Datos e inteligencia artificial

The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.

Agente de IA que aprende y crece contigo.

Plataforma para crear y ejecutar agentes de IA autónomos.

Ejecuta modelos de lenguaje en tu propio ordenador con un solo comando.

Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.

El marco de referencia para trabajar con modelos de texto, visión y audio.

Stable Diffusion web UI

Construye flujos con agentes y canalizaciones RAG en un espacio colaborativo.

Interfaz de chat para modelos de IA locales o remotos, cómoda y autoalojable.

The agent engineering platform.

Turn any codebase, with its docs, SQL schemas, configs, and PDFs, into a queryable knowledge graph. A /graphify skill for Claude Code, Cursor, Codex, and Gemini CLI: local determin

Genera vídeos cortos en alta definición a partir de un tema, con IA.

Open-source Python library for AI browser agents, plus Browser Use Cloud: stealth browsers and a hosted agent API.

Marco multiagente con modelos de lenguaje aplicado a operativa financiera.

Reduce un 65 % el consumo de tokens de los agentes de programación simplificando el lenguaje.

Motor de inferencia para modelos de lenguaje con alto rendimiento y poco consumo de memoria.

Turn any idea, plan, or codebase into a beautiful interactive diagram. An agent skill for Claude Code, Codex, and more.

Open-source web crawler and scraper for LLMs and AI agents: any website into clean, LLM-ready Markdown. Run it yourself, or use Crawl4AI Cloud with one key. Join our Discord https:

📚 《从零开始构建智能体》——从零开始的智能体原理与实践教程

CLI proxy that reduces LLM token consumption by 60-90% on common dev commands. Single Rust binary, zero dependencies

An open-source long-horizon SuperAgent harness that researches, codes, and creates. With the help of sandboxes, memories, tools, skill, subagents and message gateway, it handles di

Bash is all you need - A nano claude code–like 「agent harness」, built from 0 to 1

Interfaz local para ejecutar y entrenar modelos de lenguaje y de imagen.

Compress tool outputs, logs, files, and RAG chunks before they reach the LLM. 20% fewer tokens for coding agents, 60-95% fewer tokens for JSON, same answers. Library, proxy, MCP se