Nicheloom

Market intelligence for builders — see what's gaining traction before it's crowded.

KeelTest

AI-driven VS Code unit test generator with bug discovery

Details

External ID
46526088
Source
HN
Company
—
Product
KeelTest
Website domain
keelcode.dev
Launched
Jan. 7, 2026
Cohort
—
Upvotes
30
Upvotes percentile
0.7134387351778656
Tags
—
Fetched at
Sept. 7, 2026, 9:25 p.m.
Updated at
Sept. 7, 2026, 9:25 p.m.

Description

I built this because Cursor, Claude Code and other agentic AI tools kept giving me tests that looked fine but failed when I ran them. Or worse - I'd ask the agent to run them and it would start looping: fix tests, those fail, then it starts "fixing" my code so tests pass, or just deletes assertions so they "pass".Out of that frustration I built KeelTest - a VS Code extension that generates pytest tests and executes them, got hooked and decided to push this project forward... When tests fail, it tries to figure out why:- Generation error: Attemps to fix it automatically, then tries again- Bug in your source code: flags it and explains what's wrongHow it works:- Static analysis to map dependencies, patterns, services to mock.- Generate a plan for each function and what edge cases to cover- Generate those tests- Execute in "sandbox"- Self-heal failures or flag source bugsPython + pytest only for now. Alpha stage - not all codebases work reliably. But testing on personal projects and a few production apps at work, it's been consistently decent. Works best on simpler applications, sometimes glitches on monorepos setups. Supports Poetry/UV/plain pip setups.Install from VS Code marketplace: https://marketplace.visualstudio.com/items?itemName=KeelCode...More detailed writeup how it works: https://keelcode.dev/blog/introducing-keeltestFree tier is 7 tests files/month (current limit is <=300 source LOC). To make it easier to try without signing up, giving away a few API keys (they have shared ~30 test files generation quota):KEY-1: tgai_jHOEgOfpMJ_mrtNgSQ6iKKKXFm1RQ7FJOkI0a7LJiWgKEY-2: tgai_NlSZN-4yRYZ15g5SAbDb0V0DRMfVw-bcEIOuzbycip0KEY-3: tgai_kiiSIikrBZothZYqQ76V6zNbb2Qv-o6qiZjYZjeaczcKEY-4: tgai_JBfSV_4w-87bZHpJYX0zLQ8kJfFrzas4dzj0vu31K5EWould love your honest feedback where this could go next, and on which setups it failed, how it failed, it has quite verbose debug output at this stage!

Enrichment

Theme
AI agent frameworks and developer tools
Vertical
—
Function
Agent / copilot
Audience
Developer
AI stance
AI-native
Project type
Commercial product
Normalized one-liner
ai unit test generator for vs code
Manually corrected
False

Could you build this?

Yes This is a VS Code extension that interacts with language servers and test runners, passing test failure outputs back into an LLM prompt with strict system instructions.

Discussion

15 comments analyzed.

Competitors mentioned: Microsoft Copilot, Cursor, Claude Code, Codex, mutation testing

Concerns raised: Non-scalable approach, Generates unnecessary/boilerplate tests that don't add value, LLMs hallucinate and assume behavior not in source code, Difficulty determining if test failure is bug vs test design issue, Generated tests pass but fail for wrong reasons when manually broken

Feature requests: Support for larger files beyond 15 functions, Negative/error case test generation, Generated test annotations and justifications, Design doc context to reduce hallucinations, Language/framework-specific test requirements tuning

Competitors

Other products that read as similar to this one — 253 launches clear the similarity bar, closest 8 shown.

Attention rank: #87 of 254 (itself plus its competitors, highest first — normalized so YC and Product Hunt are compared fairly).

Launched 69 days after the earliest competitor.

Other launches for this product