# The-PR-Agent/pr-agent > Open-source AI agent for pull request review: automatically describes, reviews and suggests improvements to PR code via comments or CLI. Supports GitHub, GitLab, Bitbucket, Azure DevOps and various LLMs. - Magnitude: 3.3 out of 10 — Breakout - Stars: 13,826 total · +6 stars measured 2026-10-31, 11:33–13:39 UTC, ≈ 28 by evening - Star trust: star growth looks organic - Category: AI agents · Language: Python · License: MIT · Created: 2023-07-05 · Last push: 2026-10-31 - GitHub: https://github.com/The-PR-Agent/pr-agent · Homepage: https://www.pr-agent.ai · Page: https://gitnova.dev/en/r/The-PR-Agent/pr-agent ## Useful for - Set up a GitHub Action to auto-review every new PR - Run pr-agent review locally to check a PR before merging - Ask /ask what a specific PR changes ## Why it’s here - Star-counter measurements on 2026-10-31 (UTC), 11:33–13:39: 13820 → 13826 stars (+6). This is the change over that interval. - Estimated end-of-day forecast: about +28 stars, using observed gains and the previous day. - Over the last two days the pace is 2.9× that of the previous week and a half. - GitHub Trending Python today: #12, +118 stars. - About 14 forks a day — people are taking the code. ## Star trust Star growth looks organic. Star-trust labels are heuristics based on the repository’s behavior, not a check of every stargazer. ## Numbers - Forks: 2,030 - Issues and pull requests: 4,491 - Watchers: 62 - Average over the last week: 34 per day - Usual pace: 19 per day - Stars in the last hour (measured): 1 - Latest release: v0.49.0 (2026-10-25) ## Stars per day, last 30 days (oldest → newest, today is partial) 2026-10-02 … 2026-10-31: 20, 11, 16, 11, 13, 11, 15, 11, 14, 18, 14, 16, 17, 17, 17, 12, 12, 16, 57, 27, 19, 17, 24, 13, 16, 26, 30, 20, 108, 6 ## Spotted in now - GitHub Trending Python today: #12, +118 stars ## Similar by description 1. **alibaba/open-code-review** — 2.9 · Steady · Developer tools · Go · +32 stars measured 2026-10-31, 00:28–13:40 UTC, ≈ 69 by evening AI code review tool from Alibaba: reads git diffs and, via an LLM agent with file access and repo search, produces line-level review comments. Ships with built-in rules (NPE, thread-safety, XSS, SQL injection) and a whole-file scan mode. Full card: https://gitnova.dev/en/r/alibaba/open-code-review.md --- Magnitude (0–10) measures how fast and how unusually interest in a repository is growing right now. It is not a quality score. Days are UTC. “So far today” is a fact; “expected by the end of the day” is a forecast. Summaries and use cases are written by an LLM (DeepSeek V4.1 Flash) from the README and may be inaccurate: verify specific claims (benchmarks, speed, hardware) in the repository itself. Data as of 2026-10-31 13:48 UTC, updated every 30 minutes.