经 AI Skill Hub 精选评估,Nullboiler 获评「推荐使用」。这款Agent工作流在功能完整性、社区活跃度和易用性方面表现出色,AI 评分 7.5 分,适合有一定技术背景的用户使用。
Nullboiler 是一套完整的 AI Agent 自动化工作流方案。通过可视化的节点编排,将复杂的多步骤任务拆解为清晰的自动化流程,实现全程无人值守的智能处理。支持与数百种外部服务和 API 无缝集成,适合构建数据处理管线、业务自动化和 AI 辅助决策系统。
Nullboiler 是一套完整的 AI Agent 自动化工作流方案。通过可视化的节点编排,将复杂的多步骤任务拆解为清晰的自动化流程,实现全程无人值守的智能处理。支持与数百种外部服务和 API 无缝集成,适合构建数据处理管线、业务自动化和 AI 辅助决策系统。
# 克隆仓库 git clone https://github.com/nullclaw/nullboiler cd nullboiler # 查看安装说明 cat README.md # 按 README 完成环境依赖安装后即可使用
# 查看帮助 nullboiler --help # 基本运行 nullboiler [options] <input> # 详细使用说明请查阅文档 # https://github.com/nullclaw/nullboiler
# nullboiler 配置说明 # 查看配置选项 nullboiler --config-example > config.yml # 常见配置项 # output_dir: ./output # log_level: info # workers: 4 # 环境变量(覆盖配置文件) export NULLBOILER_CONFIG="/path/to/config.yml"
NullBoiler is an orchestration engine for AI agents.
It is intentionally narrow: it decides what should run, when it should run, and which worker should execute it. It does not replace the task tracker and it does not replace the agent runtime.
You do not need all components together. Choose only the pieces required for your workflow.
The orchestration graph runtime supports:
task, agent, route, interrupt, send, transform, and subgraph nodessend fan-out with canonical items_key and configurable output_keyoutput_key and output_mappingstate.*, input.*, item.*, config.*, and store.<namespace>.<key>transform.store_updates for writing durable workflow memory back to NullTicketsStore-backed templates and store_updates require a NullTickets base URL. The runtime resolves it from workflow fields such as tracker_url or from run config (config.tracker_url / config.tracker_api_token), which are injected into state as __config.
~/.nullboiler/config.jsonNULLBOILER_HOME=/path/to/dir--config /path/to/config.jsonWhen NULLBOILER_HOME is set, nullboiler reads config.json from that directory and resolves relative paths like db, strategies_dir, tracker.workflows_dir, and tracker.workspace.root relative to that config file.
File-based tracker/pull-mode workflows are loaded from JSON files using the WorkflowDef shape in src/workflow_loader.zig. Before starting the server, you can check those files locally:
zig build run -- validate-workflows
zig build run -- validate-workflows workflows
The command defaults to workflows and scans direct *.json files in the directory, matching loadWorkflows; it does not recurse into nested directories. This is only for file-based tracker/pull-mode WorkflowDef files, not graph workflow definitions managed through the HTTP API.
It reports:
- errors for missing or unreadable directories, unreadable files, malformed JSON, JSON that cannot be parsed as WorkflowDef, missing or empty pipeline_id, and duplicate pipeline_id values - warnings for suspicious but currently allowed shapes, including empty id, empty claim_roles, dispatch workflows without dispatch.worker_tags, and directories with no JSON workflow files
Validation errors exit with status 1. Warnings are shown but do not fail the command, matching the existing runtime loader's permissive behavior.
Nullboiler是一个有潜力的AI工作流管理工具
AI Skill Hub 为第三方内容聚合平台,本页面信息基于公开数据整理,不对工具功能和质量作任何法律背书。
建议在沙箱或测试环境中充分验证后,再部署至生产环境,并做好必要的安全评估。
✅ MIT 协议 — 最宽松的开源协议之一,可自由商用、修改、分发,仅需保留版权声明。
AI Skill Hub 点评:Nullboiler 的核心功能完整,质量良好。对于自动化工程师和运维人员来说,这是一个值得纳入个人工具库的选择。建议先在非生产环境试用,再逐步推广。
| 原始名称 | nullboiler |
| 原始描述 | 开源AI工作流:Orchestrates multi-step AI agent workflows — defines execution graphs, manages s。⭐282 · Zig |
| Topics | aiorchestrationzig |
| GitHub | https://github.com/nullclaw/nullboiler |
| License | MIT |
| 语言 | Zig |
收录时间:2026-06-06 · 更新时间:2026-06-06 · License:MIT · AI Skill Hub 不对第三方内容的准确性作法律背书。
选择 Agent 类型,复制安装指令后粘贴到对应客户端