GStars
    alibaba

    alibaba/open-code-review

    #7 this week

    Secure, fast, efficient, battle-tested at Alibaba's scale. Hybrid architecture code review tool: deterministic pipelines + LLM Agent, precise line-level comments, built-in multi-language ruleset (NPE, thread-safety, XSS, SQL injection), OpenAI & Anthropic compatible.

    ai-agents
    agent
    agent-skills
    code-review
    code-review-assistant
    harness
    Go
    Apache-2.0
    48.1K stars
    3.5K forks
    48.1K GitHub watchers
    Updated Oct 23, 2026
    View on GitHub

    Build with Backblaze B2

    SDKs, agent skills, IDE extensions, and reference pipelines from Backblaze Labs. All open source.

    Explore Backblaze Labs

    Loading star history...

    Where it stands

    Rank, growth pace and release cadence relative to everything GStars tracks.

    Ranks #1 among AI Agents repositories tracked this week, and #1 over the last 30 days; #7 of 3,103 repositories GStars tracks this week (top 1%).

    This week's +568 stars is below its 30-day pace of about +1,727 per week.

    5 releases in the last 90 days, the latest today, with 203 contributors on GitHub.

    The biggest single-day gain in the last year, +3,258 stars on Sep 16, coincided with release v1.12.4.

    Use Cases & Benefits

    • Provides an AI-powered CLI tool for precise, line-level code reviews using a hybrid deterministic and LLM agent architecture.
    • Combines deterministic engineering with dynamic LLM agents to ensure high precision, stable quality, and efficient token usage in code reviews.
    • Use for automating code reviews in large-scale enterprise projects requiring multi-language security and quality checks.
    • Use for integrating AI-driven code review into CI/CD pipelines to catch defects like NPEs, thread-safety, XSS, and SQL injection early.
    • Use for auditing unfamiliar or legacy codebases by scanning entire files or directories beyond just diffs for comprehensive analysis.

    Should you depend on it?

    License terms, project hygiene and risks, from GitHub metadata and GStars' snapshots.

    License

    Apache 2.0

    Permissive: commercial use, modification and redistribution are allowed with attribution; includes an explicit patent grant from contributors.

    Community files

    • README: present
    • Contributing guide: present
    • Code of conduct: present

    Watch-outs

    No watch-outs from GStars' checks.

    General guidance from repository metadata, not legal advice. How we score

    From the README

    Open Code Review is an AI-powered code review CLI tool. It originated as Alibaba Group's internal official AI code review assistant — over the past two years, it has served tens of thousands of developers and identified millions of code defects. After thorough validation at massive scale, we incubated it into an open source project for the community. Simply configure a model endpoint to get started.

    It reads Git diffs, sends changed files to a configurable LLM via an agent with tool-use capabilities, and generates structured review comments with line-level precision. The agent can read full file contents, search the codebase, inspect other changed files for context, and produce deep reviews — not just surface-level diff feedback. Beyond diff review, ocr scan reviews entire files for auditing unfamiliar codebases or directories that have no meaningful diff.

    Visit the official website for more details.

    Compared to general-purpose agents (Claude Code), Open Code Review achieves significantly higher Precision and F1 with the same underlying model, while consuming only ~1/9 of the tokens and completing reviews faster. Note that its Recall is lower than general-purpose agents — a deliberate trade-off favoring precision over noise.

    A real-world code review benchmark built from 50 popular open-source repositories, 200 real Pull Requests, and 10 programming languages — cross-validated by 80+ senior engineers (1,505 annotated ground-truth issues).

    Excerpt from the alibaba/open-code-review README on GitHub (Apache-2.0 license). © its authors.Read the full README on GitHub

    Daily snapshots

    Stars gained per day, and how forks and open issues moved, from GStars' daily snapshots

    Jul 26: +837Jul 27: +989Jul 28: +795Jul 29: +451Jul 30: +639Jul 31: +447Aug 1: +464Aug 2: +403Aug 3: +536Aug 4: +376Aug 5: +341Aug 6: +228Aug 7: +236Aug 8: +149Aug 9: +103Aug 10: +126Aug 11: +187Aug 12: +167Aug 13: +127Aug 14: +82Aug 15: +55Aug 16: +54Aug 17: +68Aug 18: +68Aug 19: +117Aug 20: +116Sep 9: +64Sep 10: +19Sep 13: +503Sep 14: +2,078Sep 15: +2,752Sep 16: +3,258Sep 17: +3,123Sep 18: +2,091Sep 19: +935Sep 20: +882Sep 21: +798Sep 22: +580Sep 23: +470Sep 24: +534Sep 25: +572Sep 26: +320Sep 27: +305Sep 28: +374Oct 2: +180Oct 3: +170Oct 4: +194Oct 5: +152Oct 6: +173Oct 7: +197Oct 8: +338Oct 9: +469Oct 10: +806Oct 11: +297Oct 12: +187Oct 13: +254Oct 14: +357Oct 15: +262Oct 16: +211Oct 17: +113

    +35,268 stars over 90 days across 65 snapshot days; best day +3,258 on Sep 16.

    Forks

    3.5K+2.6K

    Open issues

    342+284

    Compared with peers in AI Agents

    Fastest-growing repositories GStars tracks in this cohort for the week of Oct 18, by 7-day star growth

    View category →
    alibaba/open-code-review compared with AI Agents repositories by stars, 7-day star growth, health score and last release
    RepositoryStars+7dHealthLast release
    morluto/rea373.3K+88.2K605 days ago
    DietrichGebert/ponytail174.8K+9.9K757 days ago
    stablyai/orca103.9K+9.5K40today
    affaan-m/ECC287.3K+6.4K6422 days ago
    Leonxlnx/taste-skill101.6K+3.8K753 days ago
    alibaba/open-code-review48.1K+56875today
    Category median174.8K+9.5K64—
    Compare open-code-review with rea, ponytail, orca →

    Also by alibaba

    Other repositories from this maintainer that GStars tracks

    Discover Repositories

    Search across tracked repositories by name or description