能力标签
钛可
⚙️
Agent工作流

钛可

基于 Rust · 无代码搭建完整 AI 自动化流程
英文名:tiycode
⭐ 8 Stars 💻 Rust 📄 Apache-2.0 🏷 AI 7.5分
7.5AI 综合评分
AIRust桌面应用
✦ AI Skill Hub 推荐

经 AI Skill Hub 精选评估,钛可 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。

📚 深度解析

钛可 是一套完整的 AI Agent 自动化工作流方案。随着 AI 能力的不断提升,基于 Agent 的自动化工作流正在成为提升个人和团队效率的核心方式。区别于传统的 RPA 自动化(模拟鼠标键盘操作),AI Agent 工作流通过理解任务意图、动态规划执行路径,能够处理更复杂的非结构化任务。

钛可 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 7.5 分,是同类 Agent 工作流中的精选推荐。

📋 工具概览

钛可 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。

GitHub Stars
⭐ 8
开发语言
Rust
支持平台
Windows / macOS / Linux
维护状态
轻量级项目,按需更新
开源协议
Apache-2.0
AI 综合评分
7.5 分
工具类型
Agent工作流
Forks

📖 中文文档

以下内容由 AI Skill Hub 根据项目信息自动整理,如需查看完整原始文档请访问底部「原始来源」。

钛可 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。

📌 核心特色
  • 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
🎯 主要使用场景
  • 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
以下安装命令基于项目开发语言和类型自动生成,实际以官方 README 为准。
安装命令
# 方式一:cargo install(推荐)
cargo install tiycode

# 方式二:从源码编译
git clone https://github.com/tiylabs/tiycode
cd tiycode
cargo build --release
# 二进制在 ./target/release/tiycode
📋 安装步骤说明
  1. 访问 GitHub 仓库获取工作流文件
  2. 在对应平台(Dify / Flowise / Make 等)中找到「导入工作流」功能
  3. 上传工作流文件
  4. 按照提示配置必要的环境变量和 API Key
  5. 运行测试确认流程正常后投入使用
以下用法示例由 AI Skill Hub 整理,涵盖最常见的使用场景。
常用命令 / 代码示例
# 查看帮助
tiycode --help

# 基本运行
tiycode [options] <input>

# 详细使用说明请查阅文档
# https://github.com/tiylabs/tiycode
以下配置示例基于典型使用场景生成,具体参数请参照官方文档调整。
配置示例
# tiycode 配置说明
# 查看配置选项
tiycode --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 TIYCODE_CONFIG="/path/to/config.yml"
📑 README 深度解析 真实文档 完整度 72/100 含工作流图 查看 GitHub 原文 →
以下内容由系统直接从 GitHub README 解析整理,保留代码块、表格与列表结构。

简介

TiyCode logo

TiyCode

An AI-first desktop coding agent.

Designed for a new coding collaboration paradigm. Humans express goals, constraints, and feedback through conversation, while agents take the lead in understanding, execution, and forward progress.

简体中文

CI Release Downloads License Rust Platform


TiyCode screenshot

Highlights

  • AI-first coding collaboration. TiyCode is designed around the idea that humans express intent through conversation while agents take the lead in execution.
  • Agent Profiles. Mix models from different providers, tune response style, language, and custom instructions, and switch profiles flexibly for different kinds of work.
  • Three-tier model architecture. Each profile supports a Primary model for core reasoning, an Auxiliary model for helper tasks, and a Lightweight model for fast operations — with automatic fallback chains across tiers.
  • Multi-provider support. Connect to 13+ LLM providers out of the box — OpenAI, Anthropic, Google, Ollama, xAI, Groq, OpenRouter, DeepSeek, MiniMax, Kimi, and more — or add any OpenAI-compatible endpoint as a custom provider.
  • Workspace-centered execution. Threads stay grounded in the local workspace and connect naturally to code review, version control, repository inspection, Git worktrees, and terminal workflows.
  • Task-aware execution. Thread-scoped task boards, plan checkpoints, tool status events, and subagent progress make longer runs easier to follow and review.
  • Rich composer inputs. Prompt input supports text, file/photo attachments, screenshots, slash command structured argument interpolation (--key=value, positional args, {{placeholder}} templates), and large-paste handling.
  • Real-time execution streaming. A rich thread stream event system delivers live updates — message deltas, tool calls, requested/active statuses, reasoning steps, subagent progress, and plan updates — all rendered through purpose-built AI Elements components.
  • Operator-friendly experience. Slash commands with structured argument parsing, smart conversation titles, context compression controls, commit message generation, external terminal handoff including Ghostty, and compact workbench controls help the product feel fast and practical in day-to-day use.
  • Bilingual interface. Full i18n coverage with English and Simplified Chinese, switchable at any time.
  • Extensible by design. Plugins, MCP servers, and Skills are treated as first-class building blocks through the Extensions Center.
  • Built-in runtime path. The main execution flow is Frontend -> Rust Core -> BuiltInAgentRuntime -> tiycore -> LLM.

Install via Homebrew (macOS)

brew tap tiylabs/tap
brew install --cask tiycode

To upgrade later:

brew upgrade tiycode

Build from Source

Prerequisites

Before running the app, make sure your environment has the toolchain needed for a Tauri 2 project:

  • Node.js and npm
  • Rust toolchain
  • Platform dependencies required by Tauri

Run in development

npm install
npm run dev

Run the web UI only

npm install
npm run dev:web

Build

npm run build

Type-check the frontend

npm run typecheck

Run Rust tests

cargo test --manifest-path src-tauri/Cargo.toml

Shell Environment Setup

TiyCode's built-in agent shell may launch as a non-interactive, non-login shell. In this mode, only minimal system paths (e.g. /usr/bin:/bin) are available. Tools installed via version managers — such as node, npm, bun, cargo, or go — will not be found unless you configure your shell startup files correctly.

Quick Start

~/.zprofile — examples

eval "$(/opt/homebrew/bin/brew shellenv)" # Homebrew (macOS) export NVM_DIR="$HOME/.nvm" # nvm (Node.js) [ -s "$NVM_DIR/nvm.sh" ] && \. "$NVM_DIR/nvm.sh" export BUN_INSTALL="$HOME/.bun" # Bun export PATH="$BUN_INSTALL/bin:$PATH" . "$HOME/.local/bin/env" # Rust / Cargo export PATH="/usr/local/go/bin:$PATH" # Go


</details>

<details>
<summary><strong>Linux (Bash)</strong></summary>

1. Keep environment variables in `~/.bash_profile` (or `~/.profile`).
2. Set `BASH_ENV` to point to a file that sources your profile:
bash

How Shell Config Files Are Loaded

Different shell invocation modes load different config files. The table below shows which files are sourced in each mode:

Zsh (macOS default / Linux)

FileNon-interactiveLoginInteractiveInteractive + Login
~/.zshenv
~/.zprofile
~/.zshrc

Bash (Linux default)

FileNon-interactiveLoginInteractiveInteractive + Login
~/.bashrc❌ ¹
~/.bash_profile
$BASH_ENV

<sub>¹ Most distros source ~/.bashrc from ~/.bash_profile, so in practice it runs for login shells too.</sub>

TiyCode's agent shell falls into the non-interactive column — only ~/.zshenv (zsh) or $BASH_ENV (bash) is guaranteed to load.

Fix: Ensure Environment Variables Load for All Shell Modes

<details> <summary><strong>macOS / Linux (Zsh)</strong></summary>

  1. Move all export statements and PATH modifications from ~/.zshrc into ~/.zprofile. Keep interactive-only settings (aliases, completions, oh-my-zsh, themes, prompt) in ~/.zshrc.
  1. Source ~/.zprofile from ~/.zshenv so that non-interactive shells also get the environment:

```bash

~/.zshenv

if [ -z "$__ZPROFILE_LOADED" ] && [ -f "$HOME/.zprofile" ]; then export __ZPROFILE_LOADED=1 source "$HOME/.zprofile" fi


The `__ZPROFILE_LOADED` guard prevents double-loading in login + interactive shells.

Common items to move into `~/.zprofile`:
bash

~/.bash_env — new file

if [ -z "$__BASH_PROFILE_LOADED" ] && [ -f "$HOME/.bash_profile" ]; then export __BASH_PROFILE_LOADED=1 source "$HOME/.bash_profile" fi


</details>

<details>
<summary><strong>Windows (PowerShell)</strong></summary>

On Windows, TiyCode typically inherits the system and user environment variables set via **System Settings > Environment Variables**. If you installed Node.js, Rust, or other tools via their official installers, they should already be on PATH.

If you use a version manager like **nvm-windows**, **fnm**, or **volta**, make sure the shim directory is added to your **User PATH** in system environment variables — not only in a PowerShell profile.

To verify your current PATH in PowerShell:
powershell $env:PATH -split ';' ```

</details>

Verify After Configuration

After updating your shell config files, restart TiyCode (a full quit + relaunch, not just a new thread) and ask the agent to run:

echo $PATH
which <your-tool>   # e.g. node, cargo, go, bun, python ...

If the output includes the expected paths and the tool is found, your environment is correctly configured.

Continuous Integration

Pull requests to master run GitHub Actions checks for commit message format, frontend type-checking, Vitest unit tests, web asset builds, Rust formatting, and locked Rust tests. An optional PR review workflow can run TiyAgents/code-review-agent-action when the required LLM secrets and variables are configured.

Extensions Model

TiyCode treats extensibility as a first-class part of the desktop workbench.

  • Plugins provide locally installed extension packages with hooks, tools, commands, and skill packs.
  • MCP is modeled as its own extension category and managed by the Rust host, including user/workspace scoped configuration.
  • Skills act as reusable agent capability assets and are indexed from builtin, workspace, or plugin sources.
  • Provider catalogs are bundled as snapshots and can be normalized or refreshed so model capabilities stay aligned with runtime behavior.

These capabilities are surfaced through the Extensions Center, while runtime access is still governed by the host through tool gateways, policy checks, approvals, and audit boundaries.

Troubleshooting & Debugging

When something goes wrong — model requests not being sent, responses not arriving, or behavior not matching expectations — you can use the RUST_LOG environment variable to control log verbosity on the Rust / tiycore side.

RUST_LOG valueWhat you get
RUST_LOG=tiycore=debugModel request metadata and response content summaries — good for verifying which model is called, what prompt is sent, and whether a response is received.
RUST_LOG=tiycore=traceFull SSE stream data including every chunk — useful when you need to inspect raw streaming payloads or diagnose streaming-level issues.
RUST_LOG=debugDebug-level logs for **all** crates (noisy, but covers the entire stack).
RUST_LOG=infoDefault level — informational messages only.
📚 实用指南(长尾问题)
适合谁
  • 需要让 Claude / Cursor 操作本地工具的 AI 工程师
  • 构建多智能体协作系统的 Agent 开发者
  • 跨境业务、多语言内容运营团队
最佳实践
  • 配置 MCP 服务器时建议使用 stdio 传输 + JSON-RPC,避免暴露公网
  • 本地部署优先选 GGUF 量化模型,节省显存并保持响应速度
  • Agent 任务先做 dry-run 验证工具调用链,再开启自主执行
常见错误
  • API key 直接提交到 git 仓库(请用 .env 并加入 .gitignore)
  • MCP 配置路径拼错或权限不足,重启 Claude Desktop 才生效
  • 显存不足直接 OOM — 优先降低 context 或换更小的量化模型
部署方案
  • CLI:直接 npm install -g / pip install,命令行调用
  • 本地部署:CPU 8GB 起,GPU 推荐 16GB+ 显存
  • 云端托管:可放在 Vercel / Railway / Fly.io 等 PaaS 平台
相关搜索
tiycode 中文教程tiycode 安装报错怎么办tiycode MCP 配置tiycode Agent 工作流tiycode 与同类工具对比tiycode 最佳实践tiycode 适合谁用

⚡ 核心功能

👥 适合谁
  • 需要让 Claude / Cursor 操作本地工具的 AI 工程师
  • 构建多智能体协作系统的 Agent 开发者
  • 跨境业务、多语言内容运营团队
⭐ 最佳实践
  • 配置 MCP 服务器时建议使用 stdio 传输 + JSON-RPC,避免暴露公网
  • 本地部署优先选 GGUF 量化模型,节省显存并保持响应速度
  • Agent 任务先做 dry-run 验证工具调用链,再开启自主执行
⚠️ 常见错误
  • API key 直接提交到 git 仓库(请用 .env 并加入 .gitignore)
  • MCP 配置路径拼错或权限不足,重启 Claude Desktop 才生效
  • 显存不足直接 OOM — 优先降低 context 或换更小的量化模型

👥 适合人群

自动化工程师和运维人员项目经理和业务分析师希望减少重复性工作的专业人士数字化转型团队

🎯 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

✅ 优点
  • +Apache-2.0 协议,可免费商用
  • +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
⚠️ 不足
  • 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
⚠️ 使用须知

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。

📄 License 说明

✅ 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。

🔗 相关工具推荐

📰 相关 AI 新闻
🍿 AI 圈相关吃瓜
🗺️ 相关解决方案
🧩 你可能还需要
基于当前 Skill 的能力图谱,自动补全的工具组合

❓ 常见问题 FAQ

tiycode 是一款Rust开发的AI辅助工具。开源AI工作流:TiyCode is an AI-first desktop coding agent. “钛可”是一款践行 AI First 理念的桌面版 Vibe-Codi。⭐8 · Rust 主要应用场景包括:编码辅助。
💡 AI Skill Hub 点评

AI Skill Hub 点评:钛可 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。

⬇️ 获取与下载
⬇ 下载源码 ZIP

✅ Apache-2.0 协议 · 可免费商用 · 直接从 aiskill88 服务器下载,无需跳转 GitHub

📚 深入学习 钛可
查看分步骤安装教程和完整使用指南,快速上手这款工具
🌐 原始信息
原始名称 tiycode
原始描述 开源AI工作流:TiyCode is an AI-first desktop coding agent. “钛可”是一款践行 AI First 理念的桌面版 Vibe-Codi。⭐8 · Rust
Topics AIRust桌面应用
GitHub https://github.com/tiylabs/tiycode
License Apache-2.0
语言 Rust
🔗 原始来源
🐙 GitHub 仓库  https://github.com/tiylabs/tiycode

收录时间:2026-05-25 · 更新时间:2026-05-30 · License:Apache-2.0 · AI Skill Hub 不对第三方内容的准确性作法律背书。