lgtmaybe

lgtmaybe reviews the code a pull request changes. Pick OpenAI, Claude, Bedrock, Vertex, Azure, ollama, or any OpenAI-compatible endpoint, then run it on GitHub, GitLab, or Gitea — or from your terminal. The change gets inline comments and one summary; locally, you get the same findings before you push.

It reads the diff and a little surrounding code, but only comments on changed lines. It never checks out or runs the change. Generated files and binaries are skipped, secrets are redacted, and all author-supplied text is treated as untrusted.

It checks for:

• Correctness and security — logic errors, missed awaits, injection, auth mistakes, and leaked secrets.
• Code health — performance problems, needless complexity, deprecations, and risky dependencies.
• Tests and documentation — missing or weak tests, stale comments, and undocumented APIs.
• Intent — whether the change does what its title, description, and commits say it does.
• Ponytail — code you don't need, standard-library opportunities, and simpler ways to get the job done.

Findings are graded from info to critical and land on the exact changed line. A clean change just gets a 👍 LGTM!.

Reviews aren't all it does. /review and /improve run the review, and /diagram posts the change overview — a description, a bold High Impact Areas call-out (infrastructure, security posture, outage risk, migrations, backups, compatibility, cost and more), a flowchart of what the change touches and a sequence diagram of the flow it alters. /ask answers questions in the change. Run lgtmaybe diagram to print the same overview locally.

flowchart LR
    web["Storefront<br/>React<br/>places orders"]
    api["Order API<br/>Python<br/>creates orders (changed)"]
    db["Order database<br/>PostgreSQL<br/>stores orders"]
    queue["Order events<br/>SQS<br/>buffers events (new)"]
    worker["Notification worker<br/>Python<br/>sends confirmations (new)"]
    email["Email provider<br/>delivers messages"]
    web -->|calls| api
    api -->|stores in| db
    api -->|publishes to| queue
    queue -->|delivers to| worker
    worker -->|sends via| email

Start here

• Tutorial — Getting started: your first review with ollama, locally and free.
• How-to — task recipes: choose a review model, run locally, Bedrock OIDC, Vertex WIF, Azure OpenAI, GitHub Action, GitLab, Gitea.
• Reference — Configuration: every config field and schema.
• Explanation — What gets reviewed, Architecture, Auth model, Data & privacy.

Providers

Provider	Auth
openai	OPENAI_API_KEY
anthropic	ANTHROPIC_API_KEY
openrouter	OPENROUTER_API_KEY
zai	ZAI_API_KEY — GLM / Zhipu AI; optional --api-base for the China / coding-plan endpoint
bedrock	Ambient AWS creds — GitHub OIDC, no static key
vertex	Ambient GCP creds — Workload Identity Federation, no key
azure	Ambient Azure AD creds — GitHub OIDC, no static key (or AZURE_API_KEY) + endpoint
ollama	None — local only, zero cost
openai-compatible	--api-base to any OpenAI /v1 endpoint; key optional (placeholder for keyless local servers)

Where it posts

The model provider and the code host are independent — any provider above works on any host below.

Host	How it runs	Token	Guide
GitHub	GitHub Action	GITHUB_TOKEN	GitHub Action
GitLab	GitLab CI job	GITLAB_TOKEN	Review on GitLab
Gitea	Gitea Actions	GITEA_TOKEN	Review on Gitea
None	lgtmaybe review locally	—	Install the CLI

The review is identical on all three. What differs is what each host's API can do with the result — auto-resolving a fixed finding, reviewing only new commits, and keyless cloud auth are not available everywhere. See Architecture for the details.

For AI agents

The site root publishes a curated llms.txt index of these docs, plus a whole-corpus llms-full.txt, for LLM crawlers and coding agents.