Your Code, Your Model

Self-hosted Code Review Agent on your infrastructure

Use any local model or API you want.

Supports GitLab, Forgejo, and GitHub.

Try the demo

Read the docs View on GitHub

Features

From setup to review output.

Browse the dashboard and review output.

proval.local

Every review run, model, and connected repository in one place.

Integration

Plug into the Git host you already run.

Webhooks and host APIs connect your Git host to Proval. Review context goes to the model you run.

Git provider

GH
GitHub

GitHub App
GL
GitLab

Access Token
Fj
Forgejo

Access Token

Proval

Review Agent

Runs Agent loop

Dashboard :7900
Webhook :7901

LLM

Lc Llama.cpp
OA OpenAI-compatible
OR OpenRouter
An Anthropic

Gitea and Codeberg use the same Forgejo-compatible webhook and API path.

Public webhooks may need nginx or Caddy in front of Proval for HTTPS (TLS).

How agent works

One predictable path for every repository event.

The same flow on every event. See how it runs.

Load Context

PR Metadata

Git Diff

Existing code

Plan Agent

Group related files

Review

Concurrent agents

Review Agent

More...

Writing Agent

Deployment

Start with a small self-hosted deployment.

Run the service, connect your model, link repositories, and test a real merge request.

Open the Docker guide

docker-compose.yml

services:
    proval:
        image: ghcr.io/seoes/proval:latest
        ports:
            - "7900:7900"
            - "7901:7901"
        volumes:
            - ./data:/data
        environment:
            - ENCRYPTION_KEY=[Encryption Key]

Deploy in a minute with Docker Compose. Full setup guide

FAQ

A few practical answers.

Is Proval a replacement for Cursor, Copilot, or Claude?

No Those tools are strong agents on IDE(or Cli) for individual developers. Proval is a team review layer on your Git host. Reviews and replies appear on pull requests and issues, and you can choose any model API you want.

Does code leave our infrastructure?

Proval does not store your code. It only sends review context to the LLM endpoint you configure. Use a local model if you need to keep everything on your network.