open-code-review
Open-source & free — Battle-tested at Alibaba's scale. Hybrid architecture code review tool: deterministic pipelines + LLM Agent, precise line-level comments, built-in fine-tuned ruleset (NPE, thread-safety, XSS, SQL injection), OpenAI & Anthropic compatible.
Discover how Alibaba Open-Code-Review's comment reflection module boosts review accuracy by validating AI suggestions, catching errors before they reach developers, and ensuring precise comment positioning.
What Is the Manifest Hash and Its Role in Session Integrity in Open‑Code‑ReviewUnderstand the manifest hash in Open Code Review. This SHA-256 fingerprint ensures session integrity for review runs through deterministic verification and tamper detection.
How OpenCodeReview Handles Large Changesets: Scalable Architecture ExplainedDiscover how OpenCodeReview scales to handle large changesets by batching, parallel processing, and streaming LLM responses. Learn about its efficient architecture.
Open Code Review Agent Tools: Available Tools and Phase-Based SelectionExplore Open Code Review agent tools. Discover the six available tools and understand how they are automatically selected based on the review phase using plan_task and main_task flags.
How the Open Code Review Session Viewer Interface Works: Architecture, Security, and Data FlowExplore the alibaba/open-code-review Session Viewer interface. Understand its three-layer HTTP server architecture, host-guard security, and data flow for browsing and replaying code reviews.
How to Customize OpenCodeReview Output Format for JSON and Agent WorkflowsCustomize OpenCodeReview output to JSON or agent format. Learn how to generate machine-readable data for CI pipelines and autonomous agents with simple command-line options.
Performance Implications of max-tools and max-git-procs Settings in Open Code ReviewOptimize Open Code Review performance by understanding max-tools and max-git-procs. Learn how these settings impact LLM analysis and Git operations for faster scans and reduced latency.
OpenCodeReview Scan vs Review: Understanding the Difference Between OCR CommandsUnderstand the OpenCodeReview scan vs review commands. Discover how scan performs full-file analysis while review focuses on Git diffs for efficient code audits and reviews.
How to Debug Suboptimal Review Quality or Misplaced Comments in Open Code ReviewDebug suboptimal review quality or misplaced comments in Open Code Review by enabling debug mode. Trace issues from LLM output to final payload to identify generation, sanitization, or positioning problems.
Open Code Review Token Budget System: How to Configure max-tokens-budgetConfigure Open Code Review's max-tokens-budget to control LLM token consumption. Understand the token budget system and prevent exceeding limits for efficient code reviews.
How to Provide Business Context Using Background Flags in Open-Code-ReviewLearn to provide business context in Open-Code-Review using background flags. Inject domain specific requirements into LLM prompts with --background or --background-file.
How to Exclude Specific Files or Patterns from OpenCodeReview: 3 Configuration MethodsLearn to exclude specific files from OpenCodeReview using CLI flags, rule.json, or default patterns. Master your code review filtering with three powerful methods.
Have a question about this repo?
These articles cover the highlights, but your codebase questions are specific. Give your agent direct access to the source. Share this with your agent to get started:
curl -s "https://instagit.com/install.md" 
Maintain an open-source project? Get it listed too →