Loading...
Antifailure creates a disposable copy of your production stack for each pull request so teams can catch migration issues, side effects, and other deploy-time failures before merge. It runs locally without an account for the core engine, with an optional hosted control plane for team coordination.
PR Lens helps developers review pull requests by turning code changes into animated architecture and data flow diagrams inside the PR. It is aimed at AI-generated and other complex changes where understanding the system shape matters more than reading a long diff first.
Heretic is a bot and device detection product that returns a verdict with documented findings, plus an optional phone challenge for step-up verification. It is designed for browser checks, backend decisions, and form-based verification flows.
Context Goblin is an AI code reviewer for GitHub pull requests that adds call-graph and cross-repository context before writing a review. It helps teams catch issues that depend on how services, files, and external knowledge sources are connected.
A2A Net is an AI agent builder for B2B SaaS teams that connects to existing APIs or an MCP server, tests agents in real conversations, and publishes them to channels like websites, Slack, Teams, Copilot, and Gemini Enterprise.
Offline JS Playground is a Chrome extension for writing, running, and testing JavaScript snippets directly in Chrome. It is designed for offline use and helps with quick experiments, debugging, and managing saved snippets.
Gemini 3.8 Flash and Gemini 3.8 Flash Cyber are Google Gemini models for agentic coding, multi-step reasoning, and cybersecurity defense. 3.8 Flash is the general workhorse model, while 3.8 Flash Cyber is available to trusted defenders through the Fairwind Program.
fedt.ai checks how ready a public website is for AI agents by analyzing visible site signals such as metadata, crawl files, structure, and machine-readable context. It offers a free preview scan and a paid Deep Scan and Fix Pack with prioritized fixes and implementation prompts.
EAS Observe is a production performance monitoring tool for Expo and React Native apps. It shows startup metrics, session timelines, release markers, and errors inside the Expo dashboard.
Revalvo is a browser-based, local-first LLM eval workbench for running prompts across multiple models, scoring results, versioning prompts, and batch-testing datasets. It is designed for users who want to compare outputs and keep prompt work in the browser without creating an account.
VibeView streams iOS and Android simulators to a browser and adds AI-assisted testing, recorded flows, collaboration links, embeddable sessions, and cloud builds for app teams.
HFlow is an open source SDK for building multimodal data-quality, processing, enrichment, and curation pipelines for robotics and physical AI. It helps robotics teams turn recorded episodes into quality-checked, queryable datasets with provenance and catalog-backed curation.
Traccia is an agent observability and governance platform that adds OpenTelemetry-native tracing, policy enforcement, prompt evaluation, and compliance evidence for AI workflows. It supports frameworks including LangChain, CrewAI, OpenAI Agents SDK, AutoGen, and LlamaIndex.
Lenz is a fact-checking API and workflow tool for verifying AI-generated or manually entered claims before they are published or used in automated decisions. It returns cited, auditable verdicts and can be connected through API, SDKs, CLI, MCP, n8n, and Zapier.
ReWeaver AI DriftDetector scans a GitHub repository for code drift across nine production-readiness dimensions. It shows where issues appear, how they change over commits, and includes a technical-debt estimate.
LoupeKit is a browser panel that inspects live web pages for stack details, layout, SEO, accessibility, and AI-generated code smells. It works as an over-the-page extension with a free tier and Pro options for exports, reports, advisories, and server-side readings.
Inquio is a bot QA and conversation intelligence platform for analyzing chatbot and conversational AI conversations. It helps teams review correctness, surface issues, and generate report cards without manual tagging or complex setup.
Alchemize is an AI code review platform that helps teams review changes in stacked pull requests with dependency-aware context and agent-based testing. It syncs review activity with GitHub and keeps GitHub as the source of truth.
Buddy Visual Tests compares rendered UI snapshots against approved baselines to catch visual regressions before they merge. It is built for pipeline, GitHub Actions, and local workflows, and supports both code-based and scriptless capture paths.
Agnost AI is product analytics for conversational agents. It helps teams find silent failures, user frustration, feature requests, and policy violations across production conversations.