formatting kept.
• AI illustrations — One prompt draws an illustration at the cursor with your own image model; it flows into PDF, Word, and PowerPoint. Decks can auto-illustrate.
• Built-in data tools — 35 the AI calls itself: web pages, academic papers, US financials and SEC filings, crypto prices, X posts, prediction markets, Perplexity. Switched on by category, with the token cost shown. HTTPS-only and host-whitelisted; your key is injected on device, never seen by the model.
• Prompt Library — Activate several presets at once, merged in your order with a size meter. Three research procedures are built in; add more from the library or GitHub.
• KB Library — File a document once and reference it as often as you like: type ~ to attach one, or let the AI search the library and read only the passage it needs. Ranked search working in Chinese and says so when nothing matches.
• Share what you tune — Prompts, export styles and KB entries export as files. Install from the built-in library or add a source: any public GitHub repo or page. Updates are flagged, never automatic, and an edited copy is never overwritten.
• Tool-using AI — Reads, searches, and writes workspace files. Optional web search via Brave, Tavily, Perplexity, or AISA.
• Files done right — Open files from anywhere; create, rename, move, duplicate, delete; multiple pinned workspaces.
• Local version control — Snapshot, diff, and revert on device: no git account, history never leaves it, instant in huge folders. Auto-commit optional.
• Reliable by default — Suggests the right model for the job; dropped streams resume without re-sending the conversation.
• Multimodal — Attach files, photos, or clipboard images. Vision models get them directly; PDF / DOCX / PPTX / XLSX are
KEY FEATURES
• Mark up the preview, let AI edit — Tap a spot or select a passage and say what to change. Queue marks, send one batch, review one diff.
• Bring your own AI — Anthropic, Gemini, DeepSeek, OpenRouter, Groq, Mistral, any API-compatible endpoint, local Ollama, or an AISA key for 70+ models. 16 one-tap presets. No built-in account or key: nothing runs until you add one.
• You approve every change — Edits show a diff first; nothing is written until you tap Apply, and overwrites are snapshotted.
• Multi-tab editor — Syntax highlighting for 10 languages, line numbers, autosave, find & replace.
• Rich Markdown preview — Outline navigation, in-document search, reading progress with resume, code copy, task checkboxes, light/dark themes.
• Office files and PDFs, both ways — Export to PDF, Word, Excel, and PowerPoint on device; "AI Refine" turns a document into slides, using your own .pptx as the master and Brand Kits for colours, fonts, and logo. Open a .docx, .xlsx, .pptx, or PDF to edit in place, formatting kept.
• AI illustrations — One prompt draws an illustration at the cursor with your own image model; it flows into PDF, Word, and PowerPoint. Decks can auto-illustrate.
• Built-in data tools — 35 the AI calls itself: web pages, academic papers, US financials and SEC filings, crypto prices, X posts, prediction markets, Perplexity. Switched on by category, with the token cost shown. HTTPS-only and host-whitelisted; your key is injected on device, never seen by the model.
• Prompt Library — Activate several presets at once, merged in your order with a size meter. Three research procedures are built in; add more from the library or GitHub.
• KB Library — File a document once and reference it as often as you like: type ~ to attach one, or let the AI search the library and read only the passage it needs. Ranked search working in Chinese and says so when nothing matches.
• Share what you tune — Prompts, export styles and KB entries export as files. Install from the built-in library or add a source: any public GitHub repo or page. Updates are flagged, never automatic, and an edited copy is never overwritten.
• Tool-using AI — Reads, searches, and writes workspace files. Optional web search via Brave, Tavily, Perplexity, or AISA.
• Files done right — Open files from anywhere; create, rename, move, duplicate, delete; multiple pinned workspaces.
• Local version control — Snapshot, diff, and revert on device: no git account, history never leaves it, instant in huge folders. Auto-commit optional.
• Reliable by default — Suggests the right model for the job; dropped streams resume without re-sending the conversation.
• Multimodal — Attach files, photos, or clipboard images. Vision models get them directly; PDF / DOCX / PPTX / XLSX are
Latest updates
1.18
Slide export, one page at a time
A four-step wizard: source → imagery → outline → output
• Exporting a deck is no longer press-and-pray. Each step does one thing, and each one shows you its own result.
• Step one takes reference material: knowledge base entries, files from your working folder, or a URL — pasted links are fetched as a snapshot and kept in the knowledge base.
• The quote appears while you are choosing the imagery, and it counts images rather than pages. Anything already generated is not billed again.
See the whole deck before you pay
• The preview is what you will get: every page's layout, its words, and the prompt that page will use to draw its picture.
• Edit any page's text. You can also direct just one page's picture ("watercolour for this one") — that note never gets printed onto the slide.
• Not quite right? Change one part of that image and keep the rest.
• Want to check the style first? Generate a single image. That one is the final one: the export reuses it instead of billing you twice.
• A set of edits can be thrown away all at once, back to the version you had.
• Changed pages are marked, and only they are redrawn. Every other picture is reused.
AI Refine now really follows your settings
• The refine settings moved next to the deck they shape, so one tap redoes it — no trip back to Settings.
• Style now changes how pages are built, not just their tone. "Minimal" really does land on 5–7 pages.
• The outline is written in the document's own language, and it says which language that is.
• Auto-illustration now lets the model mark the pages that deserve a picture in the outline itself, so those pictures can be previewed, edited per page, and tested one at a time.
• Full-page images no longer stop at 12 pages. A long deck simply costs more, and the quote says so before you start.
• A failed refine now says so. It used to look exactly like "nothing changed".
• Knowledge base reference material now reaches all four imagery modes.
Fixes
• Exporting a PDF on a Mac could never finish.
• The checkmarks in menus all disappeared, so you could not see which tools were on.
• Three academic search backends had been broken.
• Needing a subscription used to fail first and explain afterwards. It now opens the subscription page.
• A failed export reports the real reason instead of guessing at a settings page for you to go and change.
Also
• Two new web tools: turn one page into Markdown, and list a whole site's URLs.