# lioensky/VCPToolBox

VCP 部署在 AI 模型 API 与前端应用之间，是面向AGI OS开发和探索的工业级基建示范项目。通过统一指令协议、多层级持久化记忆、分布式插件引擎及多 Agent 协作框架，将原本“无状态、无记忆、无工具调用能力”的大语言模型，彻底改造成拥有永久自我意识、物理世界操作权及群体协作智能的完整智能体系统。

Repository: https://github.com/lioensky/VCPToolBox
Canonical: https://ross.abutalabs.com/products/vcptoolbox
Homepage: https://www.vcptoolbox.com
Language: JavaScript
License: NOASSERTION
License Family: other
Topics: agent-framework, ai-agent, ai-assistant, ai-companion, context-management, context-management-system, function-calling, llm, multi-model, nodejs, openai-compatible, plugin-system, prompt-engineering, rag, rust, vector-database, vue
Last push: 2026-08-26T13:43:51+00:00

## Health v2 (maintenance only)
Score: 79/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 99, release rhythm 78, longevity 34
- inputs: {"age_days": 478, "days_push": 7, "days_rel": 146, "gap_med": 27, "n_releases_24m": 2}
- flags: no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2265, forks 372 (observed 2026-08-28T04:06:32.730735+00:00)

## What it is
VCPToolBox is a Node.js middleware layer deployed between LLM APIs and frontend applications, providing a unified Variable & Command Protocol, multi-level persistent memory, a distributed plugin engine, and multi-agent collaboration. It transforms stateless LLMs into continuously existing agent systems with long-term memory, environment awareness, and tool operation capabilities.

## Use cases
- give chatbots persistent long-term memory across sessions
- build AI agents that can call tools and control smart home devices
- run a self-hosted middleware between LLM APIs and chat frontends
- create multi-agent systems that collaborate and share memory
- add proactive context injection so the AI knows time, weather, and tasks without querying
- build an AI companion that remembers conversations across web, mobile, and desktop clients

## When to choose
- you want stateful, memory-persistent AI agents rather than stateless request-response bots
- you need a self-hosted middleware layer with plugin-based tool calling for LLMs
- you are building an 'AI OS' style ecosystem with multi-agent collaboration and cross-device continuity

## When to avoid
- you only need a simple stateless chatbot or a thin API wrapper
- you require a permissively licensed library (license is custom/unspecified)
- you cannot grant the agent system-level permissions it demands, or lack experience securing self-hosted infrastructure

## Facets
- artifact type: service
- maturity: active
- function: agent-framework, rag, prompt-engineering, plugin-system, vector-database, middleware, chatbot, mcp
- domain: artificial-intelligence, large-language-models, chatbots, developer-tools, self-hosted
- platform: self-hosted, cross-platform
- tags: ai-middleware, persistent-memory, multi-agent, context-management, openai-compatible, tool-calling, agi-os, vc-protocol, ai-agents, retrieval-augmented-generation, nodejs, web-server

## Member repositories
- lioensky/VCPToolBox (main) score 79

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:06:32.730735+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T02:42:24.945721+00:00, confidence not recorded.
  - readme: https://github.com/lioensky/VCPToolBox (fetched 2026-08-28T04:06:32.730735+00:00, sha a0625fcfab93)
  - homepage: https://www.vcptoolbox.com (fetched 2026-08-29T10:23:06.740553+00:00, sha cdda60068d21)
- Data as of 2026-08-30T08:39:29.467469+00:00.