code-review-agent

OrcaCode Review — the open code review harness. Multi-model reviews, merge gates, and no markup. Pay only for inference.

An autonomous, context-aware AI Code Review Agent for GitLab. Powered by multi-LLMs (OpenAI, Anthropic, Gemini) with a self-learning feedback loop to enforce repository best practices.

Azure devops extension for OpenCode

Agentic AI code review for GitLab MRs and GitHub PRs, with the LLM of your choice. Posts only actionable findings as inline review threads.

deep research agent for codebase

ML/LLM lab for vector search, RAG, code review agents, weather baselines, evaluation metrics, and enterprise AI integration with Python and Java ecosystems.

🚀 Production-grade AI-Native SDLC starter template for autonomous coding agents. Unbroken artifact gates (Intent ➔ Spec ➔ Plan), strict TDD, and AI PR reviews.

AI code review agent using parallel LangGraph specialist agents (security, style, logic) that post structured feedback on GitHub PRs.

Local-first AI PR review agent for GitHub Pull Requests: diff parsing, lightweight repo context, conservative LLM findings, validation, and JSON/Markdown reports.

Multi-model code review skill — dispatches diffs to frontier LLMs in parallel, filters by confidence + cross-reviewer corroboration

Multi-agent academic peer-review panel as a Claude Code skill — anonymized reviewers, prior-art grounding, and a synthesized meta-review.

OpenAI Codex skill for multi-agent pull request review using multiple subagents