How does Vinv verify that a fix actually works?

Vinv restarts the app in a fresh process, requires the port to actually serve, and runs acceptance tests that were written before the fix and which the agent never sees. If tests fail, the findings feed the next attempt and one click reverts everything the fix touched.

Does Vinv require code changes or SDK integration?

No. Vinv runs Python services with zero code changes and traces without requiring any SDK integration.

How does Vinv compare with frontier AI models for code fixing?

In testing, a commodity model with Vinv evidence found 4 bugs and 1 optimization, while a frontier model without evidence found only 1 bug, and a commodity model without evidence found nothing. The evidence made the difference, not the model size.

My AI coding agent says done but the tests fail. How does Vinv help?

Vinv never accepts the agent's own claim. When a fix comes back it restarts the app in a fresh process, requires the port to actually serve, and runs acceptance tests generated before the fix that the agent never sees. Failures feed the next attempt; one click reverts everything the fix touched.

What does Auto-Pilot exercise today?

Services and APIs. Auto-Pilot discovers runnable Python services, brings them up under tracelens, and drives their HTTP and related entrypoints. Plain library or in-process function driving is not the Auto-Pilot surface right now.

AI testing & review

Vinv

Tools and algorithms for AI agents to test, fix and optimize your codebase

0 votes. Log in to give Vinv a nod

Community votes: 0
DR by Ahrefs: 9 +1 (up) since last check

Ahrefs Domain Rating benchmarked 29 Oct 2026, rebuilt 27 Oct 2026.

Vinv runs Python services with zero code changes, provides AI agents with real runtime evidence, then re-runs code to verify fixes locally.

What it is

Screenshot of the Vinv homepage — vinv.ai, as visitors see it

Vinv is a set of tools and algorithms that enables AI agents to test, fix, and optimize Python codebases. It runs Python services with zero code changes and generates real runtime evidence—traces, argument values, failing frames—for AI agents to use when fixing issues. After the agent proposes a fix, Vinv re-runs the code to verify it works, ensuring the fix passes acceptance tests before deployment.

The platform provides multiple detection methods including an HTTP exerciser for endpoints, differential oracles for comparing against reference implementations, fault injection at dependency boundaries, concurrency oracles for detecting deadlocks, environment compatibility checks, golden I/O baselines, dead code detection from actual execution, and runtime analysis for hotspots and memory leaks.

Vinv works as an MCP server compatible with any AI coding agent—Claude Code, Cursor, Windsurf, Codex, Gemini CLI, and others—eliminating the need for new subscriptions or API keys. It runs 100% locally with an embedded model that never uploads data, maintaining complete privacy and control.

What it is built with

Acceptance test verification before fix deployment
One-click revert of all changes from a failed fix attempt

Pricing

Pricing model: Free

Vinv is free and open source under the Apache 2.0 license.

Vinv metrics

Benchmarks for vinv.ai: Ahrefs Domain Rating and Majestic link data, with the change since the last build.
Metric	Value
Domain Rating	9 +1 (up) since last check
Trust Flow	0 no change since last check
Citation Flow	13 no change since last check
Referring domains	39 no change since last check
External backlinks	160 no change since last check

Ahrefs Domain Rating benchmarked 29 Oct 2026, rebuilt 27 Oct 2026. Majestic benchmarked 6 Oct 2026, rebuilt 6 Oct 2026. Link data built by Majestic. Trust Flow, Citation Flow and Topical Trust Flow are trademarks of Majestic-12 Ltd.

Vinv domain build sheet

Open the build sheet

Public RDAP record, last read 28 Oct 2026, 15:16 UTC.
Domain age	5 months
Registered	4 May 2026
Expires	4 May 2028
Registrar	GoDaddy.com, LLC
DNSSEC	Not signed

Inspect vinv.ai's registration

Vinv after-launch build log

Since Vinv launched on Maker Launches on 6 October 2026, these are the figures we have tracked.

Domain Rating (Ahrefs): 9 −1 (down) since launch; 10 at launch (6 Oct 2026), 9 on 29 Oct 2026
Referring domains (Majestic): 39; First measured 6 Oct 2026

Day 24 since launch. Next receipt: day 30, 5 Nov 2026. We show what changed, not what caused it: many things affect these numbers. Nothing here is estimated.

Biggest gains on Maker Launches

Compare and explore

Questions from the bench

How does Vinv verify that a fix actually works?: Vinv restarts the app in a fresh process, requires the port to actually serve, and runs acceptance tests that were written before the fix and which the agent never sees. If tests fail, the findings feed the next attempt and one click reverts everything the fix touched.
Does Vinv require code changes or SDK integration?: No. Vinv runs Python services with zero code changes and traces without requiring any SDK integration.
How does Vinv compare with frontier AI models for code fixing?: In testing, a commodity model with Vinv evidence found 4 bugs and 1 optimization, while a frontier model without evidence found only 1 bug, and a commodity model without evidence found nothing. The evidence made the difference, not the model size.
My AI coding agent says done but the tests fail. How does Vinv help?: Vinv never accepts the agent's own claim. When a fix comes back it restarts the app in a fresh process, requires the port to actually serve, and runs acceptance tests generated before the fix that the agent never sees. Failures feed the next attempt; one click reverts everything the fix touched.
What does Auto-Pilot exercise today?: Services and APIs. Auto-Pilot discovers runnable Python services, brings them up under tracelens, and drives their HTTP and related entrypoints. Plain library or in-process function driving is not the Auto-Pilot surface right now.

Leave a review for Vinv

Nobody has put Vinv on the bench yet. Leave the first review.

Reviewing is free, and nobody can pay for a review. Read the bench notes

Maker reviews · Workshop notes · Show it off · Did you make this? Claim it · Report this build

More builds like this

#1

Number 1: Ora

Make your site work for agents
- AI testing & review
- United States
- DR 60 +1 (up) since last check
2 votes. Log in to give Ora a nod
#2

Number 2: Ocular AI

Encoding Human Expertise into Machines
- AI testing & review
- United States
- DR 28 +1 (up) since last check
1 votes. Log in to give Ocular AI a nod
#3

Number 3: Dock

One-click molecular docking with AutoDock Vina in your browser
- AI testing & review
- DR 3 +1 (up) since last check
0 votes. Log in to give Dock a nod
#4

Number 4: Cobalynx

Free AI detector with published error rates
- AI testing & review
- Italy
- DR 0 no change since last check
0 votes. Log in to give Cobalynx a nod