wangziqi06/724-office

Health v2 · maintenance only

Flags: no_releases young

Adoption not part of the score

1020 stars · 169 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

A self-evolving, production-running AI agent system written in ~10,000 lines of pure Python with no agent frameworks, featuring 36 tools, MCP plugin support, three-layer memory with vector retrieval, cron scheduling, and 24/7 multi-user operation. Its successor xiaowang-v2 rewrites the system as a single Node process with durable cross-day execution and a hand-written agentic loop.

Use cases

• run a personal AI agent 24/7
• build an agent without LangChain or other frameworks
• connect MCP servers to an LLM agent
• schedule recurring AI tasks with cron
• give an LLM long-term memory with vector retrieval
• let an agent create its own tools at runtime
• deploy a multi-tenant chatbot over WeCom

When to choose

• you want a dependency-light, framework-free agent you can read and modify end to end
• you need persistent scheduling, memory, and self-repair in one always-on agent
• you want MCP plugin support and runtime tool creation
• you prefer a battle-tested production agent with self-test assertions

When to avoid

• you need a polished GUI or managed product rather than a self-hosted system
• you want a mainstream framework with large community and ecosystem
• you need non-Python/non-Node environments or heavy multi-agent orchestration
• documentation is largely in Chinese and you require English docs

Facets

application · maturity active

agent-framework mcp chatbot scheduling rag plugin-system workflow-automation large-language-models developer-tools chatbots python self-hosted cli self-evolving-agent tool-use-loop three-layer-memory mcp-plugins multi-tenant wecom cron-scheduling self-repair zero-framework ai-agents automation nodejs

Member repositories

For agents

markdown · JSON · MCP: product_card(name="wangziqi06/724-office")