Ml.ai is an AI coding agent that goes where your code goes. Use it inside VS Code and Cursor, in its own desktop app with no IDE required, from the terminal, or as a PR Reviewer that checks every pull request. Every surface runs on the same engine, with the same settings and the same memory of your repo.
Most coding agents send every step to the same expensive frontier model. Ml.ai hands each step to a focused agent and picks the most cost-efficient model that meets your quality bar, which typically cuts model spend by 30 to 45% on the same work. Explore reads and explains the codebase. Architect and Plan map the files, order of work and trade-offs. Only General can change code, and every edit or command waits for you to Allow or Deny it.
The PR Reviewer summarizes each pull request, leaves line-level comments, and runs builds and tests before it recommends approve or request changes. It never merges on its own.
Also included: reusable skills, background runs, MCP server support, a command safety classifier, and an access token that stays on your machine. Ml.ai is a product of Pixis.ai, backed by SoftBank Vision Fund and General Atlantic.
ML.ai provides an AI coding agent that automates bug fixes, tests, migrations and PR creation across IDEs, CLI and GitHub.
- for
- Developers and engineering teams needing automated code changes and review.
- pricing
- paid · free trial
works withGitHubDockerpnpmpytestTerraformKubernetesAWSPrismaPlaywrightGNU Make
Key features
8 features of ML.ai
- Auto model routing — Selects the most cost-effective model for each step of a task.
- IDE & CLI integration — Runs inside VS Code, JetBrains, terminal and a desktop app.
- PR reviewer — Generates line-level comments, runs tests and suggests approve or changes.
- Background routines — Schedules recurring tasks like triage, audits and CI watches.
- Reusable skills & MLAI.md — Encodes team standards once and applies them to future jobs.
- Parallel job execution — Runs multiple jobs concurrently with configurable concurrency limits.
- No token meter — Flat-price model with unlimited jobs per month, no token counters.
- API & headless CLI — Drive the agent from CI pipelines and custom tooling.
Use cases
- Fix a double-charge bug, run tests and open a PR automatically.
- Migrate authentication to passkeys across a codebase.
- Backfill database fields and ship rollback SQL in a single PR.
- Run nightly CI watch to catch flaky tests and race conditions.
- Schedule routine dependency audits and issue triage.
ML.ai pricing
- Builder$20/month1 builder · $15 included execution · Full GitHub automation · CLI/IDE with 3 concurrent agents
- Team (ML.ai Code)$99/workspace / monthUp to 50 trigger users · $75 pooled execution · 10 concurrent agents · Team rules and budgets
- Scale$499/workspace / monthUp to 250 trigger users · $350 pooled execution · SSO/SCIM · 50 concurrent agents
ML.ai vs alternatives
 ML.ai |  Fine |  Pieces Copilot | .svg?auto=compress&fit=max&w=64) Devzero |  BuildShip | |
|---|---|---|---|---|---|
| Best for | Cost-efficient AI-driven code execution | AI code generation | AI coding assistant | Speedy releases | Visual backend builder |
| Pricing | Paid | Free | Free | Subscription | Free |
| DevHunt upvotes | 1 | 75 | 63 | 85 | 118 |
| Launched | Oct 2026 | Jan 2023 | Mar 2024 | Apr 2024 | Jan 2023 |
- ML.ai vs Fine: Fine is an AI-powered code generation tool, but ML.ai focuses on end-to-end task execution with PR creation and model routing.
- ML.ai vs Pieces Copilot: Pieces Copilot is a sidekick that assists within the workflow, while ML.ai automates whole tasks and handles PR merges.
- ML.ai vs Devzero: Devzero emphasizes rapid release cycles, whereas ML.ai provides automated bug fixing, migrations and background routines.
- ML.ai vs BuildShip: BuildShip offers visual backend building, while ML.ai automates code changes across any stack via AI agents.
ML.ai FAQ
How does ML.ai keep costs low?+
It routes each step to the most cost-efficient model, typically cutting model spend by 30-45% compared to single-model agents.
Is there a token or usage meter?+
No. ML.ai uses a flat-price model with unlimited jobs per month; only usage beyond the plan’s included execution incurs a fee.
Can the agent merge PRs automatically?+
No. The PR reviewer suggests approve or request changes, but merging must be done by a human.
What platforms can I run ML.ai on?+
ML.ai is available for macOS, Linux and Windows, and works inside VS Code, JetBrains, the terminal, a desktop app and via a web UI.
How do I schedule recurring tasks?+
Use the built-in Routines feature to define background jobs like CI watches, dependency audits or issue triage.
Summarized by DevHunt from ml.ai · Sep 28, 2026. Details may change; check the official site.
