|
TryCase | Automated end-to-end testing for pull requests
Your AI QA agent tests each pull request end to end and reports bugs, verdicts, and supporting evidence on GitHub.
|
82 % |
|
Ferretta
A local-first review harness for code, intent, and the tradeoffs between them.
|
82 % |
|
Aether: Not a black box. A devbox.
Run Claude Code, Codex, and OpenCode in isolated cloud devboxes you can watch, steer, SSH into, and verify. Your provider account covers the model; Aether ch...
|
81 % |
|
Verifunnel — Verification & Review
A shared workspace for publishers and advertisers to verify pages and review submissions.
|
81 % |
|
Runweft — Turn agent failures into tests
Runweft is developing regression testing for AI-agent workflows. Turn failed runs into test fixtures, compare changes, and understand what broke before you s...
|
81 % |
|
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...
|
80 % |
|
Verdict Reviews — Fast, affordable PR reviews for GitHub
Get fast pull request feedback, clear risk scores, and verified explanations in GitHub. Affordable monthly plans, with your team in control of every merge.
|
80 % |
|
RegmateQA — Build your device. Keep the evidence connected
Meet the connected workspace we're building for small medical-device teams. Quality documents, development evidence, traceability, and AI assistance you review.
|
80 % |
|
Pravado — Prove what moves your AI visibility
Pravado measures your AI visibility honestly, proves which PR and content moved it, and runs the next move across PR, Content and AI Visibility with your app...
|
80 % |
|
Reter · Change assurance for AI-generated code
Your AI writes code faster than you can vet it. Reter gives every change an evidence-backed impact review — from a live model of your codebase, not an LLM's...
|
80 % |
|
Verifiable decision records for AI agents | AGA
Signed policy decisions for agent tool requests. Inspect an AGA sample, verify its signed record, and understand the trust and deployment boundaries.
|
80 % |
|
Arcplane - Workflow layer for AI software teams
A workflow layer for teams building software with AI agents. Shape tasks, run agents on real code, review evidence, and ship with human judgment.
|
80 % |
|
DACIP: the PR gate that proves it
AI reviewers have opinions. DACIP has proof. It reads both sides of your pull request and catches the frontend calls your backend change breaks, with a repro...
|
80 % |
|
TraceAxiom | Run AI-Written Pull Requests Before You Merge
TraceAxiom Verify, in development, runs an AI-written pull request's tests on base and head, checks its claims, and posts one verdict with its reasons.
|
80 % |
|
Crawlmend — AI SEO Agent That Opens GitHub Pull Requests
Crawlmend is an AI SEO agent that crawls your site, reads Search Console and PageSpeed evidence, and opens a reviewable GitHub pull request for each fix — ne...
|
80 % |
|
Review the contract before release · DiffHaven
A browser-local OpenAPI JSON change-review workspace. Inspect contract differences, evidence and suggested tests without uploading your specifications.
|
80 % |
|
SDDFW — Build with intent. Ship with evidence.
SDDFW turns reviewed specifications into Playwright tests, AI-assisted changes, and acceptance evidence. Try the local CLI and runnable frontend + backend ex...
|
79 % |
|
Excellent — Verification for agentic tasks
Excellent runs next to your AI agents, checks their work with independent evidence, and tests changes that make them more reliable on your own work.
|
79 % |
|
ProofCI — Evidence for every pull request
ProofCI maps requirements to implementation, tests, and CI evidence before code is merged.
|
79 % |
|
AI Coding Interviews for Practice & Hiring | nrml
Technical interviews built around real repositories and AI-assisted work. Practice your engineering skills or evaluate how candidates solve problems.
|
79 % |
Detected social media networks