AI-powered code review

CodeCanary

Catch bugs, security issues, and quality problems before they land in main. Runs on every push or locally from the terminal.

Get started View on GitHub
terminal
$ codecanary review

Loaded 1 project doc(s) for review context
Re-evaluating 2 unresolved thread(s) (base b4723757)...
Re-evaluating 2 unresolved thread(s)...

  [evaluate] internal/auth/session.go:42 — 🟠 bug — unchecked-error — code changes detected
  [skip]     internal/handler.go:87 — ⚪ nitpick — unused-param — no code changes, no human replies

Triage result: 1 skipped, 0 auto-resolved, 1 need evaluation

  [resolved] internal/auth/session.go:42 — 🟠 bug — unchecked-error — fixed by code change
1 finding(s) resolved by code changes
Reviewing incremental changes (1 known issues excluded)...
No new findings
All clear! No issues remaining.

  ──────────────────────────────────────────────
  Model              Input   Output        Cost
  ──────────────────────────────────────────────
  claude-haiku-4-5     842      156     $0.0003
  ──────────────────────────────────────────────
  Duration: 1.8s
  PR size: +24/-8 lines, 3 files

$

Built for real workflows

Not another AI gimmick. A review tool that fits into how you already work.

⚙

GitHub Actions native

Runs as a composite action on every push. Posts inline comments on exact diff lines. Zero config after setup.

↻

Incremental reviews

Go-driven triage classifies existing threads at zero LLM cost. Only changed code gets re-evaluated.

💬

Conversational

When authors reply to a finding, CodeCanary re-evaluates in context. It understands fixes, dismissals, and rebuttals.

🔒

Anti-hallucination

Explicit file allowlists, line validation against the diff, and distance thresholds prevent fabricated findings.

💰

Cost-efficient

Fast triage model for thread re-evaluation, full model for review. Tracks per-invocation usage so you see what you spend.

🔌

Multi-provider

Bring your own LLM: Anthropic, OpenAI, OpenRouter, or Claude CLI. No vendor lock-in. New providers are easy to add.

✓

Auto-resolution

When code is fixed, threads are auto-resolved. No stale reviews cluttering your PRs.

💻

Local reviews

Review your changes from the terminal before pushing. Same engine, same findings, instant feedback.

📄

Configuration-as-code

Project-specific rules, severity levels, ignore patterns, and context. Checked into your repo alongside the code.

How it works

Three commands. Automated reviews from there.

1

Install

One curl command installs the codecanary binary. Supports Linux and macOS, amd64 and arm64.

2

Setup

The interactive wizard configures your provider, stores your API key in the system keychain, and creates the config file.

3

Review

Run locally for instant feedback, or merge the GitHub Actions workflow for automated reviews on every push.

Configuration-as-code

Define rules, context, and ignore patterns in .codecanary/config.yml. Checked into your repo.

.codecanary/config.yml
version: 1
provider: anthropic
review_model: claude-sonnet-4-6
triage_model: claude-haiku-4-5-20251001

context: |
  Go REST API using chi router. Tests use testify.

rules:
  - id: error-handling
    description: "Errors must be wrapped with context"
    severity: warning
    paths: ["**/*.go"]

  - id: sql-injection
    description: "Queries must use parameterized statements"
    severity: critical

ignore:
  - "vendor/**"
  - "*.lock"

Bring your own LLM

No vendor lock-in. Pick the provider that works for you.

Anthropic
Claude Sonnet, Haiku, Opus
OpenAI
GPT-5.4, GPT-5.4-mini, o3
OpenRouter
Any model via OpenRouter
Switching providers? Change two lines:
provider: openai
review_model: gpt-5.4
Adding a new provider →
Claude CLI
Use your logged-in session, no API key needed

Start reviewing in 30 seconds

Install, setup, review. That's it.

$ curl -fsSL https://codecanary.sh/install | sh

View on GitHub