Sourcery

AI reviewer for GitHub and GitLab with line-by-line reviews, summaries and diagrams, custom rules, and BYO-LLM on its Team tier.

Visit Website [↗]

[ Facts ]

Category: AI PR Review
Open source: No
Pricing: Free for open-source repos; Pro $12/seat/mo; Team $24/seat/mo adds analytics, 3x rate limits, daily security scans, BYO-LLM; annual saves 20%; Enterprise custom source
Self-hosted: Enterprise only — Enterprise adds self-hosting; below that it is cloud-only.
Platforms: github, gitlab
Model control: BYO-LLM available on Team tier ($24/seat); vendor models otherwise
Last verified: 2026-08-11

[ Against the 9 Standards ]

Based on public documentation as of 2026-08-11. ✓ documented · ~ partial · ✗ not offered · ? unknown. Methodology on the about page.

✗ Multi-dimensional Context

PR-scoped reviews; shallower context than codebase-indexing tools per our comparison.

~ Rule-Centric & Default Quiet

Customizable review rules supported; enforcement depth not detailed in sources we verified.

? Dual-Workflow: Local vs. PR

IDE/local review surface not covered in the sources we verified.

? Business Logic Validation

Ticket/requirements validation not documented.

? Continuous Learning

Learning from review feedback not documented.

? Sandbox Validation

No documented sandbox validation; Team tier adds daily security scans.

~ Economic Transparency

BYO-LLM on Team tier ($24/seat) is rare at this price; not offered on Pro.

? Actionability

Fix-apply flow not documented in the sources we verified.

~ Measurable ROI

Team tier adds repo analytics; ROI/DORA-level reporting not documented.

[ In Our Coverage ]

Best AI Code Review Tools (2026): 12 Tools Compared

The best AI code review tools 2026 offers, compared honestly: Kodus, CodeRabbit, Greptile, Copilot and more — context depth, pricing, self-hosting.

Open Source AI Code Review: The Real Options (2026)

Open source AI code review tools compared: Kodus (AGPL), PR-Agent (MIT), and more — real licenses, BYOK costs, and how they stack up against closed SaaS.

Evaluating Sourcery?

Run it through the two-week trial protocol before you commit.

Evaluation Guide [↗]