经 AI Skill Hub 精选评估,Trinity AI工作流 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 8.0 分,适合有一定技术背景的用户使用。
Trinity 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。
Trinity 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。
# 方式一:pip 安装(推荐)
pip install trinity
# 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 trinity
# 方式三:从源码安装(获取最新功能)
git clone https://github.com/Abilityai/trinity
cd trinity
pip install -e .
# 验证安装
python -c "import trinity; print('安装成功')"
# 命令行使用
trinity --help
# 基本用法
trinity input_file -o output_file
# Python 代码中调用
import trinity
# 示例
result = trinity.process("input")
print(result)
# trinity 配置文件示例(config.yml) app: name: "trinity" debug: false log_level: "INFO" # 运行时指定配置文件 trinity --config config.yml # 或通过环境变量配置 export TRINITY_API_KEY="your-key" export TRINITY_OUTPUT_DIR="./output"
Autonomous agent orchestration and infrastructure
Deploy, orchestrate, and govern fleets of autonomous AI agents — with real-time observability, fleet-wide scheduling, agent-to-agent delegation, and complete audit trails. On your own infrastructure.
<p> <a href="https://github.com/abilityai/trinity/stargazers"><img src="https://img.shields.io/github/stars/abilityai/trinity?style=social" alt="Stars"></a> <a href="https://github.com/abilityai/trinity/blob/main/LICENSE"><img src="https://img.shields.io/badge/license-Polyform%20NC-blue.svg" alt="License"></a> <img src="https://img.shields.io/badge/python-3.11+-blue.svg" alt="Python"> <img src="https://img.shields.io/badge/vue-3.x-green.svg" alt="Vue"> <img src="https://img.shields.io/badge/docker-required-blue.svg" alt="Docker"> <a href="https://pypi.org/project/trinity-cli/"><img src="https://img.shields.io/pypi/v/trinity-cli?label=CLI&color=blue" alt="PyPI"></a> </p>
<p> <a href="#ways-to-use-trinity">How to Use</a> • <a href="#-quick-start">Quick Start</a> • <a href="#features">Features</a> • <a href="https://youtu.be/SWpNphnuPpQ">Demo Video</a> • <a href="#documentation">Docs</a> • <a href="#community--support">Community</a> • <a href="https://github.com/abilityai/trinity-ops-public">Ops Agent</a> </p>
<br/> <img src="docs/assets/trinity-explainer.gif" alt="Trinity Platform Overview" width="800"/> <br/><br/> <a href="https://youtu.be/ivljtZqsxeo"> <img src="https://img.shields.io/badge/▶_Watch_Full_Demo-YouTube-red?style=for-the-badge&logo=youtube" alt="Watch the Full Demo"> </a> <a href="https://github.com/abilityai/trinity-ops-public"> <img src="https://img.shields.io/badge/🤖_Ops_Agent-GitHub-black?style=for-the-badge&logo=github" alt="Trinity Ops Agent"> </a> <br/><br/> <img src="docs/assets/screenshots/graph-view-fleet.png" alt="Trinity Agent Fleet — Graph View" width="800"/> </div>
---
abilityai/abilities is the canonical development workflow for building and managing autonomous agents with Claude Code.
It provides 5 focused plugins covering the full agent lifecycle — from scaffolding and onboarding to deployment, scheduling, and ongoing operations:
| Plugin | What it does |
|---|---|
| **create-agent** | 12 wizards for agent scaffolding (prospector, chief-of-staff, webmaster, recon, receptionist, ghostwriter, kb-agent, website, custom, clone, adjust) |
| **agent-dev** | Add skills, memory systems, GitHub backlog workflow, autonomous work loops |
| **trinity** | Deploy to Trinity platform: connect, onboard, sync |
| **dev-methodology** | 14 skills for implementation, testing, security, and PR validation |
| **utilities** | Ops: incident investigation, safe deployment, Docker ops, batch processing |
```bash
brew install websocat jq
You need: a Trinity instance running somewhere (localhost or remote) and a local agent directory with CLAUDE.md and template.yaml.
```bash
pip install trinity-cli # or: brew install abilityai/tap/trinity-cli
cd my-agent/ trinity deploy .
trinity deploy . # updates the same agent ```
Already have a Claude Code agent? Deploy it with the Trinity plugin:
/plugin marketplace add abilityai/abilities
/plugin install trinity@abilityai
/trinity:onboard
After onboarding you get management skills: /trinity:sync (push/pull code), /trinity:remote (execute tasks), /trinity:schedules (cron automation).
```yaml
curl -fsSL https://raw.githubusercontent.com/abilityai/trinity/main/install.sh | bash
This will clone the repository, configure environment, build the base image, and start all services.
```bash
./scripts/deploy/build-base-image.sh
On first launch, Trinity will guide you through initial setup:
admin and your new password/plugin marketplace add abilityai/abilities
docker compose build backend docker compose up -d backend ```
| Guide | Use Case |
|---|---|
| [Trinity Compatible Agent Guide](docs/TRINITY_COMPATIBLE_AGENT_GUIDE.md) | **Single agents** — Template structure, CLAUDE.md, credentials, platform injection |
| [Multi-Agent System Guide](docs/MULTI_AGENT_SYSTEM_GUIDE.md) | **Multi-agent systems** — Architecture patterns, shared folders, coordination, deployment |
/plugin install trinity@abilityai /trinity:onboard
/plugin install create-agent@abilityai /create-agent:create ```
See the abilities repository for full plugin documentation and installation instructions.
cp .env.example .env
export TRINITY_API_KEY="trinity_mcp_xxx"
| Variable | Required | Description |
|---|---|---|
SECRET_KEY | Yes | JWT signing key (generate with openssl rand -hex 32) |
ADMIN_PASSWORD | Yes | Admin password for admin login |
ANTHROPIC_API_KEY | No | For Claude-powered agents (can also be set via Settings UI) |
GITHUB_PAT | No | GitHub PAT for cloning private template repos |
OTEL_ENABLED | No | Enable OpenTelemetry metrics export (default: false) |
EMAIL_PROVIDER | No | Email provider: console (dev), smtp, sendgrid, resend |
EXTRA_CORS_ORIGINS | No | Additional CORS origins |
See .env.example for the complete list.
curl -X POST http://localhost:8000/api/systems/deploy \ -H "Content-Type: application/json" \ -d '{"manifest": "...", "dry_run": false}' ```
See the Multi-Agent System Guide for architecture patterns and best practices.
Trinity includes an MCP server for external orchestration of agents:
{
"mcpServers": {
"trinity": {
"type": "streamable-http",
"url": "http://localhost:8080/mcp",
"headers": {
"Authorization": "Bearer YOUR_API_KEY"
}
}
}
}
| Feature | Trinity | Custom Build | LangChain/CrewAI | SaaS Platforms |
|---|---|---|---|---|
| Time to production | Minutes | 6-12 months | Weeks | Instant |
| Data sovereignty | ✅ | ✅ | ✅ | ❌ |
| Docker isolation per agent | ✅ | DIY | ❌ | ❌ |
| Fleet observability | ✅ | DIY | ❌ | Basic |
| Agent-to-agent delegation | ✅ | DIY | Limited | ❌ |
| Cron scheduling & autonomy | ✅ | DIY | ❌ | Limited |
| Cost tracking per agent | ✅ | DIY | ❌ | Basic |
| Complete audit trail | ✅ | DIY | ❌ | Basic |
| Multi-runtime (Claude/Gemini) | ✅ | DIY | ❌ | ❌ |
| State persistence (GitHub sync) | ✅ | DIY | Partial | Session-only |
| Open source | ✅ | N/A | ✅ | ❌ |
---
高质量的AI工作流平台
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:Trinity AI工作流 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 | trinity |
| Topics | AI工作流Python |
| GitHub | https://github.com/Abilityai/trinity |
| License | NOASSERTION |
| 语言 | Python |
收录时间:2026-06-03 · 更新时间:2026-06-03 · 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