VS Code Extension · Alpha

AI Tests That Find
Bugs Before Production

Generate pytest suites that actually run - and expose issues in your code.90% average pass rate. Source bugs flagged with fix suggestions.

Get Started FreeInstall Extension

Free forever · 7 credits/month · No credit card required

Join waitlist for paid plans
Test Generation
Target File
benchmarks/python/real/notifications.py
Completed successfully (Bugs verified)
Pass rate:75%
True quality:100%
Bugs found:2
Tests passing:6/8 (75%)
Time:1m 22s
✓
Code analysis
✓
Initial generation
✓
Working on functions
✓
Finished
Recent activity▼
Generating tests for function 1/2: testing notifications...
Generating tests for function 2/2: testing notifications...
Fixing failures (attempt 2/3)...
Running final test suite...
847
Test suites generated
127
Source bugs discovered
91%
Average pass rate

* Stats updated weekly. Based on active Alpha usage.

See it in action

From Code to Tests in 3 Clicks

KeelTest Demo - VS Code

Ready to Generate More Tests?

Join ... developers on the waitlist for premium plans with more credits and priority support.

Compare all plans
Install from VS Code Marketplace

Get Started in 3 Simple Steps

KeelTest is a VS Code extension that installs in seconds. No complex setup, no external services.

1

Open VS Code Extensions

Press Ctrl+Shift+X (Windows/Linux) or Cmd+Shift+X (Mac) to open the Extensions view in VS Code.

2

Search for KeelTest

Type "KeelTest" in the search bar and click Install on the official KeelTest extension.

3

Right-Click and Generate

Right-click any Python file in your workspace and select "KeelTest: Generate Tests" to start.

Install KeelTest Extension

Free to install • Available on VS Code Marketplace • No credit card required

Why developers switch
to KeelTest

Moving beyond simple prompts. We combined static analysis with a multi-step verification pipeline to deliver production-grade tests.

Start Free, Scale When Ready

Join ... developers already on the waitlist for our upcoming premium tiers.

Individual Plans

Starter

For regular development

$9.99/month
30 credits4x Multiplier
  • Priority queue
  • Usage analytics
  • Bug detection

Pro

For power users

$19.99/month
70 credits10x Multiplier
  • Priority queue
  • Usage analytics
  • Bug detection
  • Early access to features
Current Plan

Free

7 credits / month1x Base

Perfect for trying it out

Basic queue access
Bug detection
Start Free

Detailed Comparison

Everything you get with each tier

Feature
Free
Starter
Pro
Monthly Credits
7
30
70
Support Queue
Basic
Priority
Priority
Bug Detection
✅
✅
✅
Usage Analytics
❌
✅
✅
Early Access
❌
❌
✅
* All plans include self-healing tests, deep static analysis, and smart dependency mapping.

How Far Your Credits Go

Estimated files per month based on complexity

File SizeFreeStarterPro
Small files (≤15 fn)~15 functions
~7
files/mo
~30
files/mo
~70
files/mo
Medium files (~30 fn)~30 functions
~3
files/mo
~15
files/mo
~35
files/mo
Large files (~50 fn)~50 functions
~1
files/mo
~7
files/mo
~17
files/mo
1 credit = up to 15 functions. Larger files use proportionally more credits.

Real Pass Rates, Not Marketing

Every test is executed in a sandbox before it reaches your editor. We don't just generate code; we deliver verified functionality.

90%
Average Pass Rate
Tested on 100+ real-world Python files
Self-Healing Generation

Failures are automatically fixed by our AI validator before delivery.

Source Bug Detection

Real issues in your source code are triaged and clearly flagged.

Sandbox Execution

Tests run in isolation before reaching your project.

Linter Compliant

All output passes ruff and follows PEP8 standards.

Independent Benchmark Results

Tests That Actually Test

We tested leading AI models on generating unit tests for complex e-commerce logic. KeelTest's agentic approach-combining AI with static code analysis, test validation, and actual execution-achieved a staff-level score of 8.5/10, outperforming pure zero-shot prompts by 54%.

Overall Quality ScoreStaff Engineer = 10

KeelTest (Agentic)(Agentic AI + Static Analysis)
8.5/10
Model B (Claude Sonnet 4.5)(Zero Shot)
5.5/10
Model C (Grok Auto)(Zero Shot)
3.5/10
Model A (GPT 5.1)(Zero Shot)
2.5/10

Detailed Evaluation Criteria

CriteriaKeelTestModel BModel CModel A
Unit Test Isolation
Mocking & Dependency Injection
Edge Case Coverage
Following Instructions
Technical Correctness
DateTime/Float Precision
Excellent
Partial
Poor/Missing
8.5/10
KeelTest Score
Staff Level
54%
Better Than
Best Zero-Shot
100%
Unit Test Isolation
Proper Mocking
95
Tests Generated
All Passing

"KeelTest demonstrates the deepest understanding of unit testing principles with proper isolation, comprehensive mocking, and dependency injection. It's what a staff engineer would produce."

* KeelTest leverages advanced AI models enhanced with static code analysis, automated test validation, and real-time execution feedback-not just raw prompts.

Frequently Asked Questions

Failing tests are often the most valuable. Our triage system distinguishes between generation issues (our problem - we fix them automatically) and source bugs (your code's problem - we flag them with fix suggestions). If the pass rate is below 70% due to generation issues, we don't charge a credit. But tests that reveal real bugs? Those are features, not failures.
Because you paid for comprehensive coverage. Failing tests often reveal real edge cases or bugs in your code. They are valuable signal for understanding your system, even if they need a small amount of manual fixing before you commit them.
We use a simple tier-based system. Small files (1-15 functions) cost 1 credit. Medium files (16-30 functions) cost 2 credits. Your credits reset every 30 days based on your plan (7 for Free, 30 for Starter, 70 for Pro).
We use a specialized KeelTest agent powered by OpenAI's models. It understands business logic, mocks side effects intelligently, and writes production-grade pytest code. We no longer offer a 'fast' mode because we believe quality is non-negotiable.
Currently Python with pytest. We are always looking for ways to support more languages.
Full refund within 14 days if you're not satisfied. No questions asked.
Yes, you can switch plans at any time. If you upgrade, you'll get the difference in credits immediately. If you downgrade, your new limit will apply at the start of the next billing cycle.