# Installer open-code-review avec Homebrew, MacPorts, winget

Consultez les chemins d'installation, exécutables, métadonnées et notes de sécurité de open-code-review pour les workflows d'agents IA.

## installation

```sh
sudo av install brew:open-code-review
```

Commandes d'installation supplémentaires:

### macOS

- Homebrew (100%):

```sh
brew install open-code-review
```

  Preuve: local Homebrew formula metadata

- MacPorts (94%):

```sh
sudo port install open-code-review
```

  Preuve: MacPorts ports tree: llm/open-code-review/Portfile from https://api.github.com/repos/macports/macports-ports/git/trees/master?recursive=1

### Windows

- winget (92%):

```sh
winget install --id Alibaba.OpenCodeReview -e
```

  Preuve: Windows Package Manager source index: Alibaba.OpenCodeReview from https://cdn.winget.microsoft.com/cache/source.msix

## Faits du paquet

- **Clé du paquet:** brew:open-code-review
- **Gestionnaire de paquets:** Homebrew
- **Page du gestionnaire de paquets:** <https://formulae.brew.sh/formula/open-code-review>
- **Version:** 1.13.4
- **Résumé source:** AI-powered code review tool with deterministic pipelines and an LLM agent
- **Page d'accueil:** <https://open-codereview.ai>
- **Dépôt:** <https://github.com/alibaba/open-code-review>
- **Docs amont:** <https://open-codereview.ai>
- **Licence:** Apache-2.0
- **Archive source:** <https://github.com/alibaba/open-code-review/archive/refs/tags/v1.13.5.tar.gz>
- **Dernière mise à jour:** 2026-11-03T19:00:00Z
- **Généré:** 2026-11-04T12:20:42+00:00

## exécutables

- ocr (cli)
- ocr (alias)

## Dépendances de compilation

- go

## Comportement d'installation

- hook post-installation: non défini
- Bouteille: disponible sur arm64_golden_gate, arm64_linux, arm64_sequoia, arm64_tahoe, x86_64_linux

## Version et fraîcheur

- page générée: 2026-11-04
- version du gestionnaire: 1.13.4
- gestionnaire mis à jour: 2026-11-03
- données locales: OK
- dépôt amont: https://github.com/alibaba/open-code-review
- dernière version détectée: v1.13.5 (à jour)
## Historique du projet et usages

Open Code Review is Alibaba’s open-source AI-assisted code-review CLI. It reviews Git diffs or complete files and emits structured, line-level findings using deterministic pipelines and an LLM agent.

### Historique du projet

Open Code Review originated as Alibaba Group’s internal AI code-review assistant. Following two years of internal deployment, Alibaba incubated it as an open-source project.

The public project centers on a hybrid architecture: deterministic pipelines control coverage, bundling, rule selection, and comment positioning, while an LLM agent retrieves context and writes review findings.

### Historique d'adoption

Alibaba states that the tool served tens of thousands of internal developers and identified millions of defects over two years before being released as an open-source project. The public CLI is distributed through npm, downloadable binaries, source builds, and Homebrew.

The project also provides integrations for coding-agent skills, Claude Code plugins, GitHub Actions, and GitLab CI, extending it beyond interactive local reviews.

### Modes d'utilisation

Users configure an LLM endpoint, authentication token, and model, test connectivity with ocr llm test, then run ocr review against workspace changes, commit ranges, or individual commits. The ocr scan command audits complete files or directories.

Configuration is stored in ~/.opencodereview/config.json. LLM credentials may instead be supplied through OCR-prefixed or compatible Anthropic environment variables; because no distinct credential file is documented, the credentials-file field is null.

### Pourquoi les passionnés de paquets s'y intéressent

Open Code Review packages an internally developed, large-scale review system as a portable Go CLI. It combines deterministic file selection and rule matching with LLM-driven contextual analysis rather than relying on an unconstrained general-purpose agent.

Its multiple distribution and integration surfaces—native binaries, npm, Homebrew, CI, skills, and plugins—make it representative of the emerging AI developer-tool supply chain.

### Chronologie

- Internal era: Deployed within Alibaba for two years before open-source incubation.
- Open-source era: Released publicly with CLI, agent, plugin, skill, and CI integration surfaces.

### Related projects

- Related systems include Git, GitHub Actions, GitLab CI, Claude Code skills and plugins, OpenAI-compatible APIs, and Anthropic-compatible APIs.

### Sources

- <https://github.com/alibaba/open-code-review>
- <https://open-codereview.ai/>


## Notes de sécurité

Aucun manifest local de gestion des secrets correspondant n'a été trouvé pour open-code-review. Les métadonnées de paquet restent publiées ici afin que la couverture future dispose d'une URL stable.



## Configuration and credential file locations

These source-backed paths show where this package keeps local settings or durable credentials. Automic Vault can use them as review targets for secret scanning, migration, and command approval.


## Configuration files

- Unix: ~/.opencodereview/config.json

## Credential files

- Unix: ~/.opencodereview/config.json
## Détails de la base source

- **Source Database:** Homebrew formula API
- **Tap:** homebrew/core
- **Full Name:** open-code-review
- **Version Scheme:** 0
- **Revision:** 0
- **Head Version:** HEAD
- **Bottle Stable Root URL:** <https://ghcr.io/v2/homebrew/core>
- **Deprecated:** no
- **Disabled:** no
- **Keg Only:** no
- **URL Keys:** head, stable

## Autres enregistrements de gestionnaires de paquets

- MacPorts - open-code-review: normalized package name match | MacPorts ports tree: llm/open-code-review/Portfile from https://api.github.com/repos/macports/macports-ports/git/trees/master?recursive=1
- winget - Alibaba.OpenCodeReview: normalized package name match | Windows Package Manager source index: Alibaba.OpenCodeReview from https://cdn.winget.microsoft.com/cache/source.msix


## Liens liés

- [AI and agent packages](https://pkg.so/fr/ai-agent-tools/) - Matched AI model, agent, coding-agent, orchestration, or MCP metadata.
- [Networking and protocol packages](https://pkg.so/fr/networking-protocol-tools/) - Matched network, protocol, or remote-service metadata.
- [coderabbit](https://pkg.so/fr/cask/coderabbit/) - Choose CodeRabbit CLI when you prefer a hosted AI-review product with GitHub and GitLab pull-request integration and repository-local YAML policy, rather than Open Code Review's self-selected LLM providers and deterministic local pipeline.

  Sources: <https://open-codereview.ai/> · <https://docs.coderabbit.ai/cli> · <https://docs.coderabbit.ai/getting-started/yaml-configuration>

## Combined YAML source

View the package source record on GitHub. [combined/open-code-review.yml](https://github.com/mxcl/pkgdb/blob/main/combined/open-code-review.yml)


## Sources

- pkg.so package database
- package-page enrichment
- curated configuration and credential file locations
- curated package history
- package version freshness
- package relationship graph
- external package-manager database matches
- cross-ecosystem install command graph
