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。
Build with Backblaze B2
SDKs, agent skills, IDE extensions, and reference pipelines from Backblaze Labs. All open source.
Loading star history...
Where it stands
Rank, growth pace and release cadence relative to everything GStars tracks.
1 release in the last 90 days, the latest 60 days ago, with 50 contributors on GitHub.
Peaked at #43 in the weekly ranking the week of Feb 22, its best in the past year.
Use Cases & Benefits
- Implements a next-generation AI middleware layer that transforms stateless large language models into autonomous, memory-enabled, multi-agent intelligent systems with tool integration.
- Offers a highly extensible, plugin-based architecture with dynamic logic enhancement and distributed execution, enabling seamless AI capability expansion and multi-agent collaboration.
- Use for developing advanced AI agents with persistent memory and self-evolving capabilities across diverse AI models and modalities.
- Use for building distributed AI systems that leverage heterogeneous hardware and networked plugins for scalable, multi-node AI computation.
- Use for creating complex AI-driven workflows with asynchronous tool calls, real-time context injection, and fine-grained behavior control via a visual web management interface.
Should you depend on it?
License terms, project hygiene and risks, from GitHub metadata and GStars' snapshots.
License
Other
GitHub could not identify this license; read the LICENSE file before depending on it.
Community files
- README: present
Watch-outs
- License not identified by GitHub; read the LICENSE file before depending on it.
General guidance from repository metadata, not legal advice. How we score
From the README
VCP (Variable & Command Protocol) 旨在构建一个超越传统 AI 交互模式的革命性中间层。它不仅是一个高度兼容、通用、可扩展的工具箱，更是一个致力于赋能 AI 模型实现能力跃迁、记忆进化与群体智能涌现的生态系统。
我们的目标是创建一个**“不受模型种类、模态、功能限制”且“不受前端交互束缚 ”**的通用 VCP 系统，通过在 API 层面深度整合 AI 推理、外部工具执行与持久化记忆系统，形成高效协同的“AI-工具-记忆”铁三角。VCP 允许 AI 之间、AI 与工具之间、甚至 AI 与自身记忆之间进行前所未有的高效通讯与协同进化，一切基于私有和共享知识库实现，从而无限扩展 AI 的应用边界与智能潜力。
VCP 的核心是引领 AI Agent 进入一个能够自主学习、持续进化、并能与其他 Agent 高效协作的新纪元。
郑重警告：请勿使用任何非官方或反向代理的 API (例如各类“镜像站”、“中转API服务商”) 来调用此工具箱，VCP拥有几乎底层的系统监控权限，此类行为极易导致您的敏感信息（包括但不限于 AI 交互数据、记忆库内容、API密钥、浏览器历史、账号密码）泄露给不可信的第三方，造成不可挽回的损失。请务必确保您的 AI 模型 API 调用链路纯净、直接、可信。
VCP 的每一项特性都根植于其前瞻性的设计哲学，旨在解决当前 AI 应用的深层痛点，并引领下一代 AI Agent 的发展方向。
Daily snapshots
Stars gained per day, and how forks and open issues moved, from GStars' daily snapshots
Forks
394+32
Open issues
2-1
Compared with peers in API
Fastest-growing repositories GStars tracks in this cohort for the week of Nov 1, by 7-day star growth
| Repository | Stars | +7d | Health | Last release |
|---|---|---|---|---|
| vxcontrol/pentagi | 33.5K | +712 | 38 | 31 days ago |
| usebruno/bruno | 48.2K | +281 | 59 | 14 days ago |
| agentgateway/agentgateway | 6.0K | +183 | 60 | 9 days ago |
| mudler/LocalAI | 50.2K | +176 | 59 | 12 days ago |
| sveltejs/svelte | 88.6K | +77 | 65 | 9 days ago |
| lioensky/VCPToolBox | 2.4K | — | 52 | 60 days ago |
| Category median | 48.2K | +183 | 59 | — |
Discover Repositories
Search across tracked repositories by name or description