CoraAI Code Review CLI

BYOK, zero config. Multi-LLM code review, semantic search, and code intelligence — runs in your terminal, CI/CD, or AI coding agents. All local, zero cloud.

Get Started

Installation

GitHub

🤖

Multi-LLM

OpenAI, Anthropic, Groq, Ollama, Z.AI, or any OpenAI-compatible API. Bring your own key, pick any model.

⚡

Native Rust

Fast binary, no runtime dependencies, cross-platform. ~7.4 MB release binary.

🪝

Pre-commit Hooks

Catch issues before they reach CI. Review staged changes, unpushed commits, or any diff.

📋

SARIF Output

Upload findings to GitHub Code Scanning. Native SARIF support for CI integration.

🛡️

Deterministic Scanners

12 built-in rules + 13 security patterns + 15 secret detection patterns — run without LLM, zero cost.

🧠

Code Intelligence

Index symbols across 15 languages. Call graph, trace, impact analysis. FTS5 + vector KNN + graph hybrid search.

🌳

Tree-sitter

AST-based symbol extraction for 13 languages: Rust, Go, Python, TypeScript/TSX, Java, C, C++, C#, Ruby, PHP, Scala, JavaScript, Svelte.

🔌

MCP Server

18 tools for AI coding agents — review, search, brain, debt, trace, dead code, graph query. Works with Claude, Cursor, Windsurf, and other MCP clients.

📐

Quality Profiles

Strict, balanced, or lax presets. Configurable quality gate with pass/fail thresholds for CI enforcement.

💾

Diff-hash Caching

Skip repeat reviews automatically. Incremental index in ~6ms with mtime:size fingerprint.

🚧

Quality Gate

Configurable pass/fail thresholds for CI enforcement. Max critical, max security findings, per-category actions.

🔧

Configurable

Per-project .cora.yaml, global ~/.cora/config.yaml, or env vars. Custom regex rules in config.