|
Margyn: audit your test suite and prove which checks are hollow
Margyn finds tests that assert nothing, files git never committed and gates nothing invokes, then ships a command that reproduces every finding. Free CLI, $8...
|
84 % |
|
flowgate — Guardrails for AI coding agents that actually hold
Your AI coding agent deployed before tests and approved before review, and a longer prompt didn't fix it. flowgate puts agents on a state machine they can't...
|
84 % |
|
TestFinch: catch the bug, fix it with your agent, keep it fixed
Snag reports bugs from the browser or a phone with the screenshot, console and network attached. Your coding agent reads and fixes them through the TestFinch...
|
83 % |
|
runhmd — AI writes it. runhmd proves it.
runhmd is a verification layer for AI coding agents. AI writes it; runhmd tries to break it and says PROVEN only if it survives, otherwise DENIED with the ca...
|
82 % |
|
runhmd — AI writes it. runhmd proves it.
runhmd is a verification layer for AI coding agents. AI writes it; runhmd tries to break it and says PROVEN only if it survives, otherwise DENIED with the ca...
|
82 % |
|
CORETEXA — Can this pull request's own tests actually fail?
A pull request says it fixes a bug and adds tests. coretexa-verify puts the source back the way it was, keeps the new tests, and runs them again. If they sti...
|
82 % |
|
Corund — gate-integrity for AI-generated code
Corund is a merge check that proves an AI agent's tests can fail: it reverts the change and requires the new tests to go red, restores it and requires green.
|
82 % |
|
blastproof · AI testing agent for pull requests
Open-source AI testing agent for pull requests. End-to-end tests in plain English, run only where your diff lands. 100% local, MIT, bring your own LLM key.
|
82 % |
|
GTMS: Git Test Management System
Track your testing the way Git tracks your code. GTMS turns requirements into version-controlled test cases, runs them with AI, and shows your coverage at a...
|
81 % |
|
tolerance
Your coding agent builds a game or a site, you upload it: the platform scores it and everyone plays and votes.
|
81 % |
|
AI Agent Coder — Autonomous coding agent for complex tasks
AI Agent Coder plans, writes, tests, and ships code autonomously. Give it a task, review the PR.
|
81 % |
|
Forgehand
The tests passed. The code didn't. A coding agent hid fields from the assertions and the suite went green. Forgehand reads every pull request for a change th...
|
81 % |
|
RunBoth: find out what your refactor actually changed
RunBoth runs both versions of your code on generated inputs and reports what actually behaves differently, including the functions nobody touched. A commit g...
|
81 % |
|
Variance Authority — Understand the code. Investigate the behavior. Check the work.
Open-source tools for developers and coding agents: source intelligence, live test inspection, test selection and reduction, UI analysis, and change verifica...
|
80 % |
|
Tektonix — autonomous coding agent
A self-hosted autonomous coding agent, now with a Windows app. Give it a plain-English goal and it plans the work, writes the code, runs your project's real...
|
80 % |
|
Reticle · Make your coding agent verify its own work
Make your coding agent verify its own work, and not by asking it. Reticle is AI app testing that runs inside your app: it walks the flow the way a user would...
|
80 % |
|
breakmy.AI — Silent failures, caught within the hour
AI test agent for B2B platforms. Continuous testing of APIs, integrations and asset connectivity. Book a free two-week Critical-Path Scan.
|
80 % |
|
Testura — AI Testing for Vibe-Coded Apps
Connect your GitHub repo. Testura reads your code, generates tests, runs them, and tells you what broke — zero manual work required.
|
80 % |
|
Mergestro — know what a change breaks before it merges
Mergestro Gate mutates the code you changed and checks whether your suite notices — free, Apache-2.0, one line in your CI. Mergestro Queue derives your compo...
|
80 % |
|
fastverk — agents that behave
Give a coding agent real work without giving it the keys. fastverk sets how much it can spend, which packages it can touch, and who signs off. Then it runs e...
|
80 % |
Detected social media networks