Where can Nitpicker run?

Nitpicker can deploy to AWS Lambda, Cloudflare Workers, GitHub Actions, or a user's own server.

Is my code kept private?

Yes. Nitpicker is open source and self-hosted, so your PRs never become someone else's training set—you hold the keys and can audit the prompts yourself.

How much does it cost?

The creator states it costs pennies to operate, and the tool is free and open source.

AI Coding AssistantsOpen-Source AIHacker NewsAug 10, 2026Aug 11, 2026, 01:01 JST2 min read

Nitpicker: Open-source AI code reviewer launched after $1M vendor quote

Send on LINE

Key takeaway

A developer has released Nitpicker, an open-source AI tool that reviews GitHub pull requests and provides code feedback, after being quoted $1 million for a vendor solution.
The tool runs on multiple platforms (AWS Lambda, Cloudflare Workers, GitHub Actions, or your own server), costs pennies to operate, and keeps code private—ensuring pull requests don't become part of someone else's AI training data.
It emphasizes fast, token-efficient reviews rather than lengthy analyses.

3 Key Points

What happened
A developer built Nitpicker, an open-source AI tool that reviews GitHub pull requests and flags issues in code changes. It can run on AWS Lambda, Cloudflare Workers, GitHub Actions, or a user's own server, and costs pennies to operate.
Why it matters
The creator was quoted $1M for AI-powered PR review from a vendor, prompting them to build an alternative. Nitpicker keeps code reviews private (PRs don't become training data), uses fewer tokens for faster reviews, and can be self-hosted and audited — avoiding lock-in to cloud-only vendor solutions.
What to watch
Installation is one line (curl -fsSL https://nitpicker.dev/install | bash). The tool is free and open source, letting teams audit the prompts and retain full control of their code diffs.

Ask the AI about this article →

Summaries like this, in your inbox every morning.

Get news like this every morning — free

Context & Analysis

The announcement reflects a growing tension in the AI tooling market: vendors offering specialized AI services at enterprise prices, versus developers building lean, self-hosted alternatives. The creator's $1M quote from an unnamed vendor became the catalyst—a common inflection point where a single prohibitive estimate pushes a team to in-house solution. Nitpicker positions itself around three concrete pain points: cost (enterprise vendors charge heavily per review), privacy (vendor tools can train on submitted code), and flexibility (cloud-only lock-in). The tool's emphasis on "token-stingy" reviews and support for multiple deployment targets (Lambda, Workers, Actions, or BYOS) suggests it targets teams already running their own infrastructure and seeking to avoid both vendor dependency and large language model token spend. The one-line install and open-source licensing are deliberate signals of accessibility and auditability—removing friction for adoption and trust.

FAQ

Where can Nitpicker run?: Nitpicker can deploy to AWS Lambda, Cloudflare Workers, GitHub Actions, or a user's own server.
Is my code kept private?: Yes. Nitpicker is open source and self-hosted, so your PRs never become someone else's training set—you hold the keys and can audit the prompts yourself.
How much does it cost?: The creator states it costs pennies to operate, and the tool is free and open source.

Hacker NewsRead Original Article