开源AI工作流
开源AI工作流 是 AI Skill Hub 本期精选Agent工作流之一。综合评分 8.0 分，整体质量较高。我们强烈推荐将其纳入你的 AI 工具库，帮助提升工作效率。
📚 深度解析
开源AI工作流 工作流的设计遵循"最小配置，最大复用"原则：核心逻辑已经封装好，用户只需配置自己的 API Key 和业务参数即可快速上手。工作流内置错误处理和重试机制，在网络波动或 API 限速等情况下仍能稳定运行，适合作为生产环境的自动化基础设施。
在实际部署时，建议先在测试环境中运行 3-5 次，验证各个环节的输出结果符合预期，再部署到生产环境。AI Skill Hub 评分 8.0 分，是同类 Agent 工作流中的精选推荐。
📋 工具概览
开源AI工作流 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。
📖 中文文档
开源AI工作流 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。
- 可视化 Agent 工作流编排，无需编写复杂代码
- 支持多步骤自动化任务链，实现全流程无人值守
- 与外部 API、数据库和第三方服务无缝集成
- 内置错误处理与自动重试机制，保障稳定运行
- 提供可复用的自动化模板，快速在同类场景部署
- 自动化日常重复性工作，将精力集中于创造性任务
- 构建数据采集 → 处理 → 输出的完整自动化管线
- 实现跨平台、跨系统的数据流转和业务协同
# 方式一：pip 安装（推荐）
pip install openprogram
# 方式二：虚拟环境安装（推荐生产环境）
python -m venv .venv
source .venv/bin/activate # Windows: .venv\Scripts\activate
pip install openprogram
# 方式三：从源码安装（获取最新功能）
git clone https://github.com/Fzkuji/OpenProgram
cd OpenProgram
pip install -e .
# 验证安装
python -c "import openprogram; print('安装成功')"
- 访问 GitHub 仓库获取工作流文件
- 在对应平台（Dify / Flowise / Make 等）中找到「导入工作流」功能
- 上传工作流文件
- 按照提示配置必要的环境变量和 API Key
- 运行测试确认流程正常后投入使用
# 命令行使用
openprogram --help
# 基本用法
openprogram input_file -o output_file
# Python 代码中调用
import openprogram
# 示例
result = openprogram.process("input")
print(result)
# openprogram 配置文件示例（config.yml） app: name: "openprogram" debug: false log_level: "INFO" # 运行时指定配置文件 openprogram --config config.yml # 或通过环境变量配置 export OPENPROGRAM_API_KEY="your-key" export OPENPROGRAM_OUTPUT_DIR="./output"
简介
<p align="center"> <img src="docs/images/logo.svg" alt="OpenProgram" width="300"> </p>
<p align="center"> <b>Open-Source, General-Purpose Agent Harness — Build Your Workflows in Python.</b><br/> Any LLM · Any Platform </p>
<p align="center"> <a href="https://github.com/Fzkuji/OpenProgram/releases/tag/v0.4.0"><img alt="Release" src="https://img.shields.io/github/v/release/Fzkuji/OpenProgram?style=flat-square&color=blue"></a> <a href="https://github.com/Fzkuji/OpenProgram/blob/main/LICENSE"><img alt="License" src="https://img.shields.io/badge/license-AGPL--3.0-green?style=flat-square"></a> <a href="https://www.python.org/"><img alt="Python" src="https://img.shields.io/badge/python-3.11%2B-blue?style=flat-square"></a> <img alt="Platforms" src="https://img.shields.io/badge/platforms-macOS%20%7C%20Linux%20%7C%20Windows-lightgrey?style=flat-square"> <a href="https://github.com/Fzkuji/OpenProgram/actions/workflows/ci.yml"><img alt="Build status" src="https://img.shields.io/github/actions/workflow/status/Fzkuji/OpenProgram/ci.yml?branch=main&style=flat-square&label=build"></a> <a href="https://github.com/Fzkuji/GUI-Agent-Harness"><img alt="OSWorld" src="https://img.shields.io/badge/OSWorld_Multi--Apps-79.8%25-brightgreen?style=flat-square"></a> <a href="https://github.com/Fzkuji/OpenProgram/stargazers"><img alt="GitHub stars" src="https://img.shields.io/github/stars/Fzkuji/OpenProgram?style=flat-square"></a> </p>
<p align="center"> <a href="docs/GETTING_STARTED.md">Getting Started</a> · <a href="docs/README.md">Docs</a> · <a href="docs/API.md">API Reference</a> · <a href="docs/philosophy/agentic-programming.md">Philosophy</a> · <a href="docs/README_CN.md">中文</a> </p>
---
"The more constraints one imposes, the more one frees oneself." — Igor Stravinsky, Poetics of Music
We propose Agentic Programming. An LLM is flexible; code is deterministic. Let the model run everything and you get chaos — unpredictable execution, context explosion, no output guarantees; hard-code everything and you lose the intelligence. A harness balances the two, interleaved moment to moment — Python for the flow you want fixed, the LLM for the judgement you can't script. (the full rationale →)
<p align="center"> <img src="docs/images/why-openprogram.png" alt="Why OpenProgram — deterministic flow, run anywhere, automatic DAG context, any LLM / any provider, self-evolving workflows" width="900"> </p>
- Deterministic flow, flexible reasoning — Python drives the control flow; the LLM reasons only when asked.
- Run it anywhere — native on macOS / Linux / Windows, via terminal, browser, or chat (no WSL, no Docker).
- Automatic context — a shared DAG threads context into every call; multi-agent ready.
- Any LLM, any provider — API key, or the CLI subscription you already pay for.
- Self-evolving workflows — the agent builds, runs, and improves its own workflows and tools.
Detailed features
| Feature | One-line summary |
|---|---|
| **Automatic context** | Every @agentic_function call is a tree node; the runtime threads it through nested LLM calls — no manual prompt assembly. |
| **Deep work** | deep_work(task, level) runs an autonomous plan → execute → evaluate → revise loop until the output meets the chosen quality bar. State persists to disk. |
| **Functions that author functions** | New / fixed @agentic_functions are written by the agent itself via ordinary file-editing tools, guided by the agentic-programming skill. No dedicated create() / fix() calls. |
| **Conversation as a git DAG** | Sessions are commits + branches + merges + cherry-picks, with the right sidebar exposing the operations. File-touching branches run in isolated git worktrees. |
| **Layered memory** | Six stores under ~/.openprogram/memory/ (journal / wiki / sleep / scheduler / recall_counts / store), each for a different timescale. The agent picks the layer. |
| **Mini-DAG execution view** | The right rail draws every node + edge of the active session, scrolls with the chat, and offers a d3-hierarchy layout for fan-out-heavy traces. |
| **Multi-agent + multi-channel** | Every row tagged with its producer agent; channel layer wires external transports (Discord today, more coming). |
The detailed tour of each one — code samples, design rationale, where to look in the codebase — lives in docs/features.md.
1. Install
macOS / Linux
git clone https://github.com/Fzkuji/OpenProgram && cd OpenProgram
./scripts/install.shWindows (PowerShell)
git clone https://github.com/Fzkuji/OpenProgram; cd OpenProgram
.\scripts\install.ps1One command installs the OpenProgram host — web UI, terminal UI, and the browser tool + chat channels. The first run of openprogram opens a setup wizard whose Agent programs step offers the bundled harnesses (GUI / Research / Wiki) with their sizes — or add them any time, see step 3. Flags and per-OS notes: docs/install.md.
Quick Start
How to use
Two ways to interact day-to-day — same backend, same sessions, switch freely.
CLI use
Beyond the chat UIs, the openprogram command runs headless — script it, pipe it, automate it.
```bash
Integration
| Guide | Description |
|---|---|
| [Getting Started](docs/GETTING_STARTED.md) | 3-minute setup and runnable examples |
| [Claude Code](docs/INTEGRATION_CLAUDE_CODE.md) | Use without API key via Claude Code CLI |
| [OpenClaw](docs/INTEGRATION_OPENCLAW.md) | Use as OpenClaw skill |
| [API Reference](docs/API.md) | Full API documentation |
<details> <summary><strong>Project Structure</strong></summary>
openprogram/
├── __init__.py # agentic_function re-export
├── cli.py # `openprogram` command entry point
├── agentic_programming/ # engine — paradigm-essential primitives
│ ├── function.py # @agentic_function decorator
│ ├── runtime.py # Runtime (exec + retry + DAG context)
│ ├── session.py # session lifecycle
│ └── skills.py # SKILL.md discovery
├── context/ # flat-DAG context model — nodes, storage, render, compute_reads
├── providers/ # Anthropic, OpenAI, Gemini, Claude Code, Codex, Gemini CLI
├── functions/
│ ├── _registry.py # unified registry for tools + agentic functions
│ ├── tools/ # @function leaves — bash, read, edit, grep, semble_search, web_search, …
│ └── agentics/ # @agentic_function modules (each its own dir, code in __init__.py)
│ ├── ask_user/ # ask the user a clarifying question
│ ├── deep_work/ # autonomous plan-execute-evaluate loop
│ ├── extract_pdf_figures/ # PDF figure extraction
│ ├── … # other agentics …
│ ├── GUI-Agent-Harness/ # GUI agent (separate repo, cloned in)
│ ├── Research-Agent-Harness/ # Research agent (separate repo, cloned in)
│ └── Wiki-Agent-Harness/ # Wiki agent (separate repo, cloned in)
└── webui/ # `openprogram web` — browser UI
skills/ # SKILL.md files for agent integration
examples/ # runnable demos
tests/ # pytest suite</details>
Troubleshooting
Two diagnostic commands cover most "it broke and I don't know why" situations:
openprogram rescue # 11 platform-agnostic probes, each with a fix command
openprogram doctor # quick "is the install healthy?" check
openprogram logs tail # follow the worker log live
openprogram providers doctor # OAuth tokens — expiring? refresh wired?rescue is the one to reach for first when something doesn't work — it doesn't depend on an LLM being reachable, walks through provider config, ports, dependencies, build artefacts, and prints the exact command to fix each finding. Case-by-case docs live in docs/troubleshooting.md.
For platform-builder topics (Runtime retry semantics, the full @agentic_function decorator API, the flat-DAG context model) see docs/API.md and the per-topic notes under docs/api/.
高质量开源AI工作流框架，支持多平台和LLM
⚡ 核心功能
- 可视化 Agent 工作流编排，无需编写复杂代码
- 支持多步骤自动化任务链，实现全流程无人值守
- 与外部 API、数据库和第三方服务无缝集成
- 内置错误处理与自动重试机制，保障稳定运行
- 提供可复用的自动化模板，快速在同类场景部署
👥 适合人群
🎯 使用场景
- 自动化日常重复性工作，将精力集中于创造性任务
- 构建数据采集 → 处理 → 输出的完整自动化管线
- 实现跨平台、跨系统的数据流转和业务协同
⚖️ 优点与不足
- +大幅减少重复性人工操作
- +可视化流程，清晰直观
- +可扩展性强，支持复杂场景
- −初始配置和调试需投入一定时间
- −强依赖外部服务的稳定性
- −复杂场景需具备一定技术基础
该工具使用 AGPL-3.0 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。
⚠️ AGPL 3.0 — 最严格的 Copyleft，网络服务端使用也需开源，SaaS 使用受限。
🔗 相关工具推荐
❓ 常见问题 FAQ
经综合评估，开源AI工作流 在Agent工作流赛道中表现稳健，质量优秀。如果你已有明确的使用需求，可以直接上手体验；如果还在评估阶段，建议对比同类工具后再做决策。
| 原始名称 | OpenProgram |
| Topics | ai-agentagenticanthropicclaude |
| GitHub | https://github.com/Fzkuji/OpenProgram |
| License | AGPL-3.0 |
| 语言 | Python |
收录时间：2026-06-17 · 更新时间：2026-06-17 · License：AGPL-3.0 · AI Skill Hub 不对第三方内容的准确性作法律背书。