Failproof AI is an open-source tool for AI engineers, agent developers, and ML teams to build versioned eval datasets from production agent traces. It picks failures, edge cases, and a random slice from production traces, scrubs PII, labels them, and freezes versioned eval datasets you can replay.
Freemium · $0.60+
Natively AI is a local-first AI meeting and call assistant that captures microphone audio and screen content on-device to deliver live transcription, real-time support, structured notes, decisions, and follow-ups. It works without a bot joining your call, making it suited to privacy-conscious remote teams, call-heavy professionals, interview candidates, and meeting participants.
Agent Kernel is a framework-neutral, multi-cloud AI agent runtime for building, deploying, and running production-grade AI agents. It supports frameworks like OpenAI Agents SDK, LangGraph, CrewAI, and Google ADK, with built-in testing, observability, guardrails, knowledge bases, sandboxed code execution, and messaging integrations.
Voxt is a desktop voice input and transcription tool for macOS that turns speech into text and can use a language model to remove filler, fix punctuation, improve structure, and apply custom instructions, with local model processing, meeting transcription and analysis, translation, rewriting, and per-app enhancement rules.
TermMate is a free, open-source editor extension that integrates AI coding agents like Claude Code, Codex, OpenCode, and Pi Agent directly into Sublime Text, allowing developers to explore codebases, execute multi-file changes, and run autonomous tasks without switching windows.
Anthropic Cybersecurity Skills is an open-source project providing 754+ structured, MITRE ATT&CK-mapped cybersecurity skills for AI agents and coding platforms. It works with Claude Code, GitHub Copilot, Cursor, Gemini CLI, and 20+ AI coding platforms under the Apache 2.0 license.
