ReviewSensei

Free plan APILinuxMacSelf-hostedWebWindows

What ReviewSensei is

ReviewSensei is open-source alpha software for AI review of GitHub pull requests. It uses repository-owned knowledge and configurable stages, with specialist checks for correctness, architecture, security, and performance before combining results. Optional large-change orchestration reports each path as reviewed, partially reviewed, excluded, unsupported, or budget exhausted. Incremental reviews use stable fingerprints to mark findings new, still present, fixed, outdated, or uncertain. Proposed repository learnings can become draft pull requests and need maintainer approval before use. Separate controls govern analysis, comments, automatic approval or change requests, learning, conversations, and artifact retention. Doctor and plan commands preview configuration, budgets, stages, and skip reasons without provider calls or writes. Reviews run in GitHub Actions, a self-hosted runner, or a local CLI. A GitHub App, Action, and CLI are offered, with Ollama, Ollama Cloud, OpenAI-compatible, and OpenRouter support. The core does not persist raw prompts or provider responses, but provider retention practices are not guaranteed.

Who it suits

It suits development teams maintaining GitHub repositories who want configurable, self-hosted or local AI pull-request review. Teams should be comfortable with alpha software and provisioning model, Actions, or runner resources.

What it does well

Specialist stages cover correctness, architecture, security, and performance
Stable fingerprints track findings across incremental reviews
Repository learnings require maintainer approval
Runs in Actions, self-hosted runners, or local CLI
Separate switches control publication and retention

What to know first

The project is labeled alpha software
Provider retention, training, residency, and deletion are not guaranteed
Review validation does not prove findings are correct
Users pay model and execution costs

Verdict

ReviewSensei offers detailed controls for AI-assisted GitHub review, including coverage reporting and finding lifecycles. Its alpha status, provider limitations, and infrastructure costs should be considered before adoption.

Facts from ReviewSensei's own pages

Alpha status: The project identifies itself as alpha software and says capabilities, defaults, and distribution channels evolve. · reviewsensei.dev, 11 Oct 2026
Controls: Separate switches govern analysis, comment publication, automatic approval or request changes, learning, conversations, and artifact retention. · reviewsensei.dev, 11 Oct 2026
Coverage: Opt-in large-change orchestration reports per-path outcomes such as reviewed, partially reviewed, excluded, unsupported, or budget exhausted. · reviewsensei.dev, 11 Oct 2026
Data handling: The core does not persist raw prompts or provider responses; published comments, artifacts, approved learnings, and provider-side copies have separate retention locations. · reviewsensei.dev, 11 Oct 2026
Data persistence: The core engine does not persist raw prompts or raw provider responses; review results, GitHub comments, artifacts, and approved learnings have separate retention locations. · reviewsensei.dev, 11 Oct 2026
Diagnostics: The doctor and plan commands preview configuration, stages, budgets, and skip reasons without provider calls or writes. · reviewsensei.dev, 11 Oct 2026
Evidence limitation: Schema and diff-location validation do not prove that a finding is correct or that review coverage is complete, and legacy evidence policy is the default. · reviewsensei.dev, 11 Oct 2026
Execution: Review logic runs in the user's GitHub Actions environment, self-hosted runner, or local CLI environment. · reviewsensei.dev, 11 Oct 2026
Finding lifecycle: Incremental reviews use stable fingerprints to label findings new, still present, fixed, outdated, or uncertain. · reviewsensei.dev, 11 Oct 2026
Finding tracking: Incremental reviews use stable fingerprints to track findings through states including new, still present, fixed, outdated, and uncertain. · reviewsensei.dev, 11 Oct 2026
Installation: The site describes three installation routes: App-assisted GitHub reviews, manual GitHub Actions setup, and local CLI. · reviewsensei.dev, 11 Oct 2026
Integrations: The site offers a GitHub App, GitHub Action, and CLI, and its provider matrix lists Ollama, Ollama Cloud, OpenAI-compatible, and OpenRouter support with different workflow availability. · reviewsensei.dev, 11 Oct 2026
Learning: Proposed repository learnings can become draft pull requests and require maintainer approval before future selection for matching paths. · reviewsensei.dev, 11 Oct 2026
Model providers: The getting-started page lists local Ollama, Ollama Cloud, OpenRouter, and an OpenAI-compatible CLI option. · reviewsensei.dev, 11 Oct 2026
Provider costs: Users provision and pay for model inference, GitHub Actions minutes, and self-hosted runner capacity. · reviewsensei.dev, 11 Oct 2026
Provider data limits: ReviewSensei says it does not guarantee provider-side retention, training, residency, or deletion practices. · reviewsensei.dev, 11 Oct 2026
Publication controls: Comment publication defaults to off, and separate settings control review policy, learning, conversations, and artifact retention. · reviewsensei.dev, 11 Oct 2026
Purpose: ReviewSensei is open-source alpha software for AI code review of pull requests using repository-owned knowledge and configurable review stages. · reviewsensei.dev, 11 Oct 2026
Release status: The site labels ReviewSensei open source and alpha. · reviewsensei.dev, 11 Oct 2026
Repository learning: Proposed learnings can become draft learning pull requests and are selected for matching paths after maintainer approval. · reviewsensei.dev, 11 Oct 2026
Review coverage: Opt-in large-change orchestration reports per-path outcomes including partially reviewed, excluded by policy, unsupported, and budget exhausted. · reviewsensei.dev, 11 Oct 2026
Review stages: Its specialist reviewers cover correctness, architecture, security, and performance before synthesizing results. · reviewsensei.dev, 11 Oct 2026
Security limitation: ReviewSensei says it does not guarantee provider retention, training, residency, or deletion practices. · reviewsensei.dev, 11 Oct 2026
What it does: ReviewSensei is an open-source engine for AI reviews of GitHub pull requests using repository-owned knowledge, configurable review stages, and explicit coverage. · reviewsensei.dev, 11 Oct 2026

Where ReviewSensei stands on Freedom251

Code review software#36 of 50