AI tools for “debug”

Before you launch, know where your app can break. CleanSlop reads your code and tells you what could break when real people show up — and what to fix first. Run it from your agent: “Scan with cleanslop.com”.

Describe your buyers in plain English. Causo uses unlimited data sources to find companies and contact decision-makers. 🦝CausoSalesFundraisingPricingUse cases Industrial & supply chainIndustrial &…

Ten focused AI products for customer experience, analytics, marketing, finance, people operations, and engineering in one governed workspace.

Open-source stack that gives AI coding agents persistent memory, a right-sized workflow, curated skills and evidence-based review. One command per machine.

Open-source continual learning infrastructure for Self-Improving Agents. Connect agent inference, feedback, model training, and versioned deployment.

2,900 marketplace-visible agent skills across 434 catalog plugins for AI coding agents. Free and open source. Tons of Skills Explore Skills Docs Learn Cowork Community Work Diary Get Started Built by Intent Solutions…

Open-source Kubernetes UI with a built-in MCP server for AI agents. Diagnose Issues, understand Applications, and trace topology, events, GitOps, and traffic.

VibeUE is an Unreal Engine 5.8 plugin that expands UE5.8's native MCP server, ToolsetRegistry, and AgentSkill system. 33 service toolsets, ~86 agent skills, performance profiling, real-world terrain, Fab asset import,…

Connect your software factory or coding agent to a version-aware index of open-source code, documentation, and package data. Discover, use, debug, and maintain dependencies through one interface.

Build applications that can see, hear, and speak with LiveKit Cloud, an end-to-end developer platform for voice, video, and physical AI.

Research on aligning AI with human values and intent, and reports documenting model failures. Skip to content OpenAIAlignment Research Blog ← HomeResearch and ReleasesMisalignment Reports and NoticesSystem Cards ↗…

Kubernetes-native, high-performance distributed LLM inference Skip to main content🎉 llm-d 1.0 is here! State-of-the-art inference, ready for production operations: multi-tenant quality of service, zero-downtime…

The ideas, papers and exercises that led from n-gram counts to attention. Foundations of Large Language Models Learning by Doing by David Louapre 0 NLP before LLMs 1 Tokenizers (coming soon) 2 Transformers (coming soon)…

Find the best agent skills for Claude Code, Cursor, Codex & Copilot — hand-picked SKILL.md files, exclusive originals, prompt packs, and AI image & video prompts.

ilha shows the usage limits of every Claude Code, Codex and Grok Build account in your Mac's notch, and switches accounts before you hit one.

Get notified when Claude Code, OpenCode or omp needs you. Each session becomes a pet in Chrome: approve permission prompts and reply from any tab. Early bird: $6 one-time (regularly $25).

Enterprise-grade interaction infrastructure that enables real-time, multi-peer collaboration between agents and humans through a shared interaction layer with built-in governance.

Your customers file bugs from their AI assistant, straight into a live copy of your app. Triage replays every report on a clean machine and only sends you the ones that break again, as a link you can watch.

Infisical is the all-in-one identity security platform for developers, machines, and AI agents. Manage identities, secrets, certs, and access.

Cora Code reviews your code in the terminal: 12 deterministic scanners, BYOK, zero cloud, no subscription. Free & open-source from CodeCora.