AI Worker worker.md

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。

Agent framework 2,233 stars JavaScript NOASSERTION Worker-compatible

Source#

Tags#

agent-frameworkai-agentai-assistantai-companioncontext-managementcontext-management-system

Integration notes#

Framework-level abstraction; derive bounded worker contracts from concrete tasks and APIs in docs/examples.

worker.md example#

Starter worker.md contract mapped from this registry entry. Copy this file and adapt schemas, constraints, and statuses for your task.

---
id: vcptoolbox-repo-derived-worker
name: VCPToolBox Repo-Derived Worker
version: 1.0.0
source_registry_url: https://worker.md/registry/vcptoolbox/
source_repository: https://github.com/lioensky/VCPToolBox
repository_default_branch: main
repository_language: JavaScript
repository_license: NOASSERTION
repository_updated_at: 2026-08-08
worker_mode: agent-orchestration-worker
derivation_method: github_repository_metadata_plus_raw_readme
derivation_confidence: 0.95
derived_on: 2026-08-09
tags:
  - agent-framework
  - ai-agent
  - ai-assistant
  - ai-companion
  - context-management
  - context-management-system
---

# VCPToolBox Repo-Derived Worker

## Repo-derived summary
- Registry summary: 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 description: 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。
- Stars (snapshot): 2,233
- Primary language: JavaScript
- Worker mode classification: agent-orchestration-worker

## Extracted from
- https://github.com/lioensky/VCPToolBox
- https://github.com/lioensky/VCPToolBox/blob/main/README.md
- https://www.vcptoolbox.com
- https://www.vcptoolbox.com/?page=changelog

## Evidence notes (from repository text)
- README summary paragraph: [English](README_en.md) | [日本語](README_ja.md) | [Русский](README_ru.md)
- > ⚠️ **部署前请务必阅读**：VCP Agent 拥有分布式系统的底层级权限。请勿使用任何非官方或反向代理的 API（"镜像站""中转 API"）。在底层监控权限下，不可信的 API 可能导致交互数据、记忆库内容、密钥等敏感信息泄露。非专业用户请谨慎部署。
- 过去一年多，市面上出现了无数 Agent 框架。它们包装得各不相同，但骨子里都在做同一件事：把 AI 当成一个**被调用者**。你问一句，它醒来；它答完，它睡去。它的"记忆"是一次检索，它的"行动"是被一个 while 循环反复戳醒，它的"感知"是必须主动 query 才能拿到的几个字段。每一次对话都是一次新生，每一次结束都是一次失忆。
- 这是当下绝大多数"AI Agent"的真实处境——一个被困在单次请求里、没有昨天也没有明天的临时工。
- RiverMemo 不把语言的意义固定在一套对所有人都相同的坐标中。它以用户与 Agent 长期共同生活所沉积的全部记忆为基础，持续构造专属于这段关系的语义地形，使每一次联想都能受到私人经历、情感、因果与上下文的共同校准。换言之，它不是要求每个人服从同一张语言地图，而是让系统拥有依据私有认知修正语义坐标的能力。
- 这不只是性能意义上的重构。信息的传递、场的生成、结构的观测与记忆的排序，第一次在同一条数学链上闭合；而 Agent 长期写下的 Tag，也不再只是文档分类词，而逐渐成为因果、转折、角色交换与意义流动的信号点——一套由 Agent、记忆与算法共同沉积出来的叙事河床。于是 VCP 的记忆不再是 Agent 可以选择调用的外部工具，而是它每次醒来时所处的认知环境：**写下记忆是 Agent 的行动，想起记忆是世界本身的动力学。**

## Installation hints found in README
- `pip install -r requirements.txt`
- `npm install`

## worker.md contract (derived starter)
Purpose: Execute one orchestrated agent task as a bounded worker step.

### Input schema
```json
{
  "type": "object",
  "additionalProperties": false,
  "required": [
    "run_id",
    "task",
    "context"
  ],
  "properties": {
    "run_id": {
      "type": "string"
    },
    "task": {
      "type": "string"
    },
    "context": {
      "type": "object"
    }
  }
}
```

### Output schema
```json
{
  "type": "object",
  "additionalProperties": false,
  "required": [
    "run_id",
    "status",
    "result"
  ],
  "properties": {
    "run_id": {
      "type": "string"
    },
    "status": {
      "type": "string",
      "enum": [
        "ok",
        "retryable_error",
        "invalid_request",
        "invalid_output"
      ]
    },
    "result": {
      "type": "object"
    }
  }
}
```

### Constraints
- timeout_seconds: 30
- max_attempts: 2
- idempotency_key: run_id
- status_enum: [ok, retryable_error, invalid_request, invalid_output]
- notes: adapt to concrete APIs/classes documented in this repository before production use

## How this should be used
1. Treat this file as a repo-derived starter profile, not a claim of an official repository API contract.
2. Replace schemas with exact interfaces from code/docs you adopt.
3. Keep execution bounded and auditable using worker protocol constraints.

How to use#

  • Save this as a worker spec file (for example: vcptoolbox-my-task.worker.md).
  • Replace the input/output schemas and purpose with your real bounded task.
  • Enforce schema validation + timeout + retry policy in your runtime before production use.

Citation#

Reference URL: https://worker.md/registry/vcptoolbox/

Source URL: https://github.com/lioensky/VCPToolBox