# The best ai coding agents and automated pull request tools

> Agents that take a written task or an issue, change code across a repository, run tests, and open a pull request for human review.

Last reviewed 2026-09-20. Canonical page: https://launch500.com/best/ai-coding-agents

## What has to be true to appear here

- Operates across a repository, not a single file or an editor autocomplete
- Runs the project's own tests before proposing a change
- Opens a reviewable diff rather than writing directly to a default branch
- Documents what repository access it requires

## What every product here was put through

1. Assign 40 real issues from three open-source repositories of different sizes and measure the share of pull requests merged without human edits
2. Measure how often the agent claims tests pass when they do not
3. Review 20 diffs for scope creep, unrelated files touched, formatting churn, dependency additions
4. Test behaviour on an under-specified issue: does it ask, or does it guess and commit?

## The shortlist

Ranked by Crash Test score. Untested products appear below tested ones regardless of community rating.

| Product | Crash Test | Verified reviews | From (5 seats) | Best for |
| ------- | ---------- | ---------------- | -------------- | -------- |

## Verdicts

## Frequently asked questions

---

Launch500 independently tests SaaS and business software. Inclusion and order are not for sale: https://launch500.com/trust/how-we-make-money