# wangziqi06/724-office

7/24 Office — Self-evolving AI Agent system. 36 tools, 10,000 lines pure Python, modular architecture, MCP plugins, three-layer memory, nudge system, AI mirror, 24/7 production.

Repository: https://github.com/wangziqi06/724-office
Canonical: https://ross.abutalabs.com/products/724-office
Language: JavaScript
License: MIT
License Family: permissive
Last push: 2026-07-31T07:53:16+00:00

## Health v2 (maintenance only)
Score: 57/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 95, release rhythm 35, longevity 12
- inputs: {"age_days": 169, "days_push": 33, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, young
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1020, forks 169 (observed 2026-08-28T04:03:15.482211+00:00)

## What it is
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
- artifact type: application
- maturity: active
- function: agent-framework, mcp, chatbot, scheduling, rag, plugin-system, workflow-automation
- domain: large-language-models, developer-tools, chatbots
- platform: python, self-hosted, cli
- tags: 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
- wangziqi06/724-office (main) score 57

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:15.482211+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 2026-08-30T07:09:20.097458+00:00, confidence not recorded.
  - readme: https://github.com/wangziqi06/724-office (fetched 2026-08-28T04:03:15.482211+00:00, sha 2e8fa4430c9b)
- Data as of 2026-08-30T08:39:29.467469+00:00.