// 41% of your codebase was written by an AI that had no idea what the other 59% does.

Your AI is guessing. Maina gives it the context it was missing — and proves the diff is correct before it merges.

Every prompt, your coding agent burns 8–12k tokens pasting files it hopes are relevant. Most of them aren't. Maina runs a 4-layer context engine over your repo — working set, PR memory, AST + PageRank, code search — and hands your agent only what matters. Then a 19-tool verification pipeline checks the diff before it merges. Run it on your repo in 60 seconds. No account, no API key, no config.

Maina is the layer that makes those three things stop.

60 seconds, start to finish.

No edited video, no marketing demo. This is `maina setup` on a fresh clone of a real TypeScript repo, verified by the bytes you can run yourself.

  1. context
  2. constitution
  3. verify
  4. commit proof

▸ reproduce locally: curl -fsSL https://api.mainahq.com/install | bash

// engines

Three engines. One honest claim each.

// stack fit

Whatever you already use. Maina sits under it.

Maina ships as a CLI and as an MCP server. Your coding agent calls it. You don't change your workflow.

// compare

What this replaces.

Diff-onlyMulti-languageLearns from feedbackSelf-verifiedCost
Maina 7 languagesFree
CodeRabbit PartialMulti-language$15+/mo
DeepSource PartialMulti-language$12+/mo
Manual review Human-onlyn/aYour time

Run it on your repo. Decide in 60 seconds.

No signup. No account. No telemetry unless you turn it on. Works on macOS, Linux, Windows (WSL). Free and open source, Apache 2.0. If it doesn't earn its place in your workflow in one minute, uninstall it and we'll have failed on our own terms.

FAQ

  1. Does this phone home?

    No. Telemetry is opt-in and off by default. You can grep the source.

  2. Does this work without Claude/OpenAI keys?

    Yes, for everything except the AI-fix and AI-review steps of Verify. Everything else is deterministic.

  3. Will it slow my commits down?

    Syntax guard is <500ms. Full verify is ~12s on a typical diff. maina commit --async defers the report.

  4. How is this different from CodeRabbit?

    Diff-only, runs locally, rebuilds context for your agent upstream. CodeRabbit reviews after the fact. Maina fixes the input before the fact, then reviews after.

  5. Is the context engine just RAG?

    No. RAG retrieves by vector similarity. Maina uses tree-sitter AST + PageRank over the dependency graph + PR memory with Ebbinghaus decay + Zoekt code search. Similarity is one signal of four.