|
Strata — Compose backend features into your codebase
Strata composes proven backend modules into your project — reading your schema, following your conventions — and writes one command that proves the feature w...
|
82 % |
|
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...
|
81 % |
|
testy — write the test, skip the code
Describe a user journey in plain language. Testy turns it into a Playwright test, runs it from your CI, and fixes it when your app changes.
|
80 % |
|
tBelt | Software Studio
Digital product development, applications, and tools. Independent software studio.
|
80 % |
|
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...
|
80 % |
|
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...
|
80 % |
|
Smart SSH — See every command before it runs
An SSH client with an AI copilot that reads logs and suggests the fix — but never runs a command without your approval. macOS, Windows, Linux.
|
80 % |
|
Skeg — The AI wrote it. Now prove it's right.
Skeg gives AI-written code a spec to answer to, a review before you push, and a gate it must pass. Any IDE, any agent, any model. Self-hosted. Free for up to...
|
80 % |
|
Developer Bot — ships code, waits for your yes
Developer Bot reads your Jira tickets, writes a reasoned plan, waits for a named engineer to approve it in Slack, then opens the merge request in GitLab. Sel...
|
80 % |
|
Trust what your AI writes - a deterministic check · doloop
AI writes your code and pulls your data - but can you trust it? doloop flags what it can prove, deterministically, the same verdict every run. Bring your own...
|
79 % |
|
OpusMill — make it work on Windows
Your Node project works on your Mac and breaks on your colleague's Windows machine. I find every place it breaks and fix them. Free checker, paid repair.
|
79 % |
|
Verity: Local repository run verification
Check whether a repository you trust can build, test, launch, and pass its real checks on your computer. Verity runs locally and shows what it checked.
|
79 % |
|
Ship fixes, not guesses · Code Zero
Code Zero is the open-source autonomous engineer that finds, fixes, and verifies problems in pull requests. Observe mode is the default, so nothing changes u...
|
79 % |
|
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...
|
79 % |
|
Twnhall
Connecting developers with real-world testers.
|
78 % |
|
theiterate — CI for prompts. Know which version won
CI for prompts. Run every prompt version against real test cases, see what quietly regressed before what improved, promote the winner, and serve it over an A...
|
78 % |
|
From requirement to a running test | Qymar
QA automation that writes, runs and fixes your tests on its own. You point at the requirement, it writes the cases, runs them in the browser and rewrites the...
|
78 % |
|
DebugAI: VS Code AI Debugger Built Around Your Codebase
Most AI tools only know what you paste. DebugAI pre-indexes your project and traces errors through your actual imports, call chains and file structure. Root...
|
78 % |
|
PromptWheel — add a referee to your coding loop
Add a referee to your coding loop — a deterministic, source-only re-run that checks every change earned its win. A green test should mean your agent fixed th...
|
78 % |
|
Rebar · Autonomous repair for production software
Rebar watches every system you run, finds what broke, and ships a verified fix. You decide how much it does on its own.
|
78 % |
Detected social media networks