|
App Store and Google Play Compliance Checks | AppCompliance
Check IPA, APK and AAB builds for supported App Store and Google Play compliance risks before submission. Static analysis, store context, evidence and remedi...
|
83 % |
|
Inspect - Turn ideas into mergeable pull requests
Inspect turns ideas into mergeable pull requests. It works with the same context a real engineer has—codebase, dependencies, database, CI, logs, errors, anal...
|
82 % |
|
ProofCI — Evidence for every pull request
ProofCI maps requirements to implementation, tests, and CI evidence before code is merged.
|
82 % |
|
LogFixer - Detects production errors, ships the fix
LogFixer reads your server and app logs, finds silent failures, and opens a pull request with the fix. You approve - it ships. No dashboard to babysit.
|
82 % |
|
alidoes.ai — run it, then check it
AI can sound completely sure and still be confidently wrong. I run my real life on AI agents and show the independent checks that catch what looks right but...
|
82 % |
|
n8n Workflow Repair & Troubleshooting | RelayMend
Fix a clearly scoped n8n workflow problem. Explore the €149 repair pilot, synthetic test evidence, troubleshooting guides and FAQs.
|
82 % |
|
ReproScout — Android complaints. Clearer answers.
Focused Android complaint investigations. Get repeatable steps, exact environment details, and evidence your engineering team can review.
|
81 % |
|
Automatic Optimization Layer for AI Agents | MEGA Code
Auto-optimizes your whole agent workflow, prompts, tools, code, and orchestration, and proves every fix by execution before it ships. Model-agnostic.
|
81 % |
|
PreReviews — Find App Store review risks before you submit
A free local browser audit for known App Store review risks, with full findings, fix guidance, and Apple references.
|
81 % |
|
Assevra — Find agent failures before your users do
Open-source agent evaluation with actionable findings, explicit release gates, and portable evidence. Connect captured runs, fix failing cases, and verify th...
|
81 % |
|
CrashSignal | Failure signals, not guesswork.
Evidence-first website incident triage, Cloudflare error guides, and private browser-based incident reports.
|
80 % |
|
Sphinque — See the engineer behind the AI-assisted code
Sphinque helps teams replace the first technical screen with evidence of how candidates build, verify, and explain software with AI.
|
80 % |
|
Drifted — End-to-end validation for every change
Validate critical workflows before and after code and config changes. Catch failures early, investigate with evidence, and verify recovery with Drifted.
|
80 % |
|
Flowgine — Workflow orchestration for your applications
Connect system actions and human decisions in one workflow. Find waiting and failed steps, inspect what happened, and retrieve status and results through the...
|
80 % |
|
Pytxo: the landing layer for coding agents
Split a job across Codex, Claude Code and Cursor Agent, or bring branches from any agent tool. Pytxo checks the combined change, shows exactly what will land...
|
80 % |
|
FixVector — Authorized Web Application Security Testing & Reports
FixVector delivers authorized DAST for permitted web targets—bounded scans, normalized findings, and executive-ready PDF plus engineering-ready JSON reports.
|
80 % |
|
EvalVitals — Diagnose why a model fails. Verify the fix worked.
EvalVitals diagnoses why an open-weight model fails, then verifies the repair against the unmodified baseline.
|
80 % |
|
Toaster — checks, issues, and acceptance in one workflow
Toaster is a quality workspace for checklists, test cases, issues, retesting, and software acceptance.
|
80 % |
|
Evals Weekly
The useful ideas in AI testing, explained in five minutes. Research, company posts, and practical steps you can try.
|
80 % |
|
PtcRunner
PtcRunner is a runtime for building self-improving agents: the agent loop is a replaceable library, not the runtime, so you can change what an agent does wit...
|
80 % |
Detected social media networks