xvirobotics/metabot — 构建受监督的、自我进化的 Agent 组织的基础设施 | Infrastructure for supervised, self-improving agent organization.

Description and use

**Brief Summary**
xvirobotics/metabot provides an open‑source infrastructure that lets developers stitch together supervised, self‑improving AI agents into reusable, orchestrated workflows. It offers shared memory, an “Agent Factory,” scheduled tasks, and a communication bus that run on mobile Feishu/Telegram clients with dual Claude/Kimi engines, turning ad‑hoc prompts into repeatable pipelines.

**Value**

• **Workflow Automation** – Converts isolated prompts and tool calls into deterministic, version‑controlled agent pipelines, reducing manual glue code.
• **Scalable Coordination** – The built‑in bus and scheduling engine enable multiple agents to collaborate, share state, and trigger each other, which is ideal for complex AI‑driven processes (e.g., data enrichment → analysis → reporting).
• **Tool‑Use Extensibility** – Plug‑in support for external tools and APIs lets teams augment agents with domain‑specific capabilities without rewriting core logic.
• **Cross‑Platform Access** – Mobile Feishu/Telegram clients give on‑the‑go access to the same agent orchestration layer used in server environments, facilitating rapid experimentation and monitoring.

**Practical Adoption Path**

1. **Prototype** – Clone the repo, run the provided Docker/CLI starter, and connect a Feishu or Telegram bot token to test Claude/Kimi code execution.
2. **Define Agents** – Use the Agent Factory SDK (TypeScript) to wrap existing prompts or scripts as reusable agents, specifying input/output schemas and memory keys.
3. **Compose Pipelines** – Wire agents together via the communication bus or scheduled tasks, persisting shared memory in the built‑in store or an external DB (e.g., PostgreSQL).
4. **Integrate** – Expose the metabot API/CLI to existing services (CI/CD, ticketing, data pipelines) and replace ad‑hoc script calls with orchestrated agent calls.
5. **Scale & Monitor** – Deploy the service to a container orchestration platform (K8s, Docker Swarm), enable logging and health checks, and gradually migrate production workloads.

**Production Readiness**

• **Activity & Community** – 745 stars, 113 forks, recent commits (as of 2026‑05‑13), and a healthy issue/PR turnover indicate active maintenance.
• **Technology Stack** – Written in TypeScript, with clear API/SDK/CLI surfaces and extensive topic tagging, making integration straightforward for modern JavaScript/Node ecosystems.
• **Reliability Features** – Built‑in scheduling, shared memory persistence, and a decoupled bus provide fault isolation and observability needed for production.
• **Remaining Checks** – A final review of the license, security scanning (dependency vulnerabilities), and confirmation of long‑term maintainers is advisable, but overall the project is mature enough for a serious pilot or production deployment.

Problem

xvirobotics/metabot helps turn isolated prompts and tools into repeatable agent workflows.

Outcome

High for an OSS candidate: recent activity, adoption, and ecosystem signals are strong enough for a serious pilot.

Workflow

• coordinate multi-agent workflows
• add tool-use pipelines
• standardize agent memory

Evidence

构建受监督的、自我进化的 Agent 组织的基础设施 | Infrastructure for supervised, self-improving agent organization. 飞书/Telegram 手机端运行 Claude Code 或 Kimi Code（双引擎，两家原生订阅直接用），共享记忆、Agent 工厂、定时任务、通信总线。

Source