Powered by Claude — #1 on SWE-bench Verified

AI that fixes
your bugs

Label a GitHub issue. Plip reads your code, writes a fix with tests, runs your test suite, and opens a PR. You review, approve, and merge.

Install on GitHub — it's free See how it works
plip[bot] investigating issue #42

-- Turn 1 (12s) [12.3k tokens] --

Reading src/providers/elevenlabs.ts...

Searching for "listVoices" in codebase...

-- Turn 2 (18s) [24.1k tokens cache:19.2k] --

Hypothesis: listVoices() returns undefined on API failure,

but findIndex() is called without a null guard.

-- Turn 3 (22s) --

-> edit_file("src/providers/elevenlabs.ts")

Added ?? [] fallback when listVoices returns undefined

-- Turn 4 (28s) --

-> write_file("src/providers/__tests__/elevenlabs.test.ts")

Added regression test: "should return empty array when API fails"

-- Turn 5 (35s) --

-> run_command("npm test")

42 tests passed, 0 failed

-- Turn 6 (38s) --

-> create_pr("Fix: guard against undefined listVoices result")

PR created: github.com/your-repo/pull/87

Duration: 38s | Tokens: 156k | Cost: ~$0.12

Three steps. That's it.

No config files required. Install the app, label an issue, and get a PR.

1

Label an issue

Add the plip label to any bug report. That's the trigger.

2

Plip investigates

Plip clones your repo, reads the code, finds the bug, writes a fix with tests, and verifies everything passes.

3

Review and merge

A clean PR appears with the fix, regression tests, and a clear explanation. Always review before merging — Plip assists, humans decide.

Not just a patch. A proper fix.

Most AI tools generate code. Plip debugs like a senior engineer — it investigates, hypothesizes, fixes, tests, and verifies.

Writes tests, not just patches

Every PR includes regression tests that prove the fix works. Tests that verify behavior — not just that code exists.

Powered by the best model

Claude scores 80.9% on SWE-bench Verified — the highest of any AI model on real-world GitHub issues. Plip uses the best tool for the job.

Fully transparent

See every step Plip took — which files it read, what hypothesis it formed, how it verified the fix. No black box.

Sandboxed and secure

Every fix runs in an isolated container that's destroyed after the job. Your code is never stored. Network access is locked to GitHub and the AI provider only.

Any language, any framework

TypeScript, Python, Go, Rust, Java, C#, Ruby — Plip auto-detects your stack, installs dependencies, and runs your test suite.

Multi-platform (coming soon)

GitHub today. GitLab and Bitbucket coming soon. Same workflow, wherever your code lives.

Simple pricing. Pay for fixes, not seats.

One fix = one issue resolved with a PR. No per-seat fees, no token counting.

Free

Try it out

$0 /mo
  • 3 fixes per month
  • Up to 3 repos
  • Label trigger only
  • Chatbot support
Get started
Most popular

Pro

For active projects

$29 /mo
  • 15 fixes per month
  • Up to 5 repos
  • Label & auto triggers
  • Chatbot support
Start free trial

Team

For growing teams

$79 /mo
  • 50 fixes per month
  • Up to 20 repos
  • Priority job queue
  • Chatbot support
Start free trial

Business

For larger orgs

$199 /mo
  • 200 fixes per month
  • Up to 50 repos
  • Highest priority queue
  • Chatbot support
Start free trial

All prices in USD. No overage charges — upgrade anytime if you need more.

Frequently asked questions

Is my code safe?
Yes. Every fix runs in an isolated container that's destroyed after the job completes. Your code is cloned temporarily, never stored permanently. Network access is restricted to GitHub and the AI provider — no data leaves the sandbox. We never train on your code.
What languages does Plip support?
Any language. Plip auto-detects your project's language and package manager, installs dependencies, and runs your test suite. It works best with TypeScript, Python, Go, Rust, Java, C#, Ruby, and C++ — but it can handle anything with a standard build/test setup.
What if the fix is wrong?
Plip is an AI tool — it is not infallible. Every change Plip proposes is a pull request that requires human review before merging. Plip runs your test suite, but passing tests do not guarantee the fix is correct, secure, or complete. You are responsible for reviewing, testing, and deciding whether to merge any PR. If the fix isn't right, close the PR. Plip never pushes to your main branch directly. See our Terms of Service for full details.
How long does it take?
Typically 3-10 minutes, depending on the complexity of the bug and the size of the codebase. Plip takes as long as it needs to get the fix right — slow and correct beats fast and wrong.
How is this different from GitHub Copilot?
Copilot's coding agent is great but it's part of a $10-39/user/month suite you might not need. Plip is focused: just bug fixing, with the highest-scoring AI model, regression tests in every PR, full transparency into the agent's reasoning, and multi-platform support coming soon. Pay per fix, not per seat.
Can I self-host Plip?
Not yet, but it's on the roadmap. Enterprise customers who need to keep code on-premises can contact us to discuss early access to self-hosted Plip.

Stop fixing bugs manually.

Install Plip in 30 seconds. Your first 3 fixes are free, every month.

Install on GitHub

Plip is an AI-powered tool that generates code suggestions. All pull requests require human review before merging. Plip does not guarantee the correctness, security, or completeness of any proposed fix. You are solely responsible for reviewing, testing, and deciding whether to merge any code. By using Plip, you agree to our Terms of Service and Privacy Policy.