智能工作流 是 AI Skill Hub 本期精选Agent工作流之一。综合评分 7.5 分,整体质量较高。我们推荐使用将其纳入你的 AI 工具库,帮助提升工作效率。
智能工作流 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。
智能工作流 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。
# 方式一:go install(推荐) go install github.com/genai-io/san@latest # 方式二:从源码编译 git clone https://github.com/genai-io/san cd san go build -o san . # 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/genai-io/san/releases
# 查看帮助 san --help # 基本运行 san [options] <input> # 详细使用说明请查阅文档 # https://github.com/genai-io/san
# san 配置说明 # 查看配置选项 san --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 SAN_CONFIG="/path/to/config.yml"
San is a terminal-native unified runtime for specialized agents — coding and beyond — built on five pluggable pillars: LLMs, search backends, personas, skills & extensions (skills, plugins, MCP servers, subagents), and a self-evolving agent that levels up as you work. Written in Go.
<sub>The name — San, written 三 ("three") and drawn ☰. From the Dao De Jing, 三生万物 — "three begets the ten-thousand things": one runtime that becomes any agent, running a three-step loop (reason → act → observe). The command stays san.</sub>
curl -fsSL https://raw.githubusercontent.com/genai-io/san/main/install.sh | bash
Re-run to upgrade. To uninstall:
curl -fsSL https://raw.githubusercontent.com/genai-io/san/main/install.sh | bash -s uninstall
<details> <summary><b>Other methods</b></summary>
Go Install
go install github.com/genai-io/san/cmd/san@latest
Build from Source
git clone https://github.com/genai-io/san.git
cd san
go build -o san ./cmd/san
mkdir -p ~/.local/bin && mv san ~/.local/bin/
</details>
san # interactive
san "explain this function" # one-shot
cat main.go | san "review" # piped input
san --continue # resume latest session
san --resume # pick a past session
san inspector # open session transcript viewer
| What | How |
|---|---|
| Pick / switch model | /model — saved to ~/.san/providers.json |
| Cycle thinking budget | Ctrl+T or /think (levels vary by provider) |
| All slash commands | /help (/identity, /search, /skills, /agents, /mcp, /compact, …) |
| Toggle permission mode | Shift+Tab (ask · auto-accept · plan) |
| Expand tool · cancel · exit | Ctrl+O · Ctrl+C · Ctrl+D |
For API keys, set the matching env var (see Credentials below) or paste when prompted on first launch. Full walkthrough: docs/guides/getting-started.md.
Config lives in ~/.san/ (user) and <project>/.san/ (project, overrides user). A SAN.md or CLAUDE.md at the project root is auto-loaded into the system prompt.
<details> <summary><b>Credentials</b></summary>
| Service | Variable |
|---|---|
| **Anthropic** (Claude) | ANTHROPIC_API_KEY or [Vertex AI](https://cloud.google.com/vertex-ai/generative-ai/docs/partner-models/claude) |
| **OpenAI** (GPT, o-series, Codex) | OPENAI_API_KEY |
| **Google** (Gemini) | GOOGLE_API_KEY |
| **Moonshot** (Kimi) | MOONSHOT_API_KEY |
| **DeepSeek** (DeepSeek V4) | DEEPSEEK_API_KEY |
| **Alibaba** (Qwen) | DASHSCOPE_API_KEY |
| **MiniMax** | MINIMAX_API_KEY |
| **Z.ai** (GLM) | BIGMODEL_API_KEY |
| **Ollama** (local) | OLLAMA_BASE_URL (default http://localhost:11434/v1) |
| **Exa** search | _none_ (default) |
| **Tavily** search | TAVILY_API_KEY |
| **Brave** search | BRAVE_API_KEY |
| **Serper** search | SERPER_API_KEY |
</details>
<details> <summary><b>Directory layout</b></summary>
User-level (~/.san/):
providers.json # Provider connections and current model
settings.json # Permissions, hooks, env, identity
skills.json # Skill states
identities/ # Custom personas (see /identity)
skills/ # Custom skill definitions
agents/ # Custom agent definitions
commands/ # Custom slash commands
plugins/ # Installed plugins
projects/ # Session transcripts + indexes
Project-level (.san/):
settings.json # Permissions, hooks, disabled tools
mcp.json # MCP server definitions
identities/*.md # Project-scoped personas (override user-level)
agents/*.md # Subagent definitions
skills/*/SKILL.md # Skills
commands/*.md # Slash commands
</details>
Compared with Claude Code v2.1.112 on Apple Silicon, same model (claude-sonnet-4-6):
| Metric | San | Claude Code | Advantage |
|---|---|---|---|
| Download size | 12 MB | 63 MB (+ Node.js 112 MB) | **5x smaller** |
| Disk footprint | 38 MB | 175 MB | **4.6x smaller** |
| Startup time | ~0.01s | ~0.20s | **20x faster** |
| Startup memory | ~32 MB | ~189 MB | **5.8x less** |
| Simple task | ~2.4s / 39 MB | ~10.4s / 286 MB | **4.3x faster, 7.3x less memory** |
| Tool-use task | ~3.3s / 39 MB | ~26.0s / 285 MB | **7.9x faster, 7.2x less memory** |
Both tools have comparable features (hooks, skills, plugins, session, MCP, etc.). The performance gap comes from Go's native compilation, minimal architecture design, and lean prompt engineering — vs Node.js V8/JIT/GC runtime overhead.
See full details: docs/operations/benchmark.md
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。
✅ Apache 2.0 — 宽松开源协议,可商用,需保留版权声明和 NOTICE 文件,含专利授权条款。
经综合评估,智能工作流 在Agent工作流赛道中表现稳健,质量良好。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 | san |
| 原始描述 | 开源AI工作流:Open-source AI agent. Lives in your terminal.。⭐39 · Go |
| Topics | ai-agentsautomationcli |
| GitHub | https://github.com/genai-io/san |
| License | Apache-2.0 |
| 语言 | Go |
收录时间:2026-06-05 · 更新时间:2026-06-08 · License:Apache-2.0 · 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