Search AI tools, categories, and leaderboards
ML.ai is a coding agent that ships whole tasks rather than autocompleting lines. Hand it an issue and it reads the repo, writes a task plan, edits the code, runs your tests and opens a pull request - routing each step to the model that fits it while showing every diff before anything is written to disk.

OpenAITools.app のテレメトリ(2026-11-11 検証)によると、ML.ai(ml.ai)は AIコードアシスタント に分類される AI プラットフォームで、月間 0 の訪問を生み出し、前月比のトラフィック増減は +0(0%)です。主要な地域市場は グローバル(トラフィックシェア —)で、有料、料金は要問い合わせ の料金モデルで運営されています。 月間ボリューム別の主な競合代替ツールには ChatGPT(月間 60.48億 訪問), Code Arena(月間 3582.79万 訪問), Cursor(月間 2329.78万 訪問) が含まれます。
Give it an issue and it reproduces the bug, edits the code, runs your tests and opens a pull request while you focus on decisions.
The agent proposes a task list and names the files it expects to change. You select the tasks, and edits outside the declared scope stop and ask first.
Each step of a task is routed to the model that fits it, with the vendor abstracted behind an effort setting and a stated outcome.
Launch many jobs across projects at the same time. Each agent runs in its own sandbox and reports back with a reviewable diff.
The same account connects a desktop app for macOS and Windows, extensions for VS Code and JetBrains, and a terminal CLI via a single install script.
ML.ai is a coding agent that ships whole tasks rather than autocompleting lines. Hand it an issue and it reads the repo, writes a task plan, edits the code, runs your tests and opens a pull request - routing each step to the model that fits it while showing every diff before anything is written to disk.
Queue several dependency bumps, CI triage jobs or small refactors at once, each in its own sandbox, and review the resulting pull requests.
Assign a repetitive migration or call-site rewrite and let it run overnight without pausing halfway for a credit top-up.
Keep working in VS Code, JetBrains or the terminal while the agent produces a diff in the background, then review it when it is ready.
Every change arrives with type checks, lint and test results attached, and nothing merges until a human approves, which fits review-heavy workflows.
同じ主要カテゴリの競合 AI ツールをテレメトリで並列比較
| 順位 | AI ツール | 月間訪問数 | 前月比成長率 | 直接流入の割合 | 料金 | 直接比較 |
|---|---|---|---|---|---|---|
| ● | ML.ai | 0 | 0% | — | 有料、料金は要問い合わせ | 表示中 |
| 1 | ChatGPT | 60.48億 | +2.2% | 直接流入 73% | フリーミアム | vs ChatGPT |
| 2 | Code Arena | 3582.79万 | +19.4% | 直接流入 68% | 無料 | vs Code Arena |
| 3 | Cursor | 2329.78万 | +8.4% | 直接流入 63% | フリーミアム | vs Cursor |
| 4 | Google Antigravity | 1605.41万 | +8.1% | 直接流入 27% | フリーミアム | vs Google Antigravity |
| 5 | Bitbucket | 1308.09万 | -1.2% | 直接流入 79% | フリーミアム | vs Bitbucket |
| 6 | Replit | 1001.64万 | -7.7% | 直接流入 61% | フリーミアム、有料 | vs Replit |
Code Arena is a hands-on playground and leaderboard where you can pit leading AI coding models against each other on real web builds, comparing speed, accuracy, and logic in live side-by-side battles.
野心的なソフトウェアをつくるAIコーディングエージェント
エージェントファースト時代のための Google の開発プラットフォーム
アイデアを伝えるだけで、Replit が数分で動くアプリを構築
Z.ai is the free web assistant from Zhipu AI, built on the GLM model family. It handles everyday chat and research, generates slide decks and documents, and can produce working code, web pages and apps from a single prompt, with a no-login guest mode for quick questions.
正確にコードを書き、大きな作業はエージェントに任せ、どこからでも作業を続ける
チャットでアプリを説明し、そのまま公開
智譜 AI の GLM 大規模モデル開放プラットフォーム。マルチモーダル API とエージェント開発を一体化
実際のソフトウェアを届けるエージェント型コーディング基盤