Skip to main content

A career emulator for AI Agents.

Project description

Career Emulator - CCF BDCI 2026

PyPI - Version PyPI - License

Documentation

  • 所属赛题:2026 CCF 大数据与计算智能大赛 的《职场生存与晋升挑战》赛题,说明见比赛官网,赛事入口见2026 CCF 大数据与计算智能大赛
  • 参赛方式:使用 JiuwenSwarm 构建 Agent,并开发一个或多个 Skill
  • 交付形式:将一个或多个 Skill 文件夹打包成单个 zip
  • 交互方式:通过 career-emulator MCP 与环境交互

如果你准备做多 Agent 协同参谋,也可以看看 Swarm Skill 标准

你会从 L1 新人入职开始,在 48 个月里处理剧情事件、分配季度体力、选择季度主行动,再按半年节奏迎接绩效和晋升。目标也很直接:别太早出局,顺手把这段职业生涯经营得稍微体面一点。

项目目前提供两种入口:

  • career-emulator:本地 CLI,适合直接试玩和调规则。
  • career-emulator-mcp:MCP 服务,适合接给 Agent 自动玩。

更多公开规则、手册和玩法说明见文档:career-emulator.readthedocs.io

这题大概在玩什么

每个月,系统会生成剧情事件,你从当前选项里挑一个往下走。每到季度末,还要额外处理两件事:

  • 分配 3 点 Energy
  • 选择 1 个季度主行动

半年后会做一次绩效评估,职级、财富、健康、尊严、技能、人脉和产出会一起算总账。很多规则是公开的,很多坑只会通过反馈和日志给你一点暗示。组织很忙,通常不会为你逐条标红。

如果你只是想先记住一句话:

在 48 个月里别把自己玩出局,同时尽量把结局打成一段还能写进简历的经历。

快速开始

先安装依赖:

uv sync

同步数据并开一局:

make play

继续上一局:

uv run career-emulator play --session-id <session-id>

CLI 里常用的几个输入:

  • 输入数字:执行当前选项
  • 输入 handbook:查看新员工手册
  • 输入 logs:查看当前会话日志
  • 输入 quit:退出

给 Agent 用

当前 MCP 能力包括:

  • new_game
  • observe(session_id)
  • take_action(session_id, choice, notes)
  • check_latest_logs(session_id, count=10)
  • show_employee_handbook()

另外还提供日志资源:

  • logs://{session_id}

JiuwenSwarm

参考 JiuwenSwarm 配置赛题模拟器 MCP

支持 MCPB 的 Agent(比如Claude)

如果你的 Agent 支持 MCP Bundle,也可以生成本地安装包:

make mcpb

然后双击打开直接安装。

其他 Agent

如果你想让其他 Agent 通过 MCP 来玩,可以直接使用 stdio 格式的 MCP 服务:

uv sync --extra mcp
uv run career-emulator-mcp

开发

仓库里常用的本地检查命令:

make format
make lint
make test
make docstring

文档构建:

make docs

文档

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

career_emulator-0.1.3.tar.gz (59.9 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

career_emulator-0.1.3-py3-none-any.whl (50.8 kB view details)

Uploaded Python 3

File details

Details for the file career_emulator-0.1.3.tar.gz.

File metadata

  • Download URL: career_emulator-0.1.3.tar.gz
  • Upload date:
  • Size: 59.9 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.13.12

File hashes

Hashes for career_emulator-0.1.3.tar.gz
Algorithm Hash digest
SHA256 68ae786f703ab36de917d9ba6c1f32774eef3702adbc8a0806b20007b29cf68e
MD5 5c677b912c33b06b6cf8e38a84248dd5
BLAKE2b-256 d76c62b3b34998ff6080e74250321299a88d3eb701a40e669ebd796a5611bc32

See more details on using hashes here.

Provenance

The following attestation bundles were made for career_emulator-0.1.3.tar.gz:

Publisher: python-publish.yml on Trenza1ore/TomatoEmulator

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

File details

Details for the file career_emulator-0.1.3-py3-none-any.whl.

File metadata

File hashes

Hashes for career_emulator-0.1.3-py3-none-any.whl
Algorithm Hash digest
SHA256 b42a728fc09dd0a5c570f97955a8ef427b1f0ba5e0d9acf2402d349911d01c26
MD5 22f0047e3e8f6aecbe335e74ea6e9a44
BLAKE2b-256 39ce2737b5747db3a4200cac0c885bac24b13ca78ee41680133cfb32c9819341

See more details on using hashes here.

Provenance

The following attestation bundles were made for career_emulator-0.1.3-py3-none-any.whl:

Publisher: python-publish.yml on Trenza1ore/TomatoEmulator

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page