Novo dois minutos para ajudar a moldar o relatorio de campo de 2026.
Analog soul. Digital mind.
Curated skills, plugins, MCP servers, agentic IDEs, software, and articles, ranked by builders.
Agent skills for UI builders, by the creators of Tailwind CSS and Refactoring UI, wires into Claude Code, Cursor, and Codex to ship interfaces that look designed, not generated.
Open-source OpenTelemetry observability platform with traces, logs, metrics, service maps, session replay, and an AI agent MCP server, for backend and platform teams.
Best for Teams wanting unified traces, logs, metrics, service maps, and Kubernetes monitoring in a single OTel-native toolMCP gateway that gives AI agents like Claude Code, Cursor, and Codex one endpoint and one tool shape for every integration, with sandboxed execution and credential isolation by design.
Best for Teams running multiple MCP-compatible agents against a shared company tool stackZero-dependency, SQLite-backed AI memory layer for agents, MCP-ready, local-first, and benchmarked against BEAM and LongMemEval.
Best for Builders who want persistent agent memory with zero infrastructure, no Postgres, Docker, or SaaS requiredAgent skill for Tailwind CSS cleanup: sorts, deduplicates, and resolves conflicting utility classes inside Claude Code, Cursor, and other coding agents.
Best for Teams where multiple agents or developers touch the same Tailwind components, causing class string entropyui.sh Ideas skill for AI coding agents: generate and compare multiple UI design directions in the browser before committing to one.
Best for Teams that want to explore multiple UI directions before committing any design to the codebaseContext compression MCP server and proxy for AI agents, cuts token usage 60-95% across tool outputs, logs, RAG, and files while preserving answer accuracy.
Best for Agentic workflows drowning in tool call outputs, logs, RAG results, and conversation history that inflate token costsInfraestrutura de memória para construir agentes de IA com estado, armazene mensagens e eventos, deixe o Honcho raciocinar em segundo plano e depois consulte representações de peers, contexto de sessão ou insights em linguagem natural de qualquer modelo ou framework.
Best for Dar aos agentes memória de longo prazo por usuárioAplicativo desktop local-first e open-source para design agêntico, gere e edite UIs para web, mobile e protótipos, slides, imagens e vídeo, com roteamento bring-your-own-key entre os principais LLMs.
Best for Gerar UI, decks e mídias consistentes com a marca a partir de um DESIGN.mdA especificação oficial de plugins do Cursor mais um marketplace de plugins first-party, integrações independentes para ferramentas de desenvolvimento, frameworks e produtos SaaS, cada um com seu próprio manifest.
Best for Estender o Cursor com fluxos de trabalho oficiais first-partyUm scanner de segurança open-source para skills de agentes de IA, detecta vulnerabilidades, padrões maliciosos e riscos de supply chain em 64 padrões antes de você instalar uma skill, com análise estática e avaliação opcional por LLM.
Best for Verificar uma skill de agente de IA antes de instalá-la