Score breakdown
Popularity is tracked separately. Support, ads, sponsorships, and tips never affect these signals.
Why it matters
Useful for teams on self-hosted GitLab or Forgejo that cannot use GitHub-only review products; for organisations that require the review model path to stay inside their own network; for anyone comparing self-hosted alternatives to hosted review bots.
Who should use it
Who should skip it
Move on from Proval — self-hosted LLM code-review agent for GitLab, Forgejo and GitHub in one Docker image if the licensing terms, language support, or platform requirements do not fit your project.
About this signal
Proval — self-hosted LLM code-review agent for GitLab, Forgejo and GitHub in one Docker image is tracked by RepoRadar as a developer tool in the Code Review Tooling section. First seen —; the source record was last checked on 2026-08-28. The current verdict is 'worth watch' with a Bronze tier and moderate setup difficulty. The standout signals for Proval — self-hosted LLM code-review agent for GitLab, Forgejo and GitHub in one Docker image are open-source/build quality (8.4) and evidence quality (7.2), while maturity (4.8) trails — that balance shapes where it fits best. This page summarizes the public evidence on the linked source page and states where additional review is still needed.
How this item is evaluated
The Proval — self-hosted LLM code-review agent for GitLab, Forgejo and GitHub in one Docker image record combines a 5.6/10 composite score with separate popularity (25.0), risk (conditional), and setup (moderate) signals. See the scoring methodology for the current weights and evidence definitions.
Questions worth asking before you adopt this
Putting this into practice? Read How to vet an AI agent or MCP server before you wire it in for the checklist behind this score.
Risk explanation
The agent needs repository and pull-request write access on your forge; scope the token to review comments only; AGPL-3.0 licensing carries obligations for modified or network-served deployments; review before internal distribution.