经 AI Skill Hub 精选评估,Pilot AI工作流引擎 获评「强烈推荐」。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 8.2 分,适合有一定技术背景的用户使用。
Pilot AI工作流引擎 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。
Pilot AI工作流引擎 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。
# 方式一:go install(推荐) go install github.com/qf-studio/pilot@latest # 方式二:从源码编译 git clone https://github.com/qf-studio/pilot cd pilot go build -o pilot . # 方式三:下载预编译二进制 # 访问 Releases 页面下载对应平台二进制文件 # https://github.com/qf-studio/pilot/releases
# 查看帮助 pilot --help # 基本运行 pilot [options] <input> # 详细使用说明请查阅文档 # https://github.com/qf-studio/pilot
# pilot 配置说明 # 查看配置选项 pilot --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 PILOT_CONFIG="/path/to/config.yml"
<p align="center"> <pre> ██████╗ ██╗██╗ ██████╗ ████████╗ ██╔══██╗██║██║ ██╔═══██╗╚══██╔══╝ ██████╔╝██║██║ ██║ ██║ ██║ ██╔═══╝ ██║██║ ██║ ██║ ██║ ██║ ██║███████╗╚██████╔╝ ██║ ╚═╝ ╚═╝╚══════╝ ╚═════╝ ╚═╝ </pre> </p>
<p align="center"> <strong>AI that ships your tickets while you sleep</strong> </p>
<p align="center"> <a href="https://github.com/qf-studio/pilot/releases"><img src="https://img.shields.io/github/v/release/qf-studio/pilot?style=flat-square" alt="Release"></a> <a href="LICENSE"><img src="https://img.shields.io/badge/License-BSL_1.1-blue.svg?style=flat-square" alt="License: BSL 1.1"></a> <a href="https://github.com/qf-studio/pilot/actions"><img src="https://github.com/qf-studio/pilot/workflows/CI/badge.svg?style=flat-square" alt="CI"></a> <a href="https://goreportcard.com/report/github.com/qf-studio/pilot"><img src="https://goreportcard.com/badge/github.com/qf-studio/pilot?style=flat-square" alt="Go Report Card"></a> <a href="https://discord.gg/Hsz63MTB3c"><img src="https://img.shields.io/badge/Discord-Join%20Chat-5865F2?style=flat-square&logo=discord&logoColor=white" alt="Discord"></a> </p>
<p align="center"> <a href="https://pilot.quantflow.studio">Docs</a> • <a href="#install">Install</a> • <a href="#desktop-app">Desktop</a> • <a href="#quick-start">Quick Start</a> • <a href="#how-it-works">How It Works</a> • <a href="#features">Features</a> • <a href="#cli-reference">CLI</a> • <a href="https://discord.gg/Hsz63MTB3c">Discord</a> • <a href="docs/DEPLOYMENT.md">Deploy</a> </p>
<br />
---
133 features implemented across execution, intelligence, integrations, and infrastructure.
go install github.com/qf-studio/pilot/cmd/pilot@latest
```bash
pilot init
Pilot uses Claude Code for AI execution:
| Variable | Description |
|---|---|
ANTHROPIC_API_KEY | Custom Anthropic API key (uses your own account) |
ANTHROPIC_BASE_URL | Custom API endpoint (proxies, enterprise) |
CLAUDE_CODE_USE_BEDROCK | Set to 1 for AWS Bedrock |
CLAUDE_CODE_USE_VERTEX | Set to 1 for Google Vertex AI |
Example: Using AWS Bedrock
export CLAUDE_CODE_USE_BEDROCK=1
export AWS_REGION=us-east-1
pilot start --github
Config location: ~/.pilot/config.yaml
version: "1.0"
gateway:
host: "127.0.0.1"
port: 9090
adapters:
telegram:
enabled: true
bot_token: "${TELEGRAM_BOT_TOKEN}"
chat_id: "${TELEGRAM_CHAT_ID}"
github:
enabled: true
token: "${GITHUB_TOKEN}"
repo: "owner/repo"
pilot_label: "pilot"
polling:
enabled: true
interval: 30s
orchestrator:
execution:
mode: sequential # "sequential" or "parallel"
wait_for_merge: true # Wait for PR merge before next task
poll_interval: 30s
pr_timeout: 1h
projects:
- name: "my-project"
path: "~/Projects/my-project"
navigator: true
default_branch: main
daily_brief:
enabled: true
schedule: "0 8 * * *"
timezone: "Europe/Berlin"
alerts:
enabled: true
channels:
- name: telegram-alerts
type: telegram
severities: [critical, error, warning]
executor:
backend: claude-code # "claude-code" or "opencode"
| Feature | Description |
|---|---|
| **Telegram Bot** | Chat, research, planning, tasks + voice & images |
| **GitHub Polling** | Auto-pick issues with pilot label |
| **GitLab / Azure DevOps** | Full polling + webhook adapters |
| **Linear/Jira/Asana** | Webhooks and task sync |
| **Daily Briefs** | Scheduled reports via Slack/Email/Telegram |
| **Alerting** | Task failures, cost thresholds, stuck detection |
<details> <summary><strong>Is this safe?</strong></summary>
Pilot runs in your environment with your permissions. It can only access repos you configure. All changes go through PR review (unless you enable auto-merge). You stay in control. </details>
<details> <summary><strong>How much does it cost?</strong></summary>
Pilot is free. You pay for Claude API usage (~$0.50-2.00 per typical task). Set budget limits to control costs. </details>
<details> <summary><strong>What tasks can it handle?</strong></summary>
Best for: bug fixes, small features, refactoring, tests, docs, dependency updates.
Not ideal for: large architectural changes, security-critical code, tasks requiring human judgment. </details>
<details> <summary><strong>Does it learn my codebase?</strong></summary>
Yes. Pilot uses Navigator to understand your patterns, conventions, and architecture. Cross-project memory shares learnings across repositories. </details>
Pilot是实用的AI工作流引擎,解决开发流程自动化痛点。Go实现保障性能,活跃维护提升可信度,生产级应用潜力强。
该工具使用 NOASSERTION 协议,商用场景请仔细阅读协议条款,必要时咨询法律意见。
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。
📄 NOASSERTION — 请查阅原始协议条款了解具体使用限制。
AI Skill Hub 点评:Pilot AI工作流引擎 的核心功能完整,质量优秀。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 | pilot |
| 原始描述 | 开源AI工作流:#1 Terminal Benchmark 2.0 — AI that ships your tickets.。⭐469 · Go |
| Topics | AI智能体工作流自动化开发流程Go语言端到端交付 |
| GitHub | https://github.com/qf-studio/pilot |
| License | NOASSERTION |
| 语言 | Go |
收录时间:2026-05-21 · 更新时间:2026-05-22 · License:NOASSERTION · 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