front-end-checklist vs pr-agent
Two of the top projects in Code review and testing, side by side: who leads on each score part and who each one suits, then setup, license, activity and what each review found.
front-end-checklist
Front-end rules checklist with an MCP server for agent code review
pr-agent
LLM pull request reviewer that comments via /review, /describe and /improve
Verdict
front-end-checklist ranks higher, 63 to 59. Of the 5 score parts we measure for both, front-end-checklist leads on 2, pr-agent on 1 and 2 are even.
- Adoptionfront-end-checklist leads by 72 points, 94 to 22: a wide gap.
- FreshnessEven at 100.
- Maintenancepr-agent leads by 66 points, 99 to 33: a wide gap.
- Easy to runEven at 33.
- Agent-readyfront-end-checklist leads by 40 points, 70 to 30: a wide gap.
Pick front-end-checklist if you are
Front-end developers and teams auditing sites or feeding rules to agents
- 386 rules with Critical/High/Medium/Low priorities, grouped into 11 categories
- Hosted MCP server exposes 11 tools, including review_code, search_rules and audit_url
Pick pr-agent if you are
Teams wanting self-hosted AI pull request review in CI or on their git host
- Supports GitHub, GitLab, Bitbucket, Azure DevOps and Gitea
- Model-agnostic via LiteLLM: OpenAI, Claude, Gemini, Bedrock, Ollama and others
| What we compare | front-end-checklist | pr-agent |
|---|---|---|
| Score parts, out of 100 | ||
| Adoption | 94, widely used | 22, niche |
| Freshness | 100, active | 100, active |
| Maintenance | 33, patchy | 99, healthy |
| Easy to run | 33, some setup | 33, some setup |
| Agent-ready | 70, partly | 30, minimal |
| Facts from GitHub and the README | ||
| Stars | 74.5k | 13.4k |
| License | MIT (permissive) | MIT (permissive) |
| Last commit | Oct 2026 | Oct 2026 |
| Last release | May 2026 | Oct 2026 |
| Language | MDX | Python |
| Docker | No | Yes |
| GPU | Not needed | Not needed |
| arm64 or Apple Silicon | Not stated | Not stated |
front-end-checklist
A corpus of 386 English front-end rules across 11 categories (HTML, CSS, JavaScript, performance, accessibility, SEO, security, images, testing, privacy, i18n), each with a priority level, remediation guidance and verification steps. It is readable on the website or in the README, and a hosted MCP server and installable skills let agents review code or audit public URLs against the same rules.
Who it is for: Front-end developers and teams auditing sites or feeding rules to agents
Strengths
- 386 rules with Critical/High/Medium/Low priorities, grouped into 11 categories
- Hosted MCP server exposes 11 tools, including review_code, search_rules and audit_url
- Skills install with `npx skills add frontendchecklist/skills`, global or per rule
- MIT licensed; rules also usable as a plain README checklist without any tooling
Weaknesses
- Content repo, not a linter: findings come from an agent applying the rules
- audit_url only handles public https:// pages
- Security, privacy and i18n categories are thin (22, 5 and 5 rules)
- MCP tool discovery can be lazy in some clients; the prompt must name the server
- no GPU
- Needs MCP-compatible client, pnpm (for contributing)
pr-agent
PR-Agent runs as a GitHub Action, CLI, Docker image or webhook service and posts AI-generated descriptions, reviews, code suggestions and Q&A on pull requests. Each tool makes a single LLM call, and a compression strategy handles large diffs. It supports GitHub, GitLab, Bitbucket, Azure DevOps and Gitea, and any model reachable through LiteLLM.
Who it is for: Teams wanting self-hosted AI pull request review in CI or on their git host
Strengths
- Supports GitHub, GitLab, Bitbucket, Azure DevOps and Gitea
- Model-agnostic via LiteLLM: OpenAI, Claude, Gemini, Bedrock, Ollama and others
- One LLM call per tool, about 30 seconds per command
- Review behavior is configurable through a TOML settings file and JSON prompts
Weaknesses
- Described as a community-maintained legacy project of Qodo
- /help_docs is disabled since v0.36.1 over a credential-exposure issue
- Needs your own LLM API key and per-provider setup
- Docker images moved to pragent/pr-agent from 0.34.2, so pinned references break
- no GPU
- Docker + Compose
- Needs LLM API key (e.g. OpenAI), Git provider token
- Models: OpenAI GPT, Anthropic Claude, Google Gemini, DeepSeek, Mistral
More in Code review and testing
Building with these?
We help teams pick an open-source AI stack and run it in production. Client work never changes a rank.