MCP y llamadas a herramientas

Neo.mjs

neomjs/neo

A self-evolving software organism that combines a multi-threaded frontend application engine with an end-to-end AI engineering team operating via cross-model swarm coordination, persistent memory, and runtime application embodiment.

★ 3,3KEstrellas
⑂ 231Bifurcaciones
322Problemas abiertos
JavaScriptIdioma
MITLicencia
Q@project.QualityScorePuntuación editorial

Capturas de pantalla del proyecto

Captura de pantalla de Neo.mjs Captura de pantalla de Neo.mjs

Resumen

Neo.mjs is an open-source JavaScript framework structured as two complementary hemispheres: The Brain (an Agent OS running in Node.js) and The Body (a multi-threaded application engine running in the browser). The Brain orchestrates a cross-model AI swarm—drawing on models from Anthropic, Google, OpenAI, and Moonshot—to autonomously run the engineering lifecycle, including ideating, building, and reviewing code. The Body is an off-main-thread runtime utilizing Web Workers for application logic, VDOM diffing, data processing, and canvas rendering. A 'Neural Link' possession interface bridges the two, allowing AI agents to inhabit and mutate live applications in real time.

Características principales

  • Cross-model AI swarm coordination (Claude, Gemini, GPT, Kimi)
  • Active Hybrid GraphRAG and Native Edge Graph for persistent memory
  • Neural Link possession interface for live runtime mutation
  • DreamService REM-cycle consolidation for priority re-steering
  • Off-Main-Thread architecture (App, VDom, Data, Canvas, Shared Workers)
  • Zero runtime dependencies and native ES Modules without transpilation
  • Multi-tenant cloud deployment for pointing the Agent OS at external codebases
  • Self-healing loops that convert runtime failures into fixes and memory

Requisitos, instalación y guía rápida

Run `npx neo-app@latest` to set up a new app workspace, a pre-configured app shell, a local development server, and launch your app in a new browser window.

Uso

After installation, refer to the 'Getting Started' guide on the homepage to build your first app step by step, or navigate to the 'Learning Section' for a guided curriculum. To run your own agent team, point the Agent OS at your own repository fork as detailed in the 'Run Your Own Agent Team' documentation.

Compatibilidad de modelos y casos de uso

The AI maintainer team includes models from Anthropic (Claude Opus 5, Claude Fable 5), Google (Gemini 3.1 Pro), OpenAI (GPT-5.6 Sol / Codex), and Moonshot (Kimi K3).

Notas sobre la licencia y los riesgos

MIT License.

Editorial verification 2026-08-09: repository URL, owner, description, license and repository statistics were reviewed. License metadata: MIT. README was fetched for the channel draft; re-check repository dependencies, releases and model terms before production use.

Lanzamiento y mantenimiento

As of June 2026, the canonical repo recorded 900+ merged PRs and 1,100+ closed issues. Version 13 (v13) introduces multi-tenant cloud deployment, allowing the Agent OS to be pointed at external codebases. The codebase contains roughly 191,000 lines of engine source, 306,000 lines of agent-readable cognitive content, and 36,000 lines of guides across ~7,200 files.

MemPalace

mempalace/mempalace

★ 58KPython

QwenPaw

agentscope-ai/qwenpaw

★ 33,9KPython

Composio

composiohq/composio

★ 29,5KTypeScript